o1-mini is the stronger all-rounder.
Scores updated · 18 tests both models report · How we compare
Where each one wins
Tests won in each of the two areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
Coding and reasoning rest on a single test each.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where o1-mini pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+24.8points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+18points ahead
Where DeepSeek-V2.5 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 18 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results16 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- Codeforceso1-mini by 1784 rating points35.61820+1784 rating
- AIME 2024o1-mini by 46.916.763.6+46.9
- MATHo1-mini by 15.374.790+15.3
- MATH-500 (EM)o1-mini by 15.374.790+15.3
- Aider-Polygloto1-mini by 15.117.832.9+15.1
- MMLU-Proo1-mini by 14.166.280.3+14.1
- Chinese SimpleQA (C-SimpleQA)DeepSeek-V2.5 by 13.854.140.3+13.8
- FRAMES (Acc.)o1-mini by 11.565.476.9+11.5
- MMLU-Reduxo1-mini by 6.480.386.7+6.4
- MMLUo1-mini by 4.880.485.2+4.8
- IFEvalo1-mini by 4.280.684.8+4.2
- DROP (3-shot F1)DeepSeek-V2.5 by 3.987.883.9+3.9
- HumanEvalo1-mini by 3.48992.4+3.4
- AA Intelligenceo1-mini by 3.26.69.8+3.2
- SimpleQADeepSeek-V2.5 by 3.210.27+3.2
- CLUEWSCtie90.489.9tie
Questions people ask
Which is better, DeepSeek-V2.5 or o1-mini?
o1-mini wins all two areas where both have results: coding and reasoning. DeepSeek-V2.5 wins none.
Which is better for coding?
o1-mini. It wins the one coding test both models report.
How do you compare the two?
We use the 18 benchmark tests both models have published scores on. The verdict counts the 2 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 16 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.