RankingPostTrainBench · source release snapshot; version not specified

PostTrainBench · source release snapshot; version not specified

Data updated 12 Sept 2026

Bucket
Supporting evidence
Unit
percent
Direction
Higher is better
Version
source release snapshot; version not specified
Display harness
moonshotai/Kimi-K3
Board
https://huggingface.co/moonshotai/Kimi-K3

The available records have no admitted matched comparison in the capability core. Raw results remain available below.

Compare published benchmark results with category weights →

Models

ModelScoreHarnessEvidenceSource-recorded date
Claude Fable 5Anthropic41.4%
Reported settings & source

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

moonshotai/Kimi-K3lab self-report2026-09-12
Kimi K3Moonshot36.6%
Reported settings & source

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

moonshotai/Kimi-K3lab self-report2026-09-12
GPT-5.6 SolOpenAI34.6%
Reported settings & source

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

moonshotai/Kimi-K3lab self-report2026-09-12
GLM-5.2Z.ai34.3%
Reported settings & source

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 PostTrainBench results; retain as published context, not a new Moonshot comparison.

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

moonshotai/Kimi-K3lab self-report2026-09-12
Claude Opus 4.8Anthropic34.1%
Reported settings & source

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 PostTrainBench results; retain as published context, not a new Moonshot comparison.

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

moonshotai/Kimi-K3lab self-report2026-09-12
GPT-5.5OpenAI28.4%
Reported settings & source

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 PostTrainBench results; retain as published context, not a new Moonshot comparison.

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

moonshotai/Kimi-K3lab self-report2026-09-12
Claude Fable 5Anthropic41.8%
Reported settings & source

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

First-party reported result.

Comparison limit: The source column includes fallback execution without a documented exact effort.

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

zai-org/GLM-5.3lab self-report2026-09-12
Claude Opus 4.7Anthropic42.4%
Reported settings & source

MiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted.

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

MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

MiniMax M3 model card benchmark figurelab self-report2026-09-06
Claude Opus 4.8Anthropic32.9%
Reported settings & source

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

zai-org/GLM-5.3lab self-report2026-09-12
Gemini 3.1 ProGoogle15.2%
Reported settings & source

MiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted.

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

MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

MiniMax M3 model card benchmark figurelab self-report2026-09-06
GLM-5.2Z.ai31.7%
Reported settings & source

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

zai-org/GLM-5.3lab self-report2026-09-12
GLM-5.3Z.ai39.8%
Reported settings & source

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

First-party reported result.

Comparison limit: The source changes anti-cheat checks and substitutes zero-shot baseline scores for failed runs; the modified protocol requires separate review.

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

zai-org/GLM-5.3lab self-report2026-09-12
GPT-5.5OpenAI39.3%
Reported settings & source

MiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted.

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

MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

MiniMax M3 model card benchmark figurelab self-report2026-09-06
GPT-5.6 SolOpenAI36.2%
Reported settings & source

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

zai-org/GLM-5.3lab self-report2026-09-12
Kimi K3Moonshot32%
Reported settings & source

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

zai-org/GLM-5.3lab self-report2026-09-12
MiniMax-M2.7MiniMax13.1%
Reported settings & source

MiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted.

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

MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

MiniMax M3 model card benchmark figurelab self-report2026-09-06
MiniMax-M3MiniMax37.1%
Reported settings & source

MiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted.

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

MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

MiniMax M3 model card benchmark figurelab self-report2026-09-06