Codesota · Models · GPT-4.1OpenAI5 results · 5 benchmarks
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.

#BenchmarkArea · TaskMetricValueRankDateSource
01HumanEvalCode & Software Engineering · Code Generationpass@194.5%#5/332026-04-20source ↗
02MATHLanguage & Knowledge · Mathematical Reasoningaccuracy82.1%#20/292026-04-20unverified
03MMLU—accuracy90.2%#5/192026-04-20unverified
04GPQA—accuracy66.3%#7/172026-04-20unverified
05SWE-Bench VerifiedCode & Software Engineering · Code Generationresolve-rate54.6%#31/392026-04-20unverified
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.

Code & Software Engineering
2
benchmarks
avg rank #18.0
Language & Knowledge
1
benchmark
avg rank #20.0
§ 06 · Sources & freshness

Where these numbers come from.

src
4
results
codesota-api
1
result
0 of 5 rows marked verified.