RankingGPT-5.6 Terra

GPT-5.6 Terra

Data updated 12 Sept 2026

54 published benchmark measures · 17 benchmark families contribute across 5 task areas. 5 capability estimates available in the full profile. See all results ↓ · Compare published benchmarks →

Model evidence summary

Choose a configuration

A model-wide score would mix effort settings. This page summarizes published evidence; only identified configurations receive leaderboard ranks.

Compare measured configurations →

The capability chart summarizes evidence across reported settings, not a runnable configuration or a leaderboard rank.

Performance profile

Capabilities

Adjusted comparison score · 0–100

Filled points are supported; hollow points are preliminary. Lines stop at unknown capabilities. Exact values and sources follow below.

Agentic5 families · 0 with independent evidence · Supported40.9

5 core families; 11 direct opponents across 3 labs.

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: 34.8–49.2; 0/11 scenarios unsupported. Without one publisher: 39.2–45.3; 1/15 unsupported. Smoothing check: 38.7–44.0; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage; source sensitivity still requires inspection. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

GDPval: 38.6 observed win share
Google, OpenAI · Source 1 Source 2
Browsecomp: 80.0 observed win share
OpenAI · Source 1
AutomationBench: 50.0 observed win share
OpenAI · Source 1
OSWorld: 50.0 observed win share
OpenAI · Source 1
Toolathlon: 16.7 observed win share
OpenAI · Source 1

Hard reasoning4 families · 2 with independent evidence · Supported52.1

4 core families; 58 direct opponents across 12 labs.

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: 49.6–57.1; 0/7 scenarios unsupported. Without one publisher: 36.0–53.0; 0/16 unsupported. Smoothing check: 51.1–52.9; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

GPQA: 43.2 observed win share
OpenAI, artificialanalysis.ai · Source 1 Source 2
ARC-AGI: 79.0 observed win share
OpenAI, arcprize.org · Source 1 Source 2
Humanity’s Last Exam: 20.0 observed win share
Google · Source 1
FrontierMath: 45.0 observed win share
OpenAI · Source 1 Source 2

Coding3 families · 1 with independent evidence · Supported61.0

3 core families; 27 direct opponents across 9 labs.

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: 56.1–71.2; 0/7 scenarios unsupported. Without one publisher: 58.4–63.5; 0/20 unsupported. Smoothing check: 59.0–61.3; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

DeepSWE: 66.0 observed win share
Google, OpenAI, deepswe.datacurve.ai · Source 1 Source 2 Source 3
Terminal-Bench: 66.7 observed win share
Google, OpenAI · Source 1 Source 2 Source 3
SWE-bench Pro: 50.0 observed win share
OpenAI · Source 1

Human prefNo comparable evidenceUnknown

0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 1/1 scenarios unsupported. Without one publisher: No supported estimate; 1/1 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: cross-family and cross-publisher predictions could not be evaluated from the available comparison network. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

KnowledgeNo comparable evidenceUnknown

0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 4/4 scenarios unsupported. Without one publisher: No supported estimate; 5/5 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: almost no publisher-held-out comparisons remained estimable. Cross-source validity is unresolved. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

Multimodal3 families · 0 with independent evidence · Supported48.9

3 core families; 8 direct opponents across 3 labs.

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: 46.9–61.5; 0/8 scenarios unsupported. Without one publisher: 35.1–66.8; 1/8 unsupported. Smoothing check: 48.0–49.7; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: limited publisher-held-out coverage. Cross-source validity is unresolved. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

CharXiv: 80.0 observed win share
Google · Source 1
Lvbench: 0.0 observed win share
Google · Source 1
Mmmu Pro: 41.7 observed win share
OpenAI · Source 1 Source 2

Long context2 families · 0 with independent evidence · Supported50.9

2 core families; 4 direct opponents across 2 labs.

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: 50.9–51.5; 2/5 scenarios unsupported. Without one publisher: 50.9–51.7; 2/5 unsupported. Smoothing check: 48.4–53.9; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts underperformed neutral predictions. Treat this as an exploratory estimate. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

Graphwalks: 50.0 observed win share
OpenAI · Source 1 Source 2
MRCR: 50.0 observed win share
OpenAI · Source 1 Source 2

Scores estimate outcomes against a shared reference panel; they are not accuracy percentages. Sparse or disconnected evidence cannot qualify an overall profile. Open a capability to inspect its evidence.

Compare 7 effort levels across 68 benchmark/harness combinations →

Reported effort · Not specified

Settings reported in this model's published benchmark results, including results outside the aggregate. Effort names are provider-specific. These are not API defaults or equal compute budgets.

Not specified: 64 observations

Mixed settings means multiple settings occur in the evidence. Best across efforts means the source selected its best reported result across settings; it does not mean Max. Unspecified settings stay unknown. This model-summary chart combines reported settings. The leaderboard keeps identified configurations separate and excludes unknown effort.

