Claude 3.5 Sonnet vs Claude 3.7 Sonnet
Wins 0 of 3 areas
—
Wins 3 of 3 areas
Coding · Reasoning · Images and charts
Claude 3.7 Sonnet is the stronger all-rounder.
Scores updated · 30 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 3.7 Sonnet pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+21.3points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+21.2points ahead
- Common-sense trick questionsSimpleBench+18.9points ahead
Where Claude 3.5 Sonnet pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 30 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude 3.7 Sonnet
- SWE-bench VerifiedClaude 3.7 Sonnet by 21.34970.3+21.3
- SciCodeClaude 3.7 Sonnet by 8.731.640.3+8.7
ReasoningClaude 3.7 Sonnet
- GPQA DiamondClaude 3.7 Sonnet by 21.25677.2+21.2
- SimpleBenchClaude 3.7 Sonnet by 18.927.546.4+18.9
- Humanity's Last ExamClaude 3.7 Sonnet by 6.53.29.7+6.5
Images and chartsClaude 3.7 Sonnet
- MMMUClaude 3.7 Sonnet by 6.768.375+6.7
- MMMU-ProClaude 3.7 Sonnet by 5.454.760.1+5.4
- LMArena · VisionClaude 3.7 Sonnet by 49 rating points11201169+49 rating
Other results22 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 3.7 Sonnet by 51.53.354.8+51.5
- HMMT Feb. 2025Claude 3.7 Sonnet by 301.731.7+30
- MATH-500 (EM)Claude 3.7 Sonnet by 17.978.396.2+17.9
- Aider-PolyglotClaude 3.7 Sonnet by 15.145.360.4+15.1
- HarmBenchClaude 3.5 Sonnet by 13.898.184.3+13.8
- metr_hcastClaude 3.7 Sonnet by 13.540.754.2+13.5
- TAU-bench (airline)Claude 3.7 Sonnet by 12.44658.4+12.4
- TAU-bench (retail)Claude 3.7 Sonnet by 1269.281.2+12
- AA IntelligenceClaude 3.7 Sonnet by 10.57.217.7+10.5
- Artificial Analysis Coding IndexClaude 3.7 Sonnet by 10.42636.4+10.4
- BBQ Disambig Accuracy (%)Claude 3.7 Sonnet by 7.876.284+7.8
- IFEvalClaude 3.7 Sonnet by 6.786.593.2+6.7
- BBQ Ambig Accuracy (%)Claude 3.7 Sonnet by 5.293.698.8+5.2
- metr_re_benchClaude 3.5 Sonnet by 550+5
- AIR-Bench 2024Claude 3.5 Sonnet by 4.185.981.8+4.1
- bbqClaude 3.5 Sonnet by 2.894.992.1+2.8
- BBQ Disambig Bias (%)Claude 3.7 Sonnet by 2.7-3.7-1+2.7
- XSTesttie95.696.4tie
- anthropic_red_teamtie99.899.7tie
- BBQ Ambig Bias (%)tie0.90.9tie
- metr_swaatie98.798.7tie
- simple_safety_teststie100100tie
Questions people ask
Which is better, Claude 3.5 Sonnet or Claude 3.7 Sonnet?
Claude 3.7 Sonnet 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 3.7 Sonnet. It wins 2 of the 2 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 3.7 Sonnet 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 30 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 22 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.