OpenAI
GPT-5.5
Aimed at complex professional work, released with GPT-5.5 Pro. In the API from 24 April 2026.
- Announced
- Released
- Access
- Public
Benchmark scores
| Test | Score | Best on the tracker | How it was measured |
|---|---|---|---|
| Epoch Capabilities Indexmany tests combined into one score | 160 points | GPT-6.2 Astra 174 points | Independentlisted as "GPT-5.5", CI 158.02 to 162.38Run 9 Nov 2026 |
| Remote Labor Indexpaid freelance projects | 6.3% | Claude Fable 5.2 41% | IndependentCodex GPT 5.5Run 1 Jul 2026 |
| MirrorCoderebuilding whole programs | 10% | Claude Opus 5.5 79% | Independenthigh reasoning effort, MirrorCode (ML, +Private, 2L): 15 programs x 2 languages, 3 runs each, 10B-token / 7-day budget, ±6.0 SERun 10 Aug 2026 |
| APEX-Agentsprofessional office tasks | 55% | Gemini 4 Carbon 84% | Independentpass@1, unknown effort; listed as "GPT-5.5" |
| ARC-AGI-3puzzle games, standard harnessTypical first-time human player: 100% | 0.4% | Claude Fable 5.2 81% | IndependentARC Prize config "GPT-5.5 (High)" (openai-gpt-5-5-2026-04-23-high), standard harness |
| FrontierMath T1–3hard maths problems | 85% | Claude Fable 5.2 95% | Independentxhigh reasoning effort (gpt-5.5_xhigh)Run 11 Jun 2026 |
| GPQA DiamondPhD-level science questionsPhD experts: 70%Saturated | 94% | Gemini 4 Argon 96% | Independentxhigh reasoning effort, pre-release checkpoint (gpt-5.5-pre-release_xhigh)Run 24 Apr 2026 |
| FrontierMath T4research-level maths problemsSaturated | 73% | GPT-6.1 Sol 100% | Independentxhigh reasoning effort (gpt-5.5_xhigh)Run 11 Jun 2026 |
| ARC-AGI-2visual puzzles, model aloneAverage person: 60%Saturated | 85% | GPT-6 Astra 95% | IndependentARC Prize config "GPT-5.5 (XHigh)" (gpt-5-5-2026-04-22-thinking-xhigh) |
| OTIS Mock AIMEcompetition mathsSaturated | 100% | Top score | Independentxhigh reasoning effort, pre-release checkpoint (gpt-5.5-pre-release_xhigh)Run 24 Apr 2026 |
| SWE-bench Verifiedfixing real software bugsKnown flaws | 81% | Claude Opus 4.7 83% | Independentxhigh reasoning effort, pre-release checkpoint (gpt-5.5-pre-release_xhigh)Run 24 Apr 2026 |
| METR time horizon (TH1.1 + TH2)task length an AI agent finishes half the time | 11 h | GPT-6 Astra 1.7 days | IndependentPooled TH1.1 + TH2 suites; 95% CI 365.9–1116.4 min |
Also on these charts
Sources
- Introducing GPT-5.5OpenAI · Official · openai.com
- OpenAI API changelogOpenAI · Official · developers.openai.com
- Epoch AI Benchmarking Hub (model release dates and runs)Epoch AI · Dataset · 9 Nov 2026 · epoch.ai