RankingEffort benchmarks

GPT-6.1 Sol · High

Compare models

145 measured results · 5 effort settings · 54 benchmark/harness combinations

Model evidence and sources →

Change model

Model

Current configurationSources

Compare with

Choose a second model and its effort to see both profiles and benchmark differences below.

Compare withModel and configuration

Capability profile

One configuration, seven capabilities

Comparison score · 0–100

AGPT-6.1 Sol · High3 of 7 capabilities supported

Gaps are unknown, not zero. Hollow points are preliminary.

Agentic
A75.3Supported
Hard reasoning
A74.5Supported
Coding
A88.8Supported
Human pref
Unknown
Knowledge
A68.4Preliminary
Multimodal
A67.6Preliminary
Long context
A65.7Preliminary

Each profile belongs to the named configuration. Capability scores use a shared panel for all axes, distinct from the overall ranking panel; they are not accuracy percentages or direct head-to-head wins.

Capability score evidence

GPT-6.1 Sol · High: 85.9 overall comparison score. Meets the overall evidence requirements.

6 areas measured. The available task mix affects this estimate; missing areas remain unknown.

Shared-result disagreement. This aggregate order conflicts with matched benchmark results against 2 other configurations. Different test coverage and opponents affect the fit. Inspect published results before treating the rank as conclusive.

Which sources carry the weight?

ARC Prize · 31.6% direct comparison weight · independent of the model provider
Cognition · 25.7% direct comparison weight · independent of the model provider
OpenAI · 23.3% direct comparison weight · provider report
Artificial Analysis · 19.4% direct comparison weight · independent of the model provider

Which benchmark families carry the weight?

FrontierCode · 25.7% direct comparison weight
ARC-AGI · 17.5% direct comparison weight
arc-agi-3 · 14.1% direct comparison weight
AutomationBench · 6.3% direct comparison weight
GDP.pdf · 6.3% direct comparison weight
Other families (11) · 30.1% direct comparison weight

These shares describe direct comparison weight, not fractions of the final score or confidence. Source balancing does not give every family equal weight or remove correlations between overlapping sources.

How sensitive is this score?

The audit removes one source at a time and refits against the same overall reference panel. These published results use the matching dataset audited 2026-10-20.

Both ranks use the same surviving configurations for each removal. The cohort starts with 444 configurations supported in the original audit, including separate effort settings. These are diagnostic positions, not the default leaderboard ranks. Eligibility is not rechecked after removal.

What changes when a source is removed?
Removed source	Rank before → after	Rank movement	Cohort remaining / lost support	Score after (change)
Artificial Analysis	12 → 13	Down 1	203 remaining / 241 lost	87.6 (+1.7 points)
ARC Prize	12 → 15	Down 3	444 remaining / 0 lost	86.5 (+0.6 points)
Datacurve	12 → 12	No movement	444 remaining / 0 lost	84.3 (-1.6 points)
LiveCodeBench	12 → 12	No movement	444 remaining / 0 lost	85.9 (+0.0 points)
Scale	12 → 13	Down 1	444 remaining / 0 lost	86.4 (+0.5 points)
Terminal-Bench	12 → 12	No movement	444 remaining / 0 lost	85.9 (-0.0 points)
Cognition	12 → 15	Down 3	444 remaining / 0 lost	83.3 (-2.6 points)
LiveBench	12 → 14	Down 2	443 remaining / 1 lost	86.5 (+0.6 points)
SWE-rebench	12 → 12	No movement	444 remaining / 0 lost	85.8 (-0.1 points)
Epoch AI	12 → 12	No movement	431 remaining / 13 lost	85.9 (+0.0 points)
Vals AI	12 → 13	Down 1	443 remaining / 1 lost	85.7 (-0.2 points)
Provider reports · Anthropic	12 → 11	Up 1	444 remaining / 0 lost	85.9 (-0.0 points)
Provider reports · Moonshot AI	12 → 12	No movement	444 remaining / 0 lost	85.8 (-0.1 points)
Provider reports · Meta	12 → 12	No movement	444 remaining / 0 lost	85.9 (-0.0 points)
Provider reports · Mistral	12 → 12	No movement	444 remaining / 0 lost	85.9 (+0.0 points)
Provider reports · OpenAI	12 → 18	Down 6	444 remaining / 0 lost	80.9 (-5.0 points)
All provider reports	12 → 17	Down 5	444 remaining / 0 lost	80.7 (-5.2 points)

Lost support means a configuration no longer has a comparison path to the complete reference panel. Its rank is unavailable. A surviving path alone does not establish leaderboard eligibility.

