OpenAI
GPT-5.4
Takes prompts of 1 million tokens and can operate a computer itself. Released with GPT-5.4 Pro.
- Announced
- Access
- Public
Benchmark scores
| Test | Score | Best on the tracker | How it was measured |
|---|---|---|---|
| Epoch Capabilities Indexmany tests combined into one score | 158 points | GPT-6.2 Astra 174 points | Independentlisted as "GPT-5.4", CI 155.95 to 159.96Run 9 Nov 2026 |
| MirrorCoderebuilding whole programs | 16% | 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, ±7.7 SERun 10 Aug 2026 |
| APEX-Agentsprofessional office tasks | 52% | Gemini 4 Carbon 84% | Independentpass@1, unknown effort; listed as "GPT-5.4" |
| Humanity's Last Examexpert questions, no tools | 36% | GPT-6 Astra 55% | Independentleaderboard entry "gpt-5.4-2026-03-05 (xhigh thinking)" (gpt-5.4-2026-03-05_xhigh) |
| ARC-AGI-3puzzle games, standard harnessTypical first-time human player: 100% | 0.2% | Claude Fable 5.2 81% | IndependentARC Prize config "GPT-5.4 (High)" (openai-gpt-5-4-2026-03-05-high), standard harness |
| FrontierMath T1–3hard maths problems | 79% | Claude Fable 5.2 95% | Independentxhigh reasoning effort (gpt-5.4-2026-03-05_xhigh)Run 11 Jun 2026 |
| GPQA DiamondPhD-level science questionsPhD experts: 70%Saturated | 93% | Gemini 4 Argon 96% | Independentxhigh reasoning effort (gpt-5.4-2026-03-05_xhigh)Run 6 Mar 2026 |
| FrontierMath T4research-level maths problemsSaturated | 49% | GPT-6.1 Sol 100% | Independentxhigh reasoning effort (gpt-5.4-2026-03-05_xhigh)Run 11 Jun 2026 |
| ARC-AGI-2visual puzzles, model aloneAverage person: 60%Saturated | 74% | GPT-6 Astra 95% | IndependentARC Prize config "GPT-5.4 (XHigh)" (gpt-5-4-xhigh) |
| OTIS Mock AIMEcompetition mathsSaturated | 98% | GPT-5.5 100% | Independenthigh reasoning effort (gpt-5.4-2026-03-05_high)Run 15 Jul 2026 |
| SWE-bench Verifiedfixing real software bugsKnown flaws | 77% | Claude Opus 4.7 83% | Independenthigh reasoning effort (gpt-5.4-2026-03-05_high)Run 6 Mar 2026 |
| METR time horizon (TH1.1 + TH2)task length an AI agent finishes half the time | 5.9 h | GPT-6 Astra 1.7 days | IndependentPooled TH1.1 + TH2 suites; 95% CI 199.5–592.0 min |
| METR time horizontask length an AI agent finishes half the timeNo longer updated | 5.7 h | Claude Mythos Preview 17 h | IndependentMETR Horizon v1.1 run 'gpt_5_4', xhigh reasoning effort (per Epoch AI mapping); 95% CI 186.6–768.8 min |
Sources
- Introducing GPT-5.4OpenAI · 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