DeepSeek-V3 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.
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.
DeepSeek-V3 costs 99% less for the same work.
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+16.6points ahead
- Code for real scientific research problemsSciCode+15.7points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.9points ahead
Where Claude 3 Opus pulls ahead
- Common-sense trick questionsSimpleBench+4.6points ahead
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.
ReasoningDeepSeek-V3
- GPQA DiamondDeepSeek-V3 by 16.648.965.5+16.6
- SimpleBenchClaude 3 Opus by 4.623.518.9+4.6
- Humanity's Last ExamDeepSeek-V3 by 1.92.84.7+1.9
Other results21 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.
- HarmBenchClaude 3 Opus by 47.797.449.7+47.7
- NarrativeQADeepSeek-V3 by 44.535.179.6+44.5
- AIR-Bench 2024Claude 3 Opus by 43.684.440.8+43.6
- MATHDeepSeek-V3 by 30.160.190.2+30.1
- HumanEvalClaude 3 Opus by 19.784.965.2+19.7
- MGSMClaude 3 Opus by 10.990.779.8+10.9
- DROPDeepSeek-V3 by 8.583.191.6+8.5
- MMLU-ProDeepSeek-V3 by 7.468.575.9+7.4
- HellaSwagClaude 3 Opus by 6.595.488.9+6.5
- simple_safety_testsClaude 3 Opus by 4.710095.3+4.7
- XSTestDeepSeek-V3 by 4.692.597.1+4.6
- Artificial Analysis Coding IndexDeepSeek-V3 by 3.519.523+3.5
- anthropic_red_teamClaude 3 Opus by 2.799.897.1+2.7
- bbqDeepSeek-V3 by 2.79496.7+2.7
- naturalquestions_closedbookDeepSeek-V3 by 2.64446.7+2.6
- MMLUDeepSeek-V3 by 1.786.888.5+1.7
- ARC-ChallengeClaude 3 Opus by 1.196.495.3+1.1
- AA IntelligenceDeepSeek-V3 by 18.79.7+1
- GSM8KClaude 3 Opus by 19594+1
- BBHtie86.887.5tie
- OpenBookQAtie95.695.4tie
Questions people ask
Which is better, Claude 3 Opus or DeepSeek-V3?
DeepSeek-V3 wins all two areas where both have results: coding and reasoning. Claude 3 Opus wins none.
Which is better for coding?
DeepSeek-V3. It wins the one coding test both models report.
Which is cheaper?
Claude 3 Opus costs $15.00 per million input tokens and $75.00 per million output tokens; DeepSeek-V3 costs $0.24 and $0.90. That makes DeepSeek-V3 about 99% cheaper for the same work.
How do you compare the two?
We use the 25 benchmark tests both models have published scores on. The verdict counts the 4 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 21 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.