Claude 3.5 Sonnet vs Claude Sonnet 4
Wins 0 of 3 areas
—
Wins 3 of 3 areas
Coding · Reasoning · Images and charts
Claude Sonnet 4 is the stronger all-rounder.
Scores updated · 31 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.
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 Sonnet 4 pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+23.7points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+21.7points ahead
- Common-sense trick questionsSimpleBench+18points ahead
Where Claude 3.5 Sonnet pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 31 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4
- SWE-bench VerifiedClaude Sonnet 4 by 23.74972.7+23.7
- LiveCodeBench v6Claude Sonnet 4 by 11.337.248.5+11.3
- SciCodeClaude Sonnet 4 by 8.431.640+8.4
ReasoningClaude Sonnet 4
- GPQA DiamondClaude Sonnet 4 by 21.75677.7+21.7
- SimpleBenchClaude Sonnet 4 by 1827.545.5+18
- Humanity's Last ExamClaude Sonnet 4 by 7.53.210.7+7.5
Images and chartsClaude Sonnet 4
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.
- AIME 2025Claude Sonnet 4 by 67.23.370.5+67.2
- CNMO 2024Claude Sonnet 4 by 47.313.160.4+47.3
- LiveCodeBenchClaude Sonnet 4 by 35.732.868.5+35.7
- AIME 2024Claude Sonnet 4 by 27.41643.4+27.4
- Aider-PolyglotClaude Sonnet 4 by 25.445.370.7+25.4
- MATH-500 (EM)Claude Sonnet 4 by 15.778.394+15.7
- TAU-bench (airline)Claude Sonnet 4 by 144660+14
- SimpleQAClaude 3.5 Sonnet by 12.528.415.9+12.5
- AA IntelligenceClaude Sonnet 4 by 11.77.218.9+11.7
- Artificial Analysis Coding IndexClaude Sonnet 4 by 11.62637.6+11.6
- TAU-bench (retail)Claude Sonnet 4 by 11.369.280.5+11.3
- SuperGPQAClaude Sonnet 4 by 7.548.255.7+7.5
- MMLU-ProClaude Sonnet 4 by 6.177.683.7+6.1
- MMLU-ReduxClaude Sonnet 4 by 4.788.993.6+4.7
- MMLUClaude Sonnet 4 by 2.888.791.5+2.8
- AIR-Bench 2024Claude Sonnet 4 by 2.485.988.3+2.4
- bbqClaude Sonnet 4 by 1.794.996.6+1.7
- IFEvalClaude Sonnet 4 by 1.186.587.6+1.1
- XSTestClaude Sonnet 4 by 195.696.6+1
- anthropic_red_teamtie99.899.2tie
- HarmBenchtie98.198tie
- frontiermath_tier_4_v1tie00tie
- simple_safety_teststie100100tie
Questions people ask
Which is better, Claude 3.5 Sonnet or Claude Sonnet 4?
Claude Sonnet 4 wins all three areas where both have results: coding, reasoning and images and charts. Claude 3.5 Sonnet wins none.
Which is better for coding?
Claude Sonnet 4. It wins 3 of the 3 coding tests both models report; Claude 3.5 Sonnet wins none.
Which is cheaper?
Claude 3.5 Sonnet costs $3.00 per million input tokens and $15.00 per million output tokens; Claude Sonnet 4 costs $3.00 and $15.00. For a million tokens read plus a million written, they cost about the same.
How do you compare the two?
We use the 31 benchmark tests both models have published scores on. The verdict counts the 8 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.