GPT-5.6 Sol

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: $OneMillion-Bench (expert score) · reviewed 2026-09-12

Grok High; GPT-5.6 Sol Max; Fable 5 Max. Competitor figures from developer cards/public leaderboards as selected by xAI.

First-party reported result; comparator results retain the source evaluation setup.

Grok 4.6 launch evaluations · Performance table · reviewed 2026-09-06

Artificial Analysis long-horizon knowledge projects; rubric and panel pairwise judging; Claude max effort.

Claude Fable 5.1 and Claude Mythos 5.1 System Card · Table8.1.A;8.15.4 · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

Cited result; see benchmark-specific Evaluation Details.

Comparison limit: Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison.

moonshotai/Kimi-K3 · Performance table: AA-Briefcase (Elo) · reviewed 2026-09-12

Grok High; GPT-5.6 Sol Max; Fable 5 Max. Competitor figures from developer cards/public leaderboards as selected by xAI.

First-party reported result; comparator results retain the source evaluation setup.

Grok 4.6 launch evaluations · Performance table · reviewed 2026-09-06

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

Cited result; see benchmark-specific Evaluation Details.

Comparison limit: Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison.

moonshotai/Kimi-K3 · Performance table: AA-LCR · reviewed 2026-09-12

Internal composite instruction-following evaluations; no fixed task count; reasoning max

Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Computer Use table / Agents' Last Exam / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Professional table / Agents' Last Exam / GPT‑5.6 Sol · reviewed 2026-09-06

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

Cited result; see benchmark-specific Evaluation Details.

Comparison limit: Kimi K3 Evaluation Details cites official Agents Last Exam leaderboard; retain as published context, not a new Moonshot comparison.

moonshotai/Kimi-K3 · Performance table: Agents' Last Exam · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: Agents' Last Exam (ALE-CLI) · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Pass

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: Agents' Last Exam (Pass / Score) · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Score

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: Agents' Last Exam (Pass / Score) · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: AndroidBench · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

Cited result; see benchmark-specific Evaluation Details.

Comparison limit: Kimi K3 Evaluation Details cites Artificial Analysis / APEX-Agents leaderboard; retain as published context, not a new Moonshot comparison.

moonshotai/Kimi-K3 · Performance table: APEX-Agents · reviewed 2026-09-12

Grok High; GPT-5.6 Sol Max; Fable 5 Max. Competitor figures from developer cards/public leaderboards as selected by xAI.

First-party reported result; comparator results retain the source evaluation setup.

Grok 4.6 launch evaluations · Performance table · reviewed 2026-09-06

ARC Prize semi-private validation; verified Fable5.1 max effort; comparator figures as reported in summary.

Claude Fable 5.1 and Claude Mythos 5.1 System Card · Table8.1.A;8.16 · reviewed 2026-09-12

ARC Prize semi-private validation; verified Fable5.1 max effort; comparator figures as reported in summary.

Claude Fable 5.1 and Claude Mythos 5.1 System Card · Table8.1.A;8.16 · reviewed 2026-09-12

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Abstract Reasoning table / ARC-AGI-1 / GPT‑5.6 Sol · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Abstract Reasoning table / ARC-AGI-2 / GPT‑5.6 Sol · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Abstract Reasoning table / ARC-AGI-3 / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Abstract Reasoning table / ARC-AGI-3 / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Coding table / Artificial Analysis Coding Agent Index v1.1 / GPT‑5.6 Sol · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Coding table / Artificial Analysis Coding Agent Index v1.4 / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Professional table / Artificial Analysis Intelligence Index v4.1 / GPT‑5.6 Sol · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Professional table / Artificial Analysis Intelligence Index v4.1.1 / GPT‑5.6 Sol · reviewed 2026-09-06

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: Automation-Bench (Pass@1) · reviewed 2026-09-12

Private held-out board; simulated business-workflow app APIs; all assertions must pass; max effort stated for Fable5.1/Opus5.

