Codesota · Models · o1-previewOpenAI6 results · 6 benchmarks
Model card

o1-preview.

OpenAIcommercialReasoning LLM2 current SOTA

OpenAI's reasoning-focused model.

§ 02 · Benchmarks

Every benchmark o1-preview has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01HumanEvalCode & Software Engineering · Code Generationpass@192.4%#8/332026-04-20source ↗
02MATHLanguage & Knowledge · Mathematical Reasoningaccuracy85.5%#19/292026-04-20unverified
03GSM8KLanguage & Knowledge · Mathematical Reasoningaccuracy97.8%#1/52026-04-20unverified
04MMLU—accuracy90.8%#3/192026-04-20unverified
05GPQA—accuracy73.3%#5/172026-04-20unverified
06AIME 2024Language & Knowledge · Mathematical Reasoningaccuracy83.3%#1/32026-04-20unverified
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 o1-preview actually performs.

Language & Knowledge
3
benchmarks
avg rank #7.0 · 2 SOTA
Code & Software Engineering
1
benchmark
avg rank #8.0
§ 06 · Sources & freshness

Where these numbers come from.

src
5
results
codesota-api
1
result
0 of 6 rows marked verified.