Claude 3.5 Sonnet vs DeepSeek-V2.5
Wins 3 of 3 areas
Coding · Reasoning · Long documents
Wins 0 of 3 areas
—
Claude 3.5 Sonnet is the stronger all-rounder.
Scores updated · 26 tests both models report · How we compare
Where each one wins
Tests won in each of the three 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, reasoning and long documents rest on a single test each.
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 3.5 Sonnet pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+32.2points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+13.7points ahead
- Questions about very long textsLongBench v2+5.6points ahead
Where DeepSeek-V2.5 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 26 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Long documentsClaude 3.5 Sonnet
- LongBench v2Claude 3.5 Sonnet by 5.64135.4+5.6
Other results23 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.
- CodeforcesClaude 3.5 Sonnet by 681.4 rating points71735.6+681.4 rating
- Aider-PolyglotClaude 3.5 Sonnet by 27.545.317.8+27.5
- SimpleQAClaude 3.5 Sonnet by 18.228.410.2+18.2
- Aider-Edit (Acc.)Claude 3.5 Sonnet by 12.684.271.6+12.6
- MMLU-ProClaude 3.5 Sonnet by 11.477.666.2+11.4
- LiveCodeBenchDeepSeek-V2.5 by 932.841.8+9
- BBHClaude 3.5 Sonnet by 8.893.184.3+8.8
- MMLU-ReduxClaude 3.5 Sonnet by 8.688.980.3+8.6
- MMLUClaude 3.5 Sonnet by 8.388.780.4+8.3
- HumanEval-Mul (Pass@1)Claude 3.5 Sonnet by 7.981.773.8+7.9
- FRAMES (Acc.)Claude 3.5 Sonnet by 7.172.565.4+7.1
- IFEvalClaude 3.5 Sonnet by 5.986.580.6+5.9
- CLUEWSCDeepSeek-V2.5 by 585.490.4+5
- HumanEvalClaude 3.5 Sonnet by 4.793.789+4.7
- MATHDeepSeek-V2.5 by 3.671.174.7+3.6
- MATH-500 (EM)Claude 3.5 Sonnet by 3.678.374.7+3.6
- Arena HardClaude 3.5 Sonnet by 379.276.2+3
- Chinese SimpleQA (C-SimpleQA)Claude 3.5 Sonnet by 1.355.454.1+1.3
- GSM8KClaude 3.5 Sonnet by 1.396.495.1+1.3
- AIME 2024tie1616.7tie
- AA Intelligencetie7.26.6tie
- DROP (3-shot F1)tie88.387.8tie
- MT-Benchtie8.89tie
Questions people ask
Which is better, Claude 3.5 Sonnet or DeepSeek-V2.5?
Claude 3.5 Sonnet wins all three areas where both have results: coding, reasoning and long documents. DeepSeek-V2.5 wins none.
Which is better for coding?
Claude 3.5 Sonnet. It wins the one coding test both models report.
How do you compare the two?
We use the 26 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 23 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.