RankingEffort benchmarks
GPT-5.5
158 measured results · 7 effort settings · 75 benchmark/harness combinations
Change model
Capability profile
One configuration, seven capabilities
- AGPT-5.5 · XHigh5 of 7 capabilities supported
Gaps are unknown, not zero. Hollow points are preliminary.
Agentic
A55.0SupportedHard reasoning
A58.9SupportedCoding
A66.4SupportedHuman pref
UnknownKnowledge
A61.1SupportedMultimodal
A35.2SupportedLong context
A78.1Preliminary
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-5.5 · XHigh: 56.9 overall comparison score. Meets the overall evidence requirements.
Shared-result disagreement. This aggregate order conflicts with matched benchmark results against 1 other configurations. Different test coverage and opponents affect the fit. Inspect published results before treating the rank as conclusive.
Which sources carry the weight?
- Moonshot AI · 24.2% direct comparison weight · provider report
- Cognition · 8.0% direct comparison weight · independent of the model provider
- LiveBench · 8.0% direct comparison weight · independent of the model provider
- Terminal-Bench · 8.0% direct comparison weight · independent of the model provider
- Vals AI · 8.0% direct comparison weight · independent of the model provider
- ARC Prize · 7.9% direct comparison weight · independent of the model provider
- Artificial Analysis · 7.8% direct comparison weight · independent of the model provider
- Scale · 7.8% direct comparison weight · independent of the model provider
- SWE-rebench · 7.5% direct comparison weight · independent of the model provider
- Epoch AI · 6.8% direct comparison weight · independent of the model provider
- Datacurve · 5.8% direct comparison weight · independent of the model provider
Which benchmark families carry the weight?
- Terminal-Bench · 8.5% direct comparison weight
- DeepSWE · 8.2% direct comparison weight
- FrontierCode · 8.0% direct comparison weight
- ARC-AGI · 7.9% direct comparison weight
- swe-rebench · 7.5% direct comparison weight
- Other families (40) · 59.8% 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.
DeepSWE v1.1 review: Epoch AI reported grading errors in at least 23 of 113 tasks. These published results remain included. Review their limitations in Epoch's review when interpreting this evidence.
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 2026-11-22.
Both ranks use the same surviving configurations for each removal. The cohort starts with 602 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.
| Removed source | Rank before → after | Rank movement | Cohort remaining / lost support | Score after (change) |
|---|---|---|---|---|
| Artificial Analysis | 79 → 77 | Up 2 | 230 remaining / 372 lost | 57.7 |
| ARC Prize | 90 → 93 | Down 3 | 602 remaining / 0 lost | 59.2 |
| Datacurve | 90 → 87 | Up 3 | 602 remaining / 0 lost | 52.5 |
| LiveCodeBench | 90 → 90 | No movement | 602 remaining / 0 lost | 56.8 |
| Scale | 90 → 90 | No movement | 602 remaining / 0 lost | 58.4 |
| Terminal-Bench | 90 → 90 | No movement | 602 remaining / 0 lost | 56.9 |
| Cognition | 90 → 80 | Up 10 | 602 remaining / 0 lost | 56.9 |
| LiveBench | 90 → 92 | Down 2 | 601 remaining / 1 lost | 57.4 |
| SWE-rebench | 90 → 94 | Down 4 | 602 remaining / 0 lost | 54.9 |
| Epoch AI | 90 → 91 | Down 1 | 588 remaining / 14 lost | 57.3 |
| Vals AI | 90 → 85 | Up 5 | 601 remaining / 1 lost | 58.0 |
| Provider reports · Anthropic | 90 → 90 | No movement | 602 remaining / 0 lost | 56.9 |
