OpenAI · model
GPT-5.5 Pro benchmark scores
As of 2026-11-22, GPT-5.5 Pro (OpenAI) has measured scores on 9 benchmarks and estimated scores on 76 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 93.6% | estimated ± 2.7 pp, high confidence |
| AA-HLE | 42.0% | estimated ± 4.6 pp, high confidence |
| AIME26 | 98.1% | estimated ± 1.4 pp, medium confidence |
| Artificial Analysis Intelligence Index | 33.7% | estimated ± 5.6 pp, medium confidence |
| CritPt | 30.6% | measured |
| GDPval-AA | 53.1% | estimated ± 7.8 pp, medium confidence |
| GPQA Diamond | 93.4% | estimated ± 1.4 pp, high confidence |
| HLE | 57.2% | measured |
| AA-Omniscience Accuracy | 53.8% | estimated ± 7.4 pp, medium confidence |
| BrowseComp | 90.1% | measured |
| HLE w/ tools | 62.3% | estimated ± 5.6 pp, medium confidence |
| VITA-Bench | 47.1% | estimated ± 6.7 pp, low confidence |
| τ²-bench results | 93.6% | estimated ± 11.8 pp, low confidence |
| APEX-Agents-AA | 41.0% | estimated ± 4.4 pp, high confidence |
| BioMysteryBench (human-difficult) | 49.8% | estimated ± 6.8 pp, low confidence |
| DeepSearchQA | 92.2% | estimated ± 6.8 pp, low confidence |
| CyberGym | 88.2% | estimated ± 7.3 pp, medium confidence |
| JobBench | 56.4% | estimated ± 10.7 pp, low confidence |
| SkillsBench | 63.3% | estimated ± 4.1 pp, medium confidence |
| WideResearch | 82.3% | estimated ± 3.5 pp, high confidence |
| AA Agentic Index | 49.1% | estimated ± 8.2 pp, medium confidence |
| MMLU-Pro | 85.7% | estimated ± 2.5 pp, low confidence |
| FailureSensorIQ | 68.2% | estimated ± 2.1 pp, high confidence |
| GPQA | 94.4% | estimated ± 1.6 pp, high confidence |
| Vals GPQA Diamond | 93.2% | estimated ± 2.3 pp, high confidence |
| Vals MMLU-Pro | 88.5% | estimated ± 1.8 pp, high confidence |
| Chess Puzzles | 62.0% | measured |
| Gert Labs | 66.2% | estimated ± 11.1 pp, low confidence |
| AA Harvey LAB v1.0 | 92.9% | estimated ± 9.8 pp, low confidence |
| AA Tau3 Banking | 43.9% | estimated ± 3.6 pp, medium confidence |
| ARC-AGI-1 | 95.0% | measured |
| ARC-AGI-2 | 84.2% | measured |
| EBR-bench | 52.8% | estimated ± 12.7 pp, low confidence |
| FrontierMath v2 (Tier 4) | 78.0% | measured |
| FrontierMath v2 (Tiers 1-3) | 87.7% | measured |
| Furniture Assembly | 59.7% | estimated ± 14.1 pp, low confidence |
| MaxxBench | 66.7% | estimated ± 10.3 pp, low confidence |
| MazeBench | 8.3% | estimated ± 6.4 pp, low confidence |
| Mystery Game Puzzles | 57.0% | estimated ± 10.3 pp, low confidence |
| NYT Connections | 93.0% | estimated ± 12.6 pp, low confidence |
| OSWorld-Verified | 84.8% | estimated ± 5.7 pp, low confidence |
| CWE-Bench-AA | 55.3% | estimated ± 6.4 pp, medium confidence |
| AA Cyber Index | 42.4% | estimated ± 13.5 pp, low confidence |
| DeepsecBench-AA | 24.6% | estimated ± 9.0 pp, low confidence |
| HealthBench Professional (length-adjusted, Artificial Analysis) | 57.9% | estimated ± 4.4 pp, low confidence |
| HealthBench Professional (raw, Artificial Analysis) | 70.1% | estimated ± 0.8 pp, medium confidence |
| AA ITBench | 50.1% | estimated ± 4.1 pp, high confidence |
| DRACO | 85.9% | estimated ± 2.9 pp, medium confidence |
| FrontierPhysics | 15.6% | estimated ± 6.1 pp, medium confidence |
| HLE w/o tools | 43.1% | measured |
| SpireClimb | 13.6% | estimated ± 10.3 pp, low confidence |
| StealthMark | 60.6% | estimated ± 9.7 pp, low confidence |
| Toolathlon-Verified | 74.9% | estimated ± 7.4 pp, medium confidence |
| ARC-AGI-3 | 4.9% | estimated ± 7.2 pp, medium confidence |
| SkillsBench official leaderboard (BenchFlow) | 59.5% | estimated ± 6.2 pp, medium confidence |
| FACTS Multimodal | 51.6% | estimated ± 5.6 pp, medium confidence |
| ExploitBench | 84.5% | estimated ± 13.4 pp, low confidence |
| ExploitGym | 27.8% | estimated ± 9.2 pp, low confidence |
| Claw-Eval | 80.0% | estimated ± 6.4 pp, medium confidence |
| HMMT Feb 2026 | 100.0% | estimated ± 3.1 pp, medium confidence |
| HMMT Nov 2025 | 96.0% | estimated ± 1.5 pp, low confidence |
| MCP Atlas | 79.5% | estimated ± 10.3 pp, low confidence |
| MMAnswerBench | 96.2% | estimated ± 2.4 pp, low confidence |
| MMLU-Redux | 97.0% | estimated ± 2.1 pp, medium confidence |
| SuperGPQA | 96.0% | estimated ± 7.2 pp, low confidence |
| Toolathlon | 60.9% | estimated ± 4.2 pp, high confidence |
| HealthBench Hard | 34.0% | estimated ± 8.6 pp, low confidence |
| MedXpertQA (Text) | 60.6% | estimated ± 8.9 pp, low confidence |
| ResearchClawBench | 20.0% | estimated ± 2.3 pp, low confidence |
| DAYJOB | 11.3% | estimated ± 6.3 pp, medium confidence |
| DAYJOB Healthcare | 8.3% | estimated ± 6.1 pp, low confidence |
| BioMysteryBench (human-solvable) | 89.5% | estimated ± 0.6 pp, medium confidence |
| HealthBench (raw) | 48.7% | estimated ± 7.6 pp, low confidence |
| HealthBench (length-adjusted) | 57.1% | estimated ± 2.5 pp, low confidence |
| HealthBench Professional | 52.3% | estimated ± 4.2 pp, medium confidence |
| HLE-Verified | 52.6% | estimated ± 1.3 pp, medium confidence |
| LABBench2 | 80.6% | estimated ± 1.7 pp, low confidence |
| BlenderWorld (text-only) | 85.7% | estimated ± 4.0 pp, medium confidence |
| Cookie-Bench | 89.5% | estimated ± 2.5 pp, medium confidence |
| Agents' Last Exam | 40.7% | estimated ± 11.6 pp, low confidence |
| SEC-Bench Pro | 71.6% | estimated ± 12.3 pp, low confidence |
| BioBasicsBench | 34.3% | estimated ± 5.1 pp, low confidence |
| LifeVal | 79.6% | estimated ± 1.6 pp, medium confidence |
| ExploitBench Internal Port | 10.0% | estimated ± 1.4 pp, medium confidence |
| PinchBench | 90.7% | estimated ± 3.6 pp, low confidence |