Overlapping sources may remain correlated even with source balancing. Leave-one-source-out movement is a sensitivity diagnostic, not a spread of source-specific ranks or a confidence measure. Scoring methodology · Dated configuration audit

Every benchmark family

Removed evidence	Recomputed score	Change
deepswe	83.0	-2.9
frontiercode	83.3	-2.6
arc-agi	88.0	+2.1
gdp-pdf	84.5	-1.5
terminal-bench-science	86.7	+0.8
automationbench	86.6	+0.7
arc-agi-3	86.3	+0.4
gdpval	86.3	+0.4
mmmu-pro	86.3	+0.3
simpleqa	86.2	+0.3
briefcase	86.2	+0.3
hle	86.1	+0.2
gpqa	85.7	-0.2
ifbench	85.7	-0.2
epoch-game-puzzles	85.7	-0.2
swe-atlas-qna	85.7	-0.2
mmlu-pro	86.1	+0.2
livebench-instructions	86.1	+0.1
swe-rebench	85.8	-0.1
critpt	86.1	+0.1
swe-atlas-test-writing	85.8	-0.1
aa-lcr	86.0	+0.1
terminal-bench	85.8	-0.1
enigma-eval	86.0	+0.1
multi-swe-bench	85.8	-0.1
tau-bench	85.8	-0.1
vibe-code	85.8	-0.1
omniscience	86.0	+0.1
livebench-language	86.0	+0.1
livebench-coding	85.9	-0.1
aime	85.9	-0.1
vals-code-migration	85.9	-0.1
harvey	85.9	-0.1
frontiermath	85.9	-0.0
livebench-reasoning	85.9	-0.0
vals-excel-modeling	85.9	-0.0
apex-agents	85.9	+0.0
vals-finance-agent	85.9	+0.0
livecodebench	85.9	-0.0
swe-atlas-refactoring	85.9	-0.0
math500	85.9	-0.0
gmmlu	85.9	-0.0
livebench-data	85.9	-0.0
itbench	85.9	-0.0
analyst-agent	85.9	+0.0
livebench-math	85.9	-0.0
enterprise-ops	85.9	+0.0
vals-legal-research	85.9	+0.0
swe-bench-pro	85.9	+0.0
vals-tax-agent	85.9	+0.0

What evidence is missing from the fit?

Across all collected settings for this model: 185 observations, 157 contributing, 0 matched without graph weight and 28 excluded. Counts do not establish rank eligibility.

6 · Benchmark family or source protocol has not been reviewed
5 · Original SciCode grading defects are under review; retained as supporting evidence, excluded from aggregate and capability scores. Corrected SciCode-Verified requires a separate protocol review. Sources: https://arxiv.org/abs/2608.04975 and https://artificialanalysis.ai/evaluations/scicode
2 · Evaluator has not been reviewed for independent admission
5 · Private user-flagged prompt protocol needs separate review before capability scoring; retained as an exact lower-is-better sourced claim.
4 · Safety failure behavior is not a capability or intelligence score.
2 · No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately
4 · Supporting evidence outside the reviewed capability core

Inspect every observation and exclusion →

Benchmark results

These are published benchmark scores. Supported effort estimates also appear on the Capability leaderboard. Results from different harnesses occupy different rows. Missing cells stay unknown; no scores are copied between effort levels.

