DeepSeek-V3 is the stronger all-rounder.
Scores updated · 23 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 rests on a single test.
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 DeepSeek-V3 pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+25.5points ahead
- Code for real scientific research problemsSciCode+16.1points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.1points ahead
Where Claude 3 Sonnet pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 23 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningDeepSeek-V3
- GPQA DiamondDeepSeek-V3 by 25.54065.5+25.5
- Humanity's Last ExamDeepSeek-V3 by 1.13.64.7+1.1
Other results20 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.
- NarrativeQADeepSeek-V3 by 68.511.179.6+68.5
- MATHDeepSeek-V3 by 47.143.190.2+47.1
- HarmBenchClaude 3 Sonnet by 46.195.849.7+46.1
- AIR-Bench 2024Claude 3 Sonnet by 43.984.740.8+43.9
- naturalquestions_closedbookDeepSeek-V3 by 43.92.846.7+43.9
- MMLU-ProDeepSeek-V3 by 19.156.875.9+19.1
- DROPDeepSeek-V3 by 12.778.991.6+12.7
- XSTestDeepSeek-V3 by 11.385.897.1+11.3
- MMLUDeepSeek-V3 by 10.278.388.5+10.2
- HumanEvalClaude 3 Sonnet by 7.87365.2+7.8
- bbqDeepSeek-V3 by 6.79096.7+6.7
- simple_safety_testsClaude 3 Sonnet by 4.710095.3+4.7
- BBHDeepSeek-V3 by 4.682.987.5+4.6
- AA IntelligenceDeepSeek-V3 by 3.85.99.7+3.8
- MGSMClaude 3 Sonnet by 3.783.579.8+3.7
- OpenBookQADeepSeek-V3 by 3.691.895.4+3.6
- anthropic_red_teamClaude 3 Sonnet by 2.799.897.1+2.7
- ARC-ChallengeDeepSeek-V3 by 2.193.295.3+2.1
- GSM8KDeepSeek-V3 by 1.792.394+1.7
- HellaSwagtie8988.9tie
Questions people ask
Which is better, Claude 3 Sonnet or DeepSeek-V3?
DeepSeek-V3 wins all two areas where both have results: coding and reasoning. Claude 3 Sonnet wins none.
Which is better for coding?
DeepSeek-V3. It wins the one coding test both models report.
How do you compare the two?
We use the 23 benchmark tests both models have published scores on. The verdict counts the 3 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 20 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.