Model card
GPT-5.1.
OpenAIapi
§ 01 · Benchmarks
Every benchmark GPT-5.1 has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | SWE-Bench Verified | Computer Code · Code Generation | resolve-rate | 76.3% | #11 | — | source ↗ |
| 02 | MMLU-Pro | Reasoning · Commonsense Reasoning | accuracy | 87.0% | #13 | 2026-04-20 | source ↗ |
| 03 | SWE-bench Verified | Agentic AI · SWE-bench | resolve-rate | 76.3% | #16 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area
Where GPT-5.1 actually performs.
§ 04 · Related models
Other OpenAI models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
openai-blog
1
result
pricepertoken
1
result
editorial
1
result
1 of 3 rows marked verified.