Inspect each result and its source ↓ · Download effort evidence

Compare capability profiles →

Score contributions and missing evidence

17 contributing families across 5 capabilities. Fixed reference panels do not change when the catalog expands.

Capability is fitted jointly across families. Capability estimates below describe different task areas; their weighted sum is not the Capability score.

Results without reviewed compatibility or a reference match remain in the raw evidence below. Coverage counts only contributing results.

Model information & shareable badge

Lab: OpenAI
Catalog status: active
Availability: Public provider catalog; account and region restrictions may apply
Family: GPT-5.6
Released: —
Context: 1,050,000 tokens
License: proprietary
Model card: https://developers.openai.com/api/docs/models/all
Default Capability family coverage: /badge/gpt-5.6-terra.svg

Benchmark scores & sources

Original results, evaluation harnesses, and evidence behind this model.

Benchmark	Bucket	Score	Harness	Evidence	Source-recorded date
Agents' Last Exam · not specified	Supporting evidence	50.4% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
ARC-AGI-2	Hard reasoning	83.9%	ARC Prize verified Effort: Not specified contributes to capability	official board	2026-07-09
ARC-AGI-3 · 3	Hard reasoning	0.8% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
Artificial Analysis Coding Agent Index v1.1 · v1.1	Supporting evidence	77.4 index score Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
Artificial Analysis Intelligence Index v4.1 · v4.1	Supporting evidence	55 index score Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
AutomationBench · not specified	Agentic	15.2% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
BenchCAD · not specified	Supporting evidence	62.3% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
BenchCAD (python tool) · not specified	Supporting evidence	78.2% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
Big Finance Bench · not specified	Supporting evidence	51% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
BioMysteryBench · Human Difficult	Supporting evidence	49.4% Reported settings & source Linuxterminal,bioinfotools,Python,R; allowlistednetwork; Gemini/GPTselfcomputed,Claudeproviderreports Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
BioMysteryBench · Human Solvable	Supporting evidence	83.8% Reported settings & source Linuxterminal,bioinfotools,Python,R; allowlistednetwork; Gemini/GPTselfcomputed,Claudeproviderreports Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
BrowseComp · not specified	Agentic	87.5% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
Capture-the-Flag Challenges · not specified	Supporting evidence	91.8% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
CharXiv Reasoning	Multimodal	85.9% Reported settings & source No tools; Gemini/GPT/Opus selfcomputed; Sonnet selfreported Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
DeepSWE · 1.1	Coding	69.6% Reported settings & source 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	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
DeepSWE v1.1	Coding	69.6%	DeepSWE v1.1 reported Effort: Not specified contributes to capability	official board	2026-09-03
DeepSWE v1.1 · v1.1	Coding	69.6% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
ExploitBench · not specified	Supporting evidence	52.9% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
ExploitGym · not specified	Supporting evidence	23.2% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
Finance Agent v2 · source release snapshot; version not specified	Supporting evidence	54.4% Reported settings & source 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	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
FrontierMath Tier 1-3 (v2) · v2	Hard reasoning	84.9% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
FrontierMath Tier 4 (v2) · v2	Hard reasoning	68.3% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
GDP.PDF	Supporting evidence	29% Reported settings & source All-pass rate; allmodels selfcomputed byGoogle Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
gdp.pdf · not specified	Supporting evidence	24.7% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
GDPval-AA · 2	Agentic	1528 Reported settings & source Artificial Analysis publicboard snapshot; effort as reported Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
GDPval-AA v2 · v2	Agentic	1593 Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
GeneBench Pro · not specified	Supporting evidence	23.3% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
GPQA Diamond	Hard reasoning	92.525%	GPQA Diamond reported Effort: Not specified contributes to capability	independent repro	2026-09-11
GPQA Diamond · not specified	Hard reasoning	92.9% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
GraphWalks BFS 1mil f1 · not specified	Long context	71.2% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
GraphWalks BFS 256k f1 · not specified	Long context	76.9% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
Harvey Legal Agent Benchmark · source release snapshot; version not specified	Supporting evidence	0.8% Reported settings & source 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	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
HealthBench · not specified	Supporting evidence	57 score (0-100) Reported settings & source length-adjusted; official HealthBench scoring Mean response length 2285 characters. Adjustment centered on2000characters; adjusted and unadjusted values remain distinct configurations. GPT-6 Astra System Card · Table6 / HealthBench / gpt-5.6-terra / length-adjusted · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
HealthBench · not specified	Supporting evidence	58.7 score (0-100) Reported settings & source unadjusted; official HealthBench scoring Mean response length 2285 characters. Adjustment centered on2000characters; adjusted and unadjusted values remain distinct configurations. GPT-6 Astra System Card · Table6 / HealthBench / gpt-5.6-terra / unadjusted · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