Benchmark / source	Low	Medium	High	XHigh	Max
AA-AnalystAgentArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of tasks solved on all 5 of 5 attempts · 80 tasks, 5 attempts per task · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	Not reported	Not reported	50% Reported settings GPT-6.1 Sol (Max); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol
AA-Briefcase EloArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details AA-Briefcase v1.1 is an agentic knowledge work benchmark developed by Artificial Analysis. AA-Briefcase Elo is a combined metric that aggregates rubric pass rate, analytical quality Elo and presentation Elo · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-10-18.	1,116.74 Elo Reported settings GPT-6.1 Sol (Low); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-low	1,361.16 Elo Reported settings GPT-6.1 Sol (Medium); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-medium	1,465.25 Elo Reported settings GPT-6.1 Sol (High); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-high	1,503.6 Elo Reported settings GPT-6.1 Sol (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-xhigh	1,557 Elo Reported settings GPT-6.1 Sol (Max); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol
AA-LCR v1.1Artificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	84% Reported settings GPT-6.1 Sol (Low); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-low	83.33% Reported settings GPT-6.1 Sol (Medium); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-medium	82.33% Reported settings GPT-6.1 Sol (High); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-high	79.67% Reported settings GPT-6.1 Sol (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-xhigh	83% Reported settings GPT-6.1 Sol (Max); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol
AutomationBench-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of task objectives completed with no guardrail violations · Higher is better · Benchmark developed by Zapier · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	52.57% Reported settings GPT-6.1 Sol (Low); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-low	62.57% Reported settings GPT-6.1 Sol (Medium); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-medium	64.5% Reported settings GPT-6.1 Sol (High); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-high	66.57% Reported settings GPT-6.1 Sol (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-xhigh	64.87% Reported settings GPT-6.1 Sol (Max); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol
CritPtArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by Argonne and UIUC, with contributions from 60+ researchers globally. CritPt is under review by its authors following external feedback · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	24.86% Reported settings GPT-6.1 Sol (Low); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-low	27.71% Reported settings GPT-6.1 Sol (Medium); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-medium	30% Reported settings GPT-6.1 Sol (High); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-high	31.71% Reported settings GPT-6.1 Sol (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-xhigh	31.71% Reported settings GPT-6.1 Sol (Max); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol
GDP.pdf: All-pass RateArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of attempts where every atomic criterion passed · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	27% Reported settings GPT-6.1 Sol (Low); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-low	30% Reported settings GPT-6.1 Sol (Medium); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-medium	32% Reported settings GPT-6.1 Sol (High); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-high	31.8% Reported settings GPT-6.1 Sol (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-xhigh	31% Reported settings GPT-6.1 Sol (Max); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol
GDPval-AA v2.1 LeaderboardArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Elo rating for performance on real-world work tasks · Anchored to DeepSeek V4.1 Flash (max) at 1600 · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-10-18.	1,314.67 Elo Reported settings GPT-6.1 Sol (Low); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-low	1,450.1 Elo Reported settings GPT-6.1 Sol (Medium); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-medium	1,511.35 Elo Reported settings GPT-6.1 Sol (High); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-high	1,538.05 Elo Reported settings GPT-6.1 Sol (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-xhigh	1,593.85 Elo Reported settings GPT-6.1 Sol (Max); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol
Harvey LAB-AA v1.1: Hallucination-Gated All-Pass RateArtificial Analysis · Stirrup; Harvey private dataset v1.1.0; 120 tasks across 24 practice areas; up to 200 turns; internet disabled; GPT-6 Sol, Grok 4.7 and Claude Opus 5.5 rubric judges; GPT-6 Sol High two-pass hallucination check; hallucination-gated all-pass averaged across judges Benchmark details Average over tasks of the share of the judge panel finding every rubric criterion passed, with a task zeroed on any material hallucination · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	Not reported	Not reported	6.94% Reported settings GPT-6.1 Sol (Max); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol
Humanity's Last ExamArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	47.36% Reported settings GPT-6.1 Sol (Low); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-low	49.86% Reported settings GPT-6.1 Sol (Medium); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-medium	51.39% Reported settings GPT-6.1 Sol (High); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-high	52.64% Reported settings GPT-6.1 Sol (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-xhigh	52.92% Reported settings GPT-6.1 Sol (Max); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol
MLCR-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of tasks judged accurate, complete, and concise · Expert + compound (hard) sets · Benchmark developed by Wisedocs · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	Not reported	Not reported	33.89% Reported settings GPT-6.1 Sol (Max); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol
MMMU-ProArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	83.12% Reported settings GPT-6.1 Sol (Low); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-low	83.93% Reported settings GPT-6.1 Sol (Medium); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-medium	84.91% Reported settings GPT-6.1 Sol (High); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-high	85.09% Reported settings GPT-6.1 Sol (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-xhigh	85.95% Reported settings GPT-6.1 Sol (Max); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol
AA-Omniscience IndexArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct. · Evaluation results measured independently by Artificial Analysis Unit: index. Source collected 2026-10-18.	37.63 Reported settings GPT-6.1 Sol (Low); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-low	39.95 Reported settings GPT-6.1 Sol (Medium); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-medium	41.45 Reported settings GPT-6.1 Sol (High); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-high	40.87 Reported settings GPT-6.1 Sol (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-xhigh	41.53 Reported settings GPT-6.1 Sol (Max); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol
AA-Omniscience AccuracyArtificial Analysis · 6000 questions; 1 attempt; correct-answer share; GPT-5.6 Luna medium grader Benchmark details AA-Omniscience Accuracy (higher is better) measures the proportion of correctly answered questions out of all questions, regardless of whether the model chooses to answer · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	58.87% Reported settings GPT-6.1 Sol (Low); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-low	60.4% Reported settings GPT-6.1 Sol (Medium); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-medium	60.8% Reported settings GPT-6.1 Sol (High); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-high	60.82% Reported settings GPT-6.1 Sol (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-xhigh	62.1% Reported settings GPT-6.1 Sol (Max); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol
SciCodeArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark curated by scientists across 16 disciplines. SciCode is under review following an independent audit of the dataset · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	53.24% Reported settings GPT-6.1 Sol (Low); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-low	53.24% Reported settings GPT-6.1 Sol (Medium); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-medium	55.79% Reported settings GPT-6.1 Sol (High); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-high	55.67% Reported settings GPT-6.1 Sol (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-xhigh	54.17% Reported settings GPT-6.1 Sol (Max); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol
Terminal-Bench-Science 0.1Artificial Analysis · mini-swe-agent; Terminal-Bench-Science 0.1.0; 70 tasks; pass@1 averaged over 3 repeats Benchmark details Share of tasks passed (pass@1), averaged over three repeats · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	Not reported	Not reported	58.1% Reported settings GPT-6.1 Sol (Max); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol
Terminal-Bench v4.0Artificial Analysis · mini-SWE-agent v2.4.6; 66 tasks; pass@1 averaged over 3 repeats; 500 steps; task timeout up to 8 hours Benchmark details Benchmark developed by the Laude Institute, Stanford, and open-source contributors · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	30.81% Reported settings GPT-6.1 Sol (Low); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-low	47.98% Reported settings GPT-6.1 Sol (Medium); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-medium	51.52% Reported settings GPT-6.1 Sol (High); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-high	54.04% Reported settings GPT-6.1 Sol (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol-xhigh	56.06% Reported settings GPT-6.1 Sol (Max); Model source: https://artificialanalysis.ai/models/gpt-6-1-sol
ARC-AGI-2ARC Prize · v2 Semi-Private Benchmark details Original public board. Configuration and task coverage may differ; inspect source. Unit: percent. Source collected 2026-10-18.	76.67% Reported settings GPT-6.1 Sol (Low); Source model ID: openai-gpt-6-1-sol-low; 120 tasks	86.67% Reported settings GPT-6.1 Sol (Medium); Source model ID: openai-gpt-6-1-sol-medium; 120 tasks	91.67% Reported settings GPT-6.1 Sol (High); Source model ID: openai-gpt-6-1-sol-high; 120 tasks	91.67% Reported settings GPT-6.1 Sol (XHigh); Source model ID: openai-gpt-6-1-sol-xhigh; 120 tasks	94.17% Reported settings GPT-6.1 Sol (Max); Source model ID: openai-gpt-6-1-sol-max; 120 tasks