| Provider reports · Moonshot AI | 90 → 70 | Up 20 | 602 remaining / 0 lost | 64.8 |
| Provider reports · Meta | 90 → 90 | No movement | 602 remaining / 0 lost | 56.8 |
| Provider reports · Mistral | 90 → 90 | No movement | 602 remaining / 0 lost | 56.9 |
| Provider reports · OpenAI | 90 → 91 | Down 1 | 602 remaining / 0 lost | 56.7 |
| All provider reports | 90 → 71 | Up 19 | 602 remaining / 0 lost | 64.4 |
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 | 52.0 | -4.8 |
| swe-rebench | 54.9 | -2.0 |
| arc-agi | 58.3 | +1.4 |
| swe-atlas-test-writing | 57.9 | +1.1 |
| gpqa | 55.9 | -1.0 |
| hle | 57.7 | +0.9 |
| swe-atlas-refactoring | 56.0 | -0.9 |
| simpleqa | 57.7 | +0.8 |
| swe-atlas-qna | 56.1 | -0.7 |
| swe-bench-pro | 56.3 | -0.6 |
| mmlu-pro | 57.4 | +0.6 |
| mmmu-pro | 57.4 | +0.6 |
| enigma-eval | 57.4 | +0.6 |
| terminal-bench | 57.4 | +0.5 |
| livebench-instructions | 57.4 | +0.5 |
| livebench-coding | 56.4 | -0.5 |
| frontiermath | 56.4 | -0.4 |
| vals-code-migration | 56.5 | -0.4 |
| epoch-game-puzzles | 56.5 | -0.3 |
| vals-legal-research | 56.6 | -0.3 |
| livebench-math | 57.1 | +0.2 |
| vals-excel-modeling | 56.7 | -0.2 |
| vals-finance-agent | 57.0 | +0.2 |
| livebench-reasoning | 56.7 | -0.2 |
| omniscience | 57.0 | +0.1 |
| automationbench | 57.0 | +0.1 |
| gdp-pdf | 57.0 | +0.1 |
| tau-bench | 56.7 | -0.1 |
| analyst-agent | 56.8 | -0.1 |
| aime | 56.8 | -0.1 |
| itbench | 56.8 | -0.1 |
| ifbench | 56.8 | -0.1 |
| livebench-data | 56.8 | -0.1 |
| vals-tax-agent | 56.9 | +0.0 |
| terminal-bench-science | 56.9 | +0.0 |
| livebench-language | 56.8 | -0.0 |
| harvey | 56.8 | -0.0 |
| aa-lcr | 56.8 | -0.0 |
| vibe-code | 56.9 | +0.0 |
| frontiercode | 56.9 | +0.0 |
| critpt | 56.9 | +0.0 |
| gdpval | 56.9 | +0.0 |
| livecodebench | 56.8 | -0.0 |
| apex-agents | 56.9 | +0.0 |
| arc-agi-3 | 56.9 | +0.0 |
| gmmlu | 56.9 | +0.0 |
| enterprise-ops | 56.9 | +0.0 |
| multi-swe-bench | 56.9 | -0.0 |
| briefcase | 56.9 | -0.0 |
| math500 | 56.9 | +0.0 |
What evidence is missing from the fit?
Across all collected settings for this model: 313 observations, 156 contributing, 0 matched without graph weight and 157 excluded. Counts do not establish rank eligibility.
- 3 · 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
- 1 · Fewer than two distinct model identities remain in this evaluation
- 4 · Benchmark family or source protocol has not been reviewed
- 7 · Evaluator has not been reviewed for independent admission
- 1 · Effort is not identified
- 7 · Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison.
- 1 · Kimi K3 Evaluation Details cites GLM release blog or Vals AI, per model; retain as published context, not a new Moonshot comparison.
- 1 · Kimi K3 Evaluation Details cites GLM release blog, Artificial Analysis or OpenAI, per model; retain as published context, not a new Moonshot comparison.
- 1 · Kimi K3 Evaluation Details cites FrontierSWE leaderboard; retain as published context, not a new Moonshot comparison. Historical provider claim; secondary and superseded for current FrontierSWE comparisons by the independent Proximal FrontierSWE v2 mean@5 board at https://www.frontierswe.com/. Version-unspecified claims are not v2 results. Excluded from weighted Overall.
- 54 · Supporting evidence outside the reviewed capability core
- 1 · Kimi K3 Evaluation Details cites official PostTrainBench results; retain as published context, not a new Moonshot comparison.
