Claude Opus 4 is the stronger all-rounder.
Scores updated · 25 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.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Claude Opus 4 pulls ahead
- Common-sense trick questionsSimpleBench+40.7points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+30.9points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+19.3points ahead
Where o1-mini pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 25 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4
- SWE-bench VerifiedClaude Opus 4 by 30.972.541.6+30.9
- SciCodeClaude Opus 4 by 7.539.832.3+7.5
- LiveCodeBench v6tie47.446.8tie
ReasoningClaude Opus 4
- SimpleBenchClaude Opus 4 by 40.758.818.1+40.7
- GPQA DiamondClaude Opus 4 by 19.379.660.3+19.3
- Humanity's Last ExamClaude Opus 4 by 8.712.33.6+8.7
Other results19 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.
- AIR-Bench 2024Claude Opus 4 by 40.485.745.3+40.4
- Aider-PolyglotClaude Opus 4 by 37.870.732.9+37.8
- AIME 2025Claude Opus 4 by 24.875.550.7+24.8
- ARC-AGI-1Claude Opus 4 by 21.735.714+21.7
- SimpleQAClaude Opus 4 by 15.822.87+15.8
- AIME 2024o1-mini by 15.448.263.6+15.4
- SuperGPQAClaude Opus 4 by 11.356.545.2+11.3
- AA IntelligenceClaude Opus 4 by 10.820.69.8+10.8
- CNMO 2024o1-mini by 1057.667.6+10
- MMLUClaude Opus 4 by 7.792.985.2+7.7
- MMLU-ReduxClaude Opus 4 by 7.594.286.7+7.5
- MMLU-ProClaude Opus 4 by 6.386.680.3+6.3
- MATH-500 (EM)Claude Opus 4 by 4.494.490+4.4
- HarmBenchClaude Opus 4 by 3.291.788.5+3.2
- simple_safety_testsClaude Opus 4 by 310097+3
- IFEvalClaude Opus 4 by 2.687.484.8+2.6
- anthropic_red_teamtie98.998.3tie
- bbqtie97.196.9tie
- XSTesttie9797tie
Questions people ask
Which is better, Claude Opus 4 or o1-mini?
Claude Opus 4 wins all two areas where both have results: coding and reasoning. o1-mini wins none.
Which is better for coding?
Claude Opus 4. It wins 2 of the 3 coding tests both models report; o1-mini wins none, and 1 is a tie.
How do you compare the two?
We use the 25 benchmark tests both models have published scores on. The verdict counts the 6 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 19 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.