Model card
GPT-4.1.
OpenAIapiLLM
GPT-4.1 successor to GPT-4 Turbo.
§ 02 · Benchmarks
Every benchmark GPT-4.1 has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | HumanEval | Code & Software Engineering · Code Generation | pass@1 | 94.5% | #5 | 2026-04-20 | source ↗ |
| 02 | MATH | Language & Knowledge · Mathematical Reasoning | accuracy | 82.1% | #20 | 2026-04-20 | |
| 03 | MMLU | — | accuracy | 90.2% | #5 | 2026-04-20 | |
| 04 | GPQA | — | accuracy | 66.3% | #7 | 2026-04-20 | |
| 05 | SWE-Bench Verified | Code & Software Engineering · Code Generation | resolve-rate | 54.6% | #31 | 2026-04-20 |
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.
§ 03 · Strengths by area
Where GPT-4.1 actually performs.
§ 06 · Sources & freshness
Where these numbers come from.
src
4
results
codesota-api
1
result
0 of 5 rows marked verified.