- 1 · Kimi K3 Evaluation Details cites Anthropic or OpenAI release reports; retain as published context, not a new Moonshot comparison.
- 1 · Kimi K3 Evaluation Details cites official Agents Last Exam leaderboard; retain as published context, not a new Moonshot comparison.
- 1 · Kimi K3 Evaluation Details cites Artificial Analysis / APEX-Agents leaderboard; retain as published context, not a new Moonshot comparison.
- 3 · Kimi K3 Evaluation Details cites Vals AI; retain as published context, not a new Moonshot comparison.
- 47 · No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately
- 17 · Narrow specialist biological, medical or security evaluation; preserved as raw evidence outside general capability scoring.
- 1 · MiniMax cites this comparator from the official Terminal-Bench leaderboard; a common protocol with its internal Terminus 2 run is not established. See MiniMax M3 benchmark figure, Terminal-bench 2.1 methodology.
- 5 · Composite index or publisher-specific internal evaluation lacks a stable general-capability comparison unit.
Benchmark results
Reviewed retained observations are in use. October 2026 Real-SWE board has no 95% confidence whisker, so these scores stay at the 2026-10-18 retrieval. Original source retrieval 2026-10-18; source updated 2026-10-18.
| Benchmark / source | Low | Medium | High | XHigh | None | Non-reasoning | Unspecified |
|---|---|---|---|---|---|---|---|
AA-AnalystAgentBenchmark detailsShare 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 2026-11-22. | Not reported | Not reported | Not reported | 50% Reported settingsGPT-5.5 (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5 | Not reported | 7.5% Reported settingsGPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning | Not reported |
AA-Briefcase EloBenchmark detailsAA-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 2026-11-22. | Not reported | 1,000 Elo Reported settingsGPT-5.5 (Medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium | 1,087.26 Elo Reported settingsGPT-5.5 (High); Model source: https://artificialanalysis.ai/models/gpt-5-5-high | 1,135.18 Elo Reported settingsGPT-5.5 (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5 | Not reported | Not reported | Not reported |
APEX-Agents-AABenchmark detailsIndependently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | Not reported | Not reported | Not reported | 37.68% Reported settingsGPT-5.5 (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5 | Not reported | Not reported | Not reported |
AA-LCR v1.1Benchmark detailsIndependently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | 81% Reported settingsGPT-5.5 (Low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low | 83% Reported settingsGPT-5.5 (Medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium | 84.33% Reported settingsGPT-5.5 (High); Model source: https://artificialanalysis.ai/models/gpt-5-5-high | 84.33% Reported settingsGPT-5.5 (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5 | Not reported | 64% Reported settingsGPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning | Not reported |
AutomationBench-AABenchmark detailsShare 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 2026-11-22. | Not reported | 40.07% Reported settingsGPT-5.5 (Medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium | 44.35% Reported settingsGPT-5.5 (High); Model source: https://artificialanalysis.ai/models/gpt-5-5-high | 47.3% Reported settingsGPT-5.5 (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5 | Not reported | Not reported | Not reported |
CritPtBenchmark detailsBenchmark developed by Argonne and UIUC, with contributions from 60+ researchers globally · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | 8% Reported settingsGPT-5.5 (Low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low | 18.57% Reported settingsGPT-5.5 (Medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium | 25.43% Reported settingsGPT-5.5 (High); Model source: https://artificialanalysis.ai/models/gpt-5-5-high | 27.14% Reported settingsGPT-5.5 (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5 | Not reported | 1.43% Reported settingsGPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning | Not reported |
EnterpriseOps-Gym-AABenchmark detailsOverall task success rate across all eight enterprise domains (oracle tool mode) · Benchmark developed by ServiceNow Research · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | Not reported | 44.11% Reported settingsGPT-5.5 (Medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium | Not reported | 46.64% Reported settingsGPT-5.5 (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5 | Not reported | Not reported | Not reported |