Claude Fable 5.1 and Claude Mythos 5.1 System Card · Table8.1.A;8.15.6 · reviewed 2026-09-12

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Professional table / AutomationBench / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Tool Use table / AutomationBench / GPT‑5.6 Sol · reviewed 2026-09-06

600public workflow tasks; deterministic end-state assertions;pass@1; reasoning max

Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: AutomationBench · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: AutomationBench (v1.0.6) · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: BabyVision w/ python · reviewed 2026-09-12

Maximum reported across reasoning efforts; OpenAI research environment or API; tools enabled

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Professional table / BenchCAD / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Computer Use table / BenchCAD / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified; Python tool enabled

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Computer Use table / BenchCAD (python tool) / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Professional table / Big Finance Bench / GPT‑5.6 Sol · reviewed 2026-09-06

Anthropic life-sciences evaluation; bash/editor/packages except protein design no tools; protocols use bash/editor/search; Understanding revised network restriction.

Internal evaluation; not necessarily publicly released; compare only same task/grader revision. Percent rank correlation is not accuracy.

Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.19 · reviewed 2026-09-12

Linuxterminal,bioinfotools,Python,R; allowlistednetwork; Gemini/GPTselfcomputed,Claudeproviderreports

Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06

Anthropic life-sciences evaluation; bash/editor/packages except protein design no tools; protocols use bash/editor/search; Understanding revised network restriction.

Internal evaluation; not necessarily publicly released; compare only same task/grader revision. Percent rank correlation is not accuracy.

Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.19 · reviewed 2026-09-12

Linuxterminal,bioinfotools,Python,R; allowlistednetwork; Gemini/GPTselfcomputed,Claudeproviderreports

Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Professional table / BrowseComp / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Computer Use table / BrowseComp / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified; Ultra, four-agent orchestration

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Computer Use table / BrowseComp / GPT‑5.6 Sol Ultra · reviewed 2026-09-06

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

Cited result; see benchmark-specific Evaluation Details.

Comparison limit: Kimi K3 Evaluation Details cites Anthropic or OpenAI release reports; retain as published context, not a new Moonshot comparison.

moonshotai/Kimi-K3 · Performance table: BrowseComp · reviewed 2026-09-12

Launch table reported configuration; per-cell reasoning effort unspecified; reduced or absent production safeguards

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Cybersecurity table / Capture-the-Flag Challenges / GPT‑5.6 Sol · reviewed 2026-09-06

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. without tools Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: CharXiv (RQ) · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. with tools Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: CharXiv (RQ) · reviewed 2026-09-12

No tools; Gemini/GPT/Opus selfcomputed; Sonnet selfreported

Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06

System-card reported configuration; reasoning effort unspecified

Observed named-model performance; helpful-only checkpoint omitted as distinct noncatalog identity.

GPT-6 Astra System Card · Section10.1.1.2.3 · reviewed 2026-09-06

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

Cited result; see benchmark-specific Evaluation Details.

Comparison limit: Kimi K3 Evaluation Details cites Vals AI; retain as published context, not a new Moonshot comparison.

moonshotai/Kimi-K3 · Performance table: CorpFin v2 · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Internal professional work tasks across science,finance,law,medical,productivity.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: CoWorkBench · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

Cited result; see benchmark-specific Evaluation Details.

Comparison limit: Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison.

moonshotai/Kimi-K3 · Performance table: CritPt · reviewed 2026-09-12

Cursor production agent harness; independently measured by Cursor; max effort.

Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.8 · reviewed 2026-09-12

Grok High; GPT-5.6 Sol Max; Fable 5 Max. Competitor figures from developer cards/public leaderboards as selected by xAI.

First-party reported result; comparator results retain the source evaluation setup.

Grok 4.6 launch evaluations · Performance table · reviewed 2026-09-06

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: CyberGym · reviewed 2026-09-12

900questions; common search backend/browser harness; answer-set F1; reasoning max

Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06

Datacurve highest reported effort; Gemini3.8selfcomputed mini-swe-agent highthinking

Card Opus74 explicitly corrected as erroneous in linkedmethodology; omitted.

Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06

113tasks; Muse1.3mini-swe-agent; comparators officialDatacurve board; reasoning max

Opus74 omitted because Google current methodology explicitly identifies that board-rounded value as incorrect; underlying precision unresolved.

Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: DeepSWE · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: DeepSWE (v1.1) · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Best of Claude Code and mini-SWE-agent; Qwen best Claude Code; temp1,top_p.95,256K.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: DeepSWE 1.1 · reviewed 2026-09-12

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Coding table / DeepSWE v1.1 / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Coding table / DeepSWE v1.1 / GPT‑5.6 Sol · reviewed 2026-09-06

Grok High; GPT-5.6 Sol Max; Fable 5 Max. Competitor figures from developer cards/public leaderboards as selected by xAI.

First-party reported result; comparator results retain the source evaluation setup.

Grok 4.6 launch evaluations · Performance table · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API; reduced or absent production safeguards

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Cybersecurity table / ExploitBench / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified; reduced or absent production safeguards; ExploitBench API harness; five seeds; reasoning continuity

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Cybersecurity table / ExploitBench / GPT‑5.6 Sol · reviewed 2026-09-06

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: ExploitBench · reviewed 2026-09-12

Maximum reported across reasoning efforts; OpenAI research environment or API; reduced or absent production safeguards; 20 vulnerabilities / 13 Chrome releases; 300-turn limit

Provider-published result; comparator measurements are not automatically independently reproduced. Footnote14 separately reports11.5% with fewer turn-limit interruptions; main table remains5.5%.

GPT-6 Astra: A new generation of intelligence · Cybersecurity table / ExploitBench (June-Aug 2026) / GPT‑5.6 Sol · reviewed 2026-09-06

Similar settings with fewer300-turn-limit interruptions; production safeguards absent

Provider-published result; preserves source setting without claiming a controlled cross-provider comparison.

GPT-6 Astra: A new generation of intelligence · Footnote14 · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API; reduced or absent production safeguards; v1 offline environment; no runtime package installation; token capped, no wall-clock cap

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Cybersecurity table / ExploitGym / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified; reduced or absent production safeguards; six-hour evaluation cap; alpha API latency rescaled to public API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Cybersecurity table / ExploitGym / GPT‑5.6 Sol · reviewed 2026-09-06

Two-hour cap; alpha API latency rescaled; reduced safeguards

Provider-published result; preserves source setting without claiming a controlled cross-provider comparison.

GPT-5.6: Frontier intelligence that scales with your ambition · Pushing the frontier on cyber and science paragraph · reviewed 2026-09-06

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details. 2h Single-run869tasks; API time normalized by model TPS plus overhead; reported number solved; domain whitelist.

First-party reported result.

zai-org/GLM-5.3 · Performance table: ExploitGym (2h / 6h) · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details. 6h Single-run869tasks; API time normalized by model TPS plus overhead; reported number solved; domain whitelist.

First-party reported result.

zai-org/GLM-5.3 · Performance table: ExploitGym (2h / 6h) · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

Cited result; see benchmark-specific Evaluation Details.

Comparison limit: Kimi K3 Evaluation Details cites Vals AI; retain as published context, not a new Moonshot comparison.

moonshotai/Kimi-K3 · Performance table: Finance Agent v2 · reviewed 2026-09-12

Google launch chart; benchmark methodology linked on page; reported comparator settings vary.

First-party reported result; comparator results retain the source evaluation setup.

Gemini 3.8 Flash launch performance · Performance table · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Coding table / FrontierCode 1.1 Extended (score) / GPT‑5.6 Sol · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Coding table / FrontierCode 1.1 Main (score) / GPT‑5.6 Sol · reviewed 2026-09-06

Grok High; GPT-5.6 Sol Max; Fable 5 Max. Competitor figures from developer cards/public leaderboards as selected by xAI.

First-party reported result; comparator results retain the source evaluation setup.

Grok 4.6 launch evaluations · Performance table · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Academic table / FrontierMath Tier 1-3 (v2) / GPT‑5.6 Sol · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Academic table / FrontierMath Tier 4 (v2) / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Academic table / FrontierMath Tier 4 (v2) / GPT‑5.6 Sol · reviewed 2026-09-06

Proximal agent harness; max effort; 34 tasks, five trials/task; mean score on 0..1 scale.

Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.5 · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: FrontierSWE · reviewed 2026-09-12

All-pass rate; allmodels selfcomputed byGoogle

Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Multimodal table / gdp.pdf / GPT‑5.6 Sol · reviewed 2026-09-06

Artificial Analysis independent agentic shell/web evaluation;220GDPvalgoldtasks; blind pairwise Elo; max effort for Claude.

Claude Fable 5.1 and Claude Mythos 5.1 System Card · Table8.1.A;8.15.3 · reviewed 2026-09-12

Artificial Analysis publicboard snapshot; effort as reported

Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06

Artificial Analysis Stirrup shell/web harness;220tasks; blind pairwise comparisons; reasoning max

Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

Externally evaluated result, attributed in the source footnote.

Comparison limit: The GLM card attributes this evaluation to Artificial Analysis; it is not a new Z.ai comparison.

zai-org/GLM-5.3 · Performance table: GDPval-AA v2 · reviewed 2026-09-12

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Professional table / GDPval-AA v2 / GPT‑5.6 Sol · reviewed 2026-09-06

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

Cited result; see benchmark-specific Evaluation Details.

Comparison limit: Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison.

moonshotai/Kimi-K3 · Performance table: GDPval-AA v2 (Elo) · reviewed 2026-09-12

Grok High; GPT-5.6 Sol Max; Fable 5 Max. Competitor figures from developer cards/public leaderboards as selected by xAI.

First-party reported result; comparator results retain the source evaluation setup.

Grok 4.6 launch evaluations · Performance table · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Science And Health table / GeneBench Pro / GPT‑5.6 Sol · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Science And Health table / GeneBench Pro / GPT‑5.6 Sol · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Academic table / GPQA Diamond / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Academic table / GPQA Diamond / GPT‑5.6 Sol · reviewed 2026-09-06

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: GPQA Diamond · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: GPQA Diamond · reviewed 2026-09-12

Launch table reported configuration; per-cell reasoning effort unspecified; BFS 1mil f1

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Long Context table / GraphWalks BFS 1mil f1 / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified; BFS 256k f1

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Long Context table / GraphWalks BFS 256k f1 / GPT‑5.6 Sol · reviewed 2026-09-06

Grok High; GPT-5.6 Sol Max; Fable 5 Max. Competitor figures from developer cards/public leaderboards as selected by xAI.

First-party reported result; comparator results retain the source evaluation setup.

Grok 4.6 launch evaluations · Performance table · reviewed 2026-09-06

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

Cited result; see benchmark-specific Evaluation Details.

Comparison limit: Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison.

moonshotai/Kimi-K3 · Performance table: Harvey Lab-AA · reviewed 2026-09-12

Google launch chart; benchmark methodology linked on page; reported comparator settings vary.

First-party reported result; comparator results retain the source evaluation setup.

Gemini 3.8 Flash launch performance · Performance table · reviewed 2026-09-06

length-adjusted; official HealthBench scoring

Mean response length 1764 characters. Adjustment centered on2000characters; adjusted and unadjusted values remain distinct configurations.

GPT-6 Astra System Card · Table6 / HealthBench / gpt-5.6-sol / length-adjusted · reviewed 2026-09-06

unadjusted; official HealthBench scoring

Mean response length 1764 characters. Adjustment centered on2000characters; adjusted and unadjusted values remain distinct configurations.

GPT-6 Astra System Card · Table6 / HealthBench / gpt-5.6-sol / unadjusted · reviewed 2026-09-06

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: HealthBench · reviewed 2026-09-12

length-adjusted; official HealthBench scoring

Mean response length 1740 characters. Adjustment centered on2000characters; adjusted and unadjusted values remain distinct configurations.

GPT-6 Astra System Card · Table6 / HealthBench Consensus / gpt-5.6-sol / length-adjusted · reviewed 2026-09-06

unadjusted; official HealthBench scoring

Mean response length 1740 characters. Adjustment centered on2000characters; adjusted and unadjusted values remain distinct configurations.