HealthBench Consensus · not specified	Supporting evidence	95.1 score (0-100) Reported settings & source length-adjusted; official HealthBench scoring Mean response length 2247 characters. Adjustment centered on2000characters; adjusted and unadjusted values remain distinct configurations. GPT-6 Astra System Card · Table6 / HealthBench Consensus / gpt-5.6-terra / length-adjusted · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
HealthBench Consensus · not specified	Supporting evidence	95.2 score (0-100) Reported settings & source unadjusted; official HealthBench scoring Mean response length 2247 characters. Adjustment centered on2000characters; adjusted and unadjusted values remain distinct configurations. GPT-6 Astra System Card · Table6 / HealthBench Consensus / gpt-5.6-terra / unadjusted · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
HealthBench Hard · not specified	Supporting evidence	32.7 score (0-100) Reported settings & source length-adjusted; official HealthBench scoring Mean response length 2199 characters. Adjustment centered on2000characters; adjusted and unadjusted values remain distinct configurations. GPT-6 Astra System Card · Table6 / HealthBench Hard / gpt-5.6-terra / length-adjusted · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
HealthBench Hard · not specified	Supporting evidence	34.3 score (0-100) Reported settings & source unadjusted; official HealthBench scoring Mean response length 2199 characters. Adjustment centered on2000characters; adjusted and unadjusted values remain distinct configurations. GPT-6 Astra System Card · Table6 / HealthBench Hard / gpt-5.6-terra / unadjusted · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
HealthBench Professional · not specified	Supporting evidence	57.7% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
HealthBench Professional · not specified	Supporting evidence	57.7 score (0-100) Reported settings & source length-adjusted; official HealthBench scoring Mean response length 3618 characters. Adjustment centered on2000characters; adjusted and unadjusted values remain distinct configurations. GPT-6 Astra System Card · Table6 / HealthBench Professional / gpt-5.6-terra / length-adjusted · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
HealthBench Professional · not specified	Supporting evidence	62.4 score (0-100) Reported settings & source unadjusted; official HealthBench scoring Mean response length 3618 characters. Adjustment centered on2000characters; adjusted and unadjusted values remain distinct configurations. GPT-6 Astra System Card · Table6 / HealthBench Professional / gpt-5.6-terra / unadjusted · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
HLE-Verified · source release snapshot; version not specified	Hard reasoning	51.1% Reported settings & source 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	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
Internal Research Debugging Evaluation · not specified	Supporting evidence	67.8% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
KernelGen 1P · not specified	Supporting evidence	49.2% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
LABBench · 2	Supporting evidence	81.2% Reported settings & source Selfcomputed; Linuxterminal,bioinfotools,Python,R,network; macroaverage11subtasks Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
LifeSciBench · not specified	Supporting evidence	56% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
LVBench · static	Multimodal	78.9% Reported settings & source 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	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
Management Consulting Tasks (Internal) · not specified	Supporting evidence	37.2% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
MedChemBench (Internal) · not specified	Supporting evidence	35% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
MMMU Pro (no tools) · not specified	Multimodal	80.7% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
MMMU Pro (with tools) · not specified	Multimodal	82% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
NanoGPT · not specified	Supporting evidence	14.5% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
OpenAI MRCR v2 8-needle 256K-512K · v2	Long context	89.6% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
OpenAI MRCR v2 8-needle 512K-1M · v2	Long context	72.5% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
OSWorld 2.0 · 2.0	Agentic	50.2% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
OSWorld partial · 2.0 task revision unverified gpt-5.6-terra	Agentic	50.2% Reported settings & source 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	Published configuration Effort: Not specified	lab self-report Provider-sourced OSWorld task revision is unverified; cannot join a known-version comparison.	Reviewed 2026-09-06
PostTrainBench Lite · not specified	Supporting evidence	51.5% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
RSI Index · not specified	Supporting evidence	56.3% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
SEC-Bench Pro · May2026 / public grader	Supporting evidence	57.7% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
SWE-Bench Pro · not specified	Coding	63.4% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
Terminal-Bench · 2.1	Coding	87.4% Reported settings & source Terminus2only; Gemini selfcomputed, othermodels officialboard/ArtificialAnalysis Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
Terminal-Bench · 4.0	Coding	23.6% Reported settings & source Officialpublicboard highest scoring thinking level; nativeagents may differ Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
Terminal-Bench 2.1 · 2.1	Coding	87.4% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
Toolathlon · not specified	Agentic	53.1% Reported settings & source 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 Terra · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
GDPval-AA	Agentic	—	—	—	—
Humanity's Last Exam	Hard reasoning	—	—	—	—
LiveCodeBench	Coding	—	—	—	—
LMArena Text Arena	Human pref	—	—	—	—
MMLU-Pro	Knowledge	—	—	—	—
OSWorld-Verified	Agentic	—	—	—	—
SWE-bench Pro	Agentic	—	—	—	—
SWE-bench Verified	Agentic	—	—	—	—
Terminal-Bench 2.1	Agentic	—	—	—	—