GDP.pdf: All-pass RateBenchmark detailsShare of attempts where every atomic criterion passed · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | Not reported | 20.6% Reported settingsGPT-5.5 (Medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium | 22.6% Reported settingsGPT-5.5 (High); Model source: https://artificialanalysis.ai/models/gpt-5-5-high | 21.2% Reported settingsGPT-5.5 (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5 | Not reported | Not reported | Not reported |
GDPval-AA v2.1 LeaderboardBenchmark detailsElo 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 2026-11-22. | 1,053.07 Elo Reported settingsGPT-5.5 (Low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low | 1,241.98 Elo Reported settingsGPT-5.5 (Medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium | 1,335.27 Elo Reported settingsGPT-5.5 (High); Model source: https://artificialanalysis.ai/models/gpt-5-5-high | 1,357.23 Elo Reported settingsGPT-5.5 (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5 | Not reported | 977.8 Elo Reported settingsGPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning | Not reported |
GPQA DiamondBenchmark detailsIndependently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | 91.01% Reported settingsGPT-5.5 (Low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low | 92.63% Reported settingsGPT-5.5 (Medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium | 93.23% Reported settingsGPT-5.5 (High); Model source: https://artificialanalysis.ai/models/gpt-5-5-high | 93.54% Reported settingsGPT-5.5 (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5 | Not reported | 76.77% Reported settingsGPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning | Not reported |
Humanity's Last ExamBenchmark detailsIndependently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | 32.67% Reported settingsGPT-5.5 (Low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low | 42.35% Reported settingsGPT-5.5 (Medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium | 45.04% Reported settingsGPT-5.5 (High); Model source: https://artificialanalysis.ai/models/gpt-5-5-high | 45.78% Reported settingsGPT-5.5 (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5 | Not reported | 13.72% Reported settingsGPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning | Not reported |
IFBenchBenchmark detailsIndependently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | 64.35% Reported settingsGPT-5.5 (Low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low | 70.95% Reported settingsGPT-5.5 (Medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium | 71.63% Reported settingsGPT-5.5 (High); Model source: https://artificialanalysis.ai/models/gpt-5-5-high | 75.85% Reported settingsGPT-5.5 (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5 | Not reported | 46.12% Reported settingsGPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning | Not reported |
ITBench-AABenchmark detailsCombined public and private Site Reliability Engineering (SRE) tasks · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | Not reported | Not reported | Not reported | 45.81% Reported settingsGPT-5.5 (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5 | Not reported | Not reported | Not reported |
MLCR-AABenchmark detailsShare of responses judged complete with no claim contradicting the record · Expert + compound (hard) sets · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | Not reported | 22.22% Reported settingsGPT-5.5 (Medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium | 25% Reported settingsGPT-5.5 (High); Model source: https://artificialanalysis.ai/models/gpt-5-5-high | 28.89% Reported settingsGPT-5.5 (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5 | Not reported | Not reported | Not reported |
MMMU-ProBenchmark detailsIndependently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | 79.02% Reported settingsGPT-5.5 (Low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low | 81.16% Reported settingsGPT-5.5 (Medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium | 81.1% Reported settingsGPT-5.5 (High); Model source: https://artificialanalysis.ai/models/gpt-5-5-high | 79.88% Reported settingsGPT-5.5 (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5 | Not reported | 71.39% Reported settingsGPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning | Not reported |
SciCodeBenchmark detailsBenchmark 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 2026-11-22. | Not reported | 54.51% Reported settingsGPT-5.5 (Medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium | 56.13% Reported settingsGPT-5.5 (High); Model source: https://artificialanalysis.ai/models/gpt-5-5-high | 55.79% Reported settingsGPT-5.5 (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5 | Not reported | Not reported | Not reported |