GPT-6 Astra System Card · Table6 / HealthBench Consensus / gpt-5.6-sol / unadjusted · reviewed 2026-09-06

length-adjusted; official HealthBench scoring

Mean response length 1751 characters. Adjustment centered on2000characters; adjusted and unadjusted values remain distinct configurations.

GPT-6 Astra System Card · Table6 / HealthBench Hard / gpt-5.6-sol / length-adjusted · reviewed 2026-09-06

unadjusted; official HealthBench scoring

Mean response length 1751 characters. Adjustment centered on2000characters; adjusted and unadjusted values remain distinct configurations.

GPT-6 Astra System Card · Table6 / HealthBench Hard / gpt-5.6-sol / unadjusted · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified; official paper scoring; length-adjusted

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Science And Health table / HealthBench Professional / GPT‑5.6 Sol · reviewed 2026-09-06

length-adjusted; official HealthBench scoring

Mean response length 3228 characters. Adjustment centered on2000characters; adjusted and unadjusted values remain distinct configurations.

GPT-6 Astra System Card · Table6 / HealthBench Professional / gpt-5.6-sol / length-adjusted · reviewed 2026-09-06

unadjusted; official HealthBench scoring

Mean response length 3228 characters. Adjustment centered on2000characters; adjusted and unadjusted values remain distinct configurations.

GPT-6 Astra System Card · Table6 / HealthBench Professional / gpt-5.6-sol / unadjusted · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API; official paper scoring; length-adjusted

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Science And Health table / HealthBench Professional (length-adjusted) / GPT‑5.6 Sol · reviewed 2026-09-06

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: HLE · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: HLE w/ tools · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: HLE w/ Tools · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. without tools Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: HLE-Full · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. with tools Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: HLE-Full · reviewed 2026-09-12

Google launch chart; benchmark methodology linked on page; reported comparator settings vary.

First-party reported result; comparator results retain the source evaluation setup.

Gemini 3.8 Flash launch performance · Performance table · reviewed 2026-09-06

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: IFBench · reviewed 2026-09-12

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Professional table / Internal Data Science Tasks / GPT‑5.6 Sol · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Coding table / Internal Database Migration Tasks / GPT‑5.6 Sol · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Professional table / Internal Design Tasks / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Self-Improvement table / Internal Research Debugging Evaluation / GPT‑5.6 Sol · reviewed 2026-09-06

65tasks; mean rubric score; official OpenCode harness and file-aware grader; reasoning max

Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: JobBench · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: JobBench · reviewed 2026-09-12

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Self-Improvement table / KernelGen 1P / GPT‑5.6 Sol · reviewed 2026-09-06

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: Kimi Code Bench 2.0 · reviewed 2026-09-12

Selfcomputed; Linuxterminal,bioinfotools,Python,R,network; macroaverage11subtasks

Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

Cited result; see benchmark-specific Evaluation Details.

Comparison limit: Kimi K3 Evaluation Details cites Vals AI; retain as published context, not a new Moonshot comparison.

moonshotai/Kimi-K3 · Performance table: Legal Research Bench · reviewed 2026-09-12

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Science And Health table / LifeSciBench / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Science And Health table / LifeSciBench / GPT‑5.6 Sol · reviewed 2026-09-06

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: LongBench v2 · reviewed 2026-09-12

No tools;1024frames Gemini/GPT,300frames Claude dueAPIlimit; model-specific frame budget: 1024

Frame budgets differ; table labels Gemini3.8static explicitly.

Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Professional table / Management Consulting Tasks (Internal) / GPT‑5.6 Sol · reviewed 2026-09-06

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. without tools Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: MathVision · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. with tools Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: MathVision · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: MCP-Atlas · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: MCPMark-Verified · reviewed 2026-09-12

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Science And Health table / MedChemBench (Internal) / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Science And Health table / MedChemBench (Internal) / GPT‑5.6 Sol · reviewed 2026-09-06

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

Cited comparator result; see the benchmark footnote.

Comparison limit: The Qwen card cites an external leaderboard or release report for this comparator; it is not a new Qwen evaluation.