ARC-AGI-3 · provider-adapterARC Prize · Provider Adapter Benchmark details ARC-AGI-3; Provider Adapter. Open each result for its exact effort, task subset, metric and protocol details. Unit: percent. Source collected 2026-10-18.	82.79% Reported settings ARC-AGI-3 Semi-Private verified summary; Provider Adapter harness; source group openai-gpt-6-1-sol; variant provider-adapter-low; public-demo task scores are excluded	91.02% Reported settings ARC-AGI-3 Semi-Private verified summary; Provider Adapter harness; source group openai-gpt-6-1-sol; variant provider-adapter-medium; public-demo task scores are excluded	94.99% Reported settings ARC-AGI-3 Semi-Private verified summary; Provider Adapter harness; source group openai-gpt-6-1-sol; variant provider-adapter-high; public-demo task scores are excluded	96.37% Reported settings ARC-AGI-3 Semi-Private verified summary; Provider Adapter harness; source group openai-gpt-6-1-sol; variant provider-adapter-xhigh; public-demo task scores are excluded	96.18% Reported settings ARC-AGI-3 Semi-Private verified summary; Provider Adapter harness; source group openai-gpt-6-1-sol; variant provider-adapter-max; public-demo task scores are excluded
ARC-AGI-3 · standardARC Prize · Standard Benchmark details ARC-AGI-3; Standard. Open each result for its exact effort, task subset, metric and protocol details. Unit: percent. Source collected 2026-10-18.	3.92% Reported settings ARC-AGI-3 Semi-Private verified summary; Standard harness; source group openai-gpt-6-1-sol; variant low; public-demo task scores are excluded	10.57% Reported settings ARC-AGI-3 Semi-Private verified summary; Standard harness; source group openai-gpt-6-1-sol; variant medium; public-demo task scores are excluded	26.72% Reported settings ARC-AGI-3 Semi-Private verified summary; Standard harness; source group openai-gpt-6-1-sol; variant high; public-demo task scores are excluded	39.93% Reported settings ARC-AGI-3 Semi-Private verified summary; Standard harness; source group openai-gpt-6-1-sol; variant xhigh; public-demo task scores are excluded	52.73% Reported settings ARC-AGI-3 Semi-Private verified summary; Standard harness; source group openai-gpt-6-1-sol; variant max; public-demo task scores are excluded
FrontierCode 1.1 · extended-codexCognition · codex Benchmark details FrontierCode 1.1; codex. Open each result for its exact effort, task subset, metric and protocol details. Unit: percent. Source collected 2026-10-18.	58.09% Reported settings FrontierCode 1.1; extended; 150 tasks; codex; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0013	60.4% Reported settings FrontierCode 1.1; extended; 150 tasks; codex; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0027	59.27% Reported settings FrontierCode 1.1; extended; 150 tasks; codex; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0	60.37% Reported settings FrontierCode 1.1; extended; 150 tasks; codex; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.004	59.81% Reported settings FrontierCode 1.1; extended; 150 tasks; codex; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0013
FrontierCode 1.1 · main-codexCognition · codex Benchmark details FrontierCode 1.1; codex. Open each result for its exact effort, task subset, metric and protocol details. Unit: percent. Source collected 2026-10-18.	45.46% Reported settings FrontierCode 1.1; main; 100 tasks; codex; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.002	50.23% Reported settings FrontierCode 1.1; main; 100 tasks; codex; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.004	47.98% Reported settings FrontierCode 1.1; main; 100 tasks; codex; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0	49.29% Reported settings FrontierCode 1.1; main; 100 tasks; codex; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.006	47.57% Reported settings FrontierCode 1.1; main; 100 tasks; codex; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.002
Terminal-Bench 4.0 · codexTerminal-Bench · Codex Benchmark details Terminal-Bench 4.0; Codex. Open each result for its exact effort, task subset, metric and protocol details. Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	Not reported	Not reported	58.2% Reported settings Terminal-Bench 4.0.0; 66 tasks; Codex; effort max; reported margin ±3.1 percentage points, confidence level unspecified; release date 2026-09-29; board checked 2026-10-07
LiveBench · AMPS Hard · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	Not reported	98% Reported settings LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; gpt-6.1-sol-xhigh; checkpoint=gpt-6.1-sol	98% Reported settings LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; gpt-6.1-sol-max; checkpoint=gpt-6.1-sol
LiveBench · code completion · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	Not reported	82.61% Reported settings LiveBench official task evaluation; livebench-2026-06-25-code_completion; gpt-6.1-sol-xhigh; checkpoint=gpt-6.1-sol	80.44% Reported settings LiveBench official task evaluation; livebench-2026-06-25-code_completion; gpt-6.1-sol-max; checkpoint=gpt-6.1-sol
LiveBench · code generation · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	Not reported	78.87% Reported settings LiveBench official task evaluation; livebench-2026-06-25-code_generation; gpt-6.1-sol-xhigh; checkpoint=gpt-6.1-sol	80.28% Reported settings LiveBench official task evaluation; livebench-2026-06-25-code_generation; gpt-6.1-sol-max; checkpoint=gpt-6.1-sol

What these comparisons mean

Each source reports its own effort labels. Matching labels do not establish equal compute budgets or identical fallback behavior. Open Reported settings to inspect the exact model name, agent and task coverage. Multiple results at one level remain visible rather than selecting the best. Source-reported None or Non-reasoning labels are not treated as evidence that an API supports those settings.

These measurements use their own dated source collection. The leaderboard fits identified configurations jointly; it contains no pooled model ratings. Explicit thinking budgets are separate configurations. Read the methodology.

Download all effort benchmark results · 8,915 results across 259 models · Collected 2026-10-18

GPT-6.1 Sol · High

Compare with

One configuration, seven capabilities

Agentic

Hard reasoning

Coding

Human pref

Knowledge

Multimodal

Long context

Capability score evidence

Benchmark results