𝜏²-Bench TelecomBenchmark detailsIndependently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | 83.92% Reported settingsGPT-5.5 (Low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low | 91.81% Reported settingsGPT-5.5 (Medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium | 92.98% Reported settingsGPT-5.5 (High); Model source: https://artificialanalysis.ai/models/gpt-5-5-high | 93.86% Reported settingsGPT-5.5 (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5 | Not reported | 69.3% Reported settingsGPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning | Not reported |
𝜏³-BankingBenchmark detailsBenchmark developed by Sierra Research · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | 24.95% Reported settingsGPT-5.5 (Low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low | 29.9% Reported settingsGPT-5.5 (Medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium | 36.7% Reported settingsGPT-5.5 (High); Model source: https://artificialanalysis.ai/models/gpt-5-5-high | 38.97% Reported settingsGPT-5.5 (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5 | Not reported | 14.85% Reported settingsGPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning | Not reported |
Terminal-Bench HardBenchmark detailsIndependently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | 52.27% Reported settingsGPT-5.5 (Low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low | 57.58% Reported settingsGPT-5.5 (Medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium | 59.85% Reported settingsGPT-5.5 (High); Model source: https://artificialanalysis.ai/models/gpt-5-5-high | 60.61% Reported settingsGPT-5.5 (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5 | Not reported | 49.24% Reported settingsGPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning | Not reported |
Terminal-Bench v2.1Benchmark detailsBenchmark developed by the Laude Institute and open-source contributors · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | 65.54% Reported settingsGPT-5.5 (Low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low | 80.52% Reported settingsGPT-5.5 (Medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium | 79.4% Reported settingsGPT-5.5 (High); Model source: https://artificialanalysis.ai/models/gpt-5-5-high | 84.27% Reported settingsGPT-5.5 (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5 | Not reported | 61.05% Reported settingsGPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning | Not reported |
Terminal-Bench v4.0Benchmark detailsBenchmark 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 2026-11-22. | Not reported | 5.05% Reported settingsGPT-5.5 (Medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium | 9.09% Reported settingsGPT-5.5 (High); Model source: https://artificialanalysis.ai/models/gpt-5-5-high | 14.65% Reported settingsGPT-5.5 (Xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5 | Not reported | Not reported | Not reported |
ARC-AGI-2Benchmark detailsOriginal public board. Configuration and task coverage may differ; inspect source. Unit: percent. Source collected 2026-11-22. | 33.33% Reported settingsGPT-5.5 (Low); Source model ID: gpt-5-5-2026-04-22-thinking-low; 120 tasks | 70.42% Reported settingsGPT-5.5 (Medium); Source model ID: gpt-5-5-2026-04-22-thinking-medium; 120 tasks | 83.33% Reported settingsGPT-5.5 (High); Source model ID: gpt-5-5-2026-04-22-thinking-high; 120 tasks | 85% Reported settingsGPT-5.5 (XHigh); Source model ID: gpt-5-5-2026-04-22-thinking-xhigh; 120 tasks | Not reported | Not reported | Not reported |
DeepSWE v1.1Benchmark detailsOriginal public board. Configuration and task coverage may differ; inspect source. Unit: percent. Source collected 2026-11-22. | 27% Reported settingsgpt-5-5; Reported effort: low; 113 unique tasks; 452 attempts; 4 runs | 54% Reported settingsgpt-5-5; Reported effort: medium; 113 unique tasks; 452 attempts; 4 runs | 64.4% Reported settingsgpt-5-5; Reported effort: high; 113 unique tasks; 452 attempts; 4 runs | 67% Reported settingsgpt-5-5; Reported effort: xhigh; 113 unique tasks; 452 attempts; 4 runs | Not reported | Not reported | Not reported |
Terminal-Bench 2.1Benchmark detailsOriginal public board. Configuration and task coverage may differ; inspect source. Unit: percent. Source collected 2026-11-22. | Not reported | Not reported | Not reported | 83.15% Reported settingsGPT-5.5; Reported effort: xhigh; 445 trials; recorded 2026-04-23 | Not reported | Not reported | Not reported |
Terminal-Bench 2.1Benchmark detailsOriginal public board. Configuration and task coverage may differ; inspect source. Unit: percent. Source collected 2026-11-22. | Not reported | Not reported | Not reported | 77.98% Reported settingsGPT-5.5; Reported effort: xhigh; 445 trials; recorded 2026-04-23 | Not reported | Not reported | Not reported |
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 · 10,184 results across 381 models · Collected 2026-11-22