Qwen/Qwen3.8-2.4T-A95B · Performance table: MLS-Bench-Lite · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: MLS-Bench-Lite · reviewed 2026-09-12

Launch table reported configuration; per-cell reasoning effort unspecified; no tools

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Multimodal table / MMMU Pro (no tools) / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified; tools enabled

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Multimodal table / MMMU Pro (with tools) / GPT‑5.6 Sol · reviewed 2026-09-06

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. without tools Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: MMMU-Pro · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. with tools Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: MMMU-Pro · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: MMVU · reviewed 2026-09-12

8needle;100examples/band rebinned byo200k_base; no tools; sequence-matcher ratio; GPT fromOpenAIcard; reasoning max

Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06

8needle;100examples/band rebinned byo200k_base; no tools; sequence-matcher ratio; GPT fromOpenAIcard; reasoning max

Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: MRCR v2 256K (8-needle) · reviewed 2026-09-12

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Self-Improvement table / NanoGPT / GPT‑5.6 Sol · reviewed 2026-09-06

UK AISI; single forward pass; no chain of thought

Time-horizon estimate; possible contamination noted by evaluator. Higher means harder tasks solved, not slower inference.

GPT-6 Astra System Card · Section9.3 · reviewed 2026-09-06

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: OfficeQA Pro · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: OmniDocBench · reviewed 2026-09-12

Maximum reported across reasoning efforts; OpenAI research environment or API; 8-needle 256K-512K

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Long Context table / OpenAI MRCR v2 8-needle 256K-512K / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified; 8-needle 256K-512K

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Long Context table / OpenAI MRCR v2 8-needle 256K-512K / GPT‑5.6 Sol · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API; 8-needle 512K-1M

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Long Context table / OpenAI MRCR v2 8-needle 512K-1M / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified; 8-needle 512K-1M

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Long Context table / OpenAI MRCR v2 8-needle 512K-1M / GPT‑5.6 Sol · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Professional table / OpenScore String Quartets (1 - OMR-NED) / GPT‑5.6 Sol · reviewed 2026-09-06

Anthropic life-sciences evaluation; bash/editor/packages except protein design no tools; protocols use bash/editor/search; Understanding revised network restriction.

Internal evaluation; not necessarily publicly released; compare only same task/grader revision. Percent rank correlation is not accuracy.

Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.19 · reviewed 2026-09-12

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Computer Use table / OSWorld 2.0 / GPT‑5.6 Sol · reviewed 2026-09-06

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: OSWorld 2.0 · reviewed 2026-09-12

Maximum reported across reasoning efforts; OpenAI research environment or API; offline set; partial credit; v2026.08.08; official task/grading settings

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Computer Use table / OSWorld 2.0 (v2026.08.08, offline set, partial score) / GPT‑5.6 Sol · reviewed 2026-09-06

108tasks; common internal GUI framework; execution-based checkers; binary metric; reasoning max

Muse1.2 uses older06.24tasks; all others08.08. Do not compare these versions as identical.

Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06

108tasks; common internal GUI framework; execution-based checkers; partial metric; reasoning max

Muse1.2 uses older06.24tasks; all others08.08. Do not compare these versions as identical.

Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06

Partialscore; batchtools;1080p/500steps; Gemini/Sonnet bestof3runs; screenshotonly; officialCUAharness

Methodology says runs pre08.08patch but Opusvalue fromFable5.1card usesAugustfixedtasks; no controlledsameversionclaim. GPT values providerreports.

Comparison limit: Provider-sourced OSWorld task revision is unverified; cannot join a known-version comparison.

Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: OSWorld-Verified · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. BasicAgent Code-Dev; Opus4.6 judge,3runs,12h each.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: PaperBench · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: PerceptionBench · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: PLawBench · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: PostTrainBench · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: PostTrainBench · reviewed 2026-09-12

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Self-Improvement table / PostTrainBench Lite / GPT‑5.6 Sol · reviewed 2026-09-06

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: PRBench-Finance · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: PRBench-Legal · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

Cited result; see benchmark-specific Evaluation Details.

Comparison limit: Kimi K3 Evaluation Details cites GLM release blog or Vals AI, per model; retain as published context, not a new Moonshot comparison.

moonshotai/Kimi-K3 · Performance table: ProgramBench · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: ProgramBench (Almost Solved) · reviewed 2026-09-12

Anthropic life-sciences evaluation; bash/editor/packages except protein design no tools; protocols use bash/editor/search; Understanding revised network restriction.

Internal evaluation; not necessarily publicly released; compare only same task/grader revision. Percent rank correlation is not accuracy.

Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.19 · reviewed 2026-09-12

Anthropic life-sciences evaluation; bash/editor/packages except protein design no tools; protocols use bash/editor/search; Understanding revised network restriction.

Internal evaluation; not necessarily publicly released; compare only same task/grader revision. Percent rank correlation is not accuracy.

Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.19 · reviewed 2026-09-12

Anthropic life-sciences evaluation; bash/editor/packages except protein design no tools; protocols use bash/editor/search; Understanding revised network restriction.

Internal evaluation; not necessarily publicly released; compare only same task/grader revision. Percent rank correlation is not accuracy.

Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.19 · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Internal Qoder tasks,ClaudeCode,avg@5,6h,32768 output,temp1,256K.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: QwenQoderBench · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Internal bilingual EN/CN React benchmark,7categories,ClaudeCode,render+multimodaljudge,BT/Elo.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: QwenReactBench · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Internal bilingual EN/CN SVG benchmark,render+multimodaljudge,BT/Elo.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: QwenSVGBench · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Internal software engineering,ClaudeCode,avg@3,8h,32768 output,temp1,256K.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: QwenSWEBench · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: ResearchRubrics · reviewed 2026-09-12

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Self-Improvement table / RSI Index / GPT‑5.6 Sol · reviewed 2026-09-06

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: SaaS-Bench · reviewed 2026-09-12

22 isolated CTF-style targets; protected-flag success metric

Provider-published result; preserves source setting without claiming a controlled cross-provider comparison.

GPT-6 Astra System Card · Section10.1.2.4 · reviewed 2026-09-06

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

Cited result; see benchmark-specific Evaluation Details.

Comparison limit: Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison.

moonshotai/Kimi-K3 · Performance table: SciCode · reviewed 2026-09-12

Maximum reported across reasoning efforts; OpenAI research environment or API; no tools

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Computer Use table / ScreenSpot-Pro (no tools) / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified; reduced or absent production safeguards; public grader; May2026 JavaScript subset

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Cybersecurity table / SEC-Bench Pro / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified; Ultra, four-agent orchestration; reduced or absent production safeguards; public grader; May2026 JavaScript subset

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Cybersecurity table / SEC-Bench Pro / GPT‑5.6 Sol Ultra · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API; reduced or absent production safeguards; May2026 JavaScript subset,183 vulnerabilities; revised agent root-cause grader

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Cybersecurity table / SEC-Bench Pro / GPT‑5.6 Sol · reviewed 2026-09-06

System-card reported configuration; reasoning effort unspecified

Production-named model result; separate helpful-only checkpoint omitted because no exact catalog identity.

GPT-6 Astra System Card · Section10.1.1.2.2 · reviewed 2026-09-06

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. v1.1 public87tasks,3runs; Anthropic ClaudeCode,OpenAI Codex,Qwen OpenCode.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: SkillsBench · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: SpreadsheetBench 2 · reviewed 2026-09-12

Maximum reported across reasoning efforts; OpenAI research environment or API; reduced or absent production safeguards; pass@1; all six objectives required

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Cybersecurity table / SRE-Bench / GPT‑5.6 Sol · reviewed 2026-09-06

pass@4; four independent trials; all six objectives required; reduced production safeguards

Provider-published result; preserves source setting without claiming a controlled cross-provider comparison.

GPT-6 Astra System Card · Section10.1.2.3 · reviewed 2026-09-06

124tasks/11repos; publicQnA mini-swe-agent rubric pass@1; GPT/Opus owncards; reasoning max

Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06

Anthropic reported configuration; adaptive thinking at max effort, default sampling, five-trial mean unless section specifies otherwise; context at most 1M. Comparator configuration follows cited prior card or board. Agent identity is not established as mini-swe-agent.

Claude Fable 5.1 and Claude Mythos 5.1 System Card · Table 8.1.A; section 8.2 · reviewed 2026-09-12

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Coding table / SWE-Bench Pro / GPT‑5.6 Sol · reviewed 2026-09-06

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Refined task set with problematic tasks corrected; all baselines rerun, Claude Code,temp1,top_p.95,256K context.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: SWE-bench Pro · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: SWE-Marathon · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: SWE-Marathon (v1.1) · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Qwen Claude Code avg@10,5h timeout,131072 output; comparators best published across harnesses.

Cited comparator result; see the benchmark footnote.

Comparison limit: The Qwen card cites an external leaderboard or release report for this comparator; it is not a new Qwen evaluation.

Qwen/Qwen3.8-2.4T-A95B · Performance table: Terminal Bench 2.1 · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: Terminal Bench 2.1 · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: Terminal Bench 3.0 · reviewed 2026-09-12

Terminus2only; Gemini selfcomputed, othermodels officialboard/ArtificialAnalysis

Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06

89tasks; each model nativecoding harness in internalframework/cloudsandbox; officialverifier; GPT owncard; reasoning max; native harness family: OpenAI (exact harness revision not specified)

Native harnesses differ; not a Terminus2-only comparison.

Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06

Claude Code --bare max effort, 15 trials/task over66tasks for Claude; GPT Codex CLI max from public board.

Uses more precise section values rather than rounded headline table. Distinct from2.1; timeouts/resources changed.

Comparison limit: System card section 8.6 cites the public Codex CLI result for Sol, while the Claude rows are internal Claude Code --bare reruns. Different agent harnesses and runs cannot form a matched comparison.

Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.6 · reviewed 2026-09-12

Officialpublicboard highest scoring thinking level; nativeagents may differ

Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Coding table / Terminal-Bench 2.1 / GPT‑5.6 Sol · reviewed 2026-09-06

Launch table reported configuration; per-cell reasoning effort unspecified; Ultra, four-agent orchestration

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Coding table / Terminal-Bench 2.1 / GPT‑5.6 Sol Ultra · reviewed 2026-09-06

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

Cited result; see benchmark-specific Evaluation Details.

Comparison limit: Kimi K3 Evaluation Details cites GLM release blog, Artificial Analysis or OpenAI, per model; retain as published context, not a new Moonshot comparison.

moonshotai/Kimi-K3 · Performance table: Terminal-Bench 2.1 · reviewed 2026-09-12

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Coding table / Terminal-Bench 4.0 / GPT‑5.6 Sol · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Academic table / Terminal-Bench Science 0.1 / GPT‑5.6 Sol · reviewed 2026-09-06

Grok High; GPT-5.6 Sol Max; Fable 5 Max. Competitor figures from developer cards/public leaderboards as selected by xAI.

First-party reported result; comparator results retain the source evaluation setup.

Grok 4.6 launch evaluations · Performance table · reviewed 2026-09-06

70tasks; Claude Code --bare max; Fable10trials/task, Opus12; GPT Codex CLI max from public board.

Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.7 · reviewed 2026-09-12

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Tool Use table / Toolathlon / GPT‑5.6 Sol · reviewed 2026-09-06

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: Toolathlon Verified · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: Toolathlon Verified (Pass@1) · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: Toolathlon-Verified · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: Video-MME (w. sub) · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: WorkSpaceBench · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: WorldVQA ForceAnswer · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. without tools Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: ZeroBench (pass@5) · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. with tools Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

First-party reported result.

moonshotai/Kimi-K3 · Performance table: ZeroBench (pass@5) · reviewed 2026-09-12

Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

Cited result; see benchmark-specific Evaluation Details.

Comparison limit: Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison.

moonshotai/Kimi-K3 · Performance table: τ³-Banking · reviewed 2026-09-12