Claude 3.5 Sonnet vs Claude Opus 4
Wins 0 of 4 areas
—
Wins 4 of 4 areas
Coding · Reasoning · Images and charts · Long documents
Claude Opus 4 is the stronger all-rounder.Claude 3.5 Sonnet is cheaper.
Scores updated · 35 tests both models report · How we compare
Where each one wins
Tests won in each of the four 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.
Long documents 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.
Claude 3.5 Sonnet costs 80% 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 Claude Opus 4 pulls ahead
- Common-sense trick questionsSimpleBench+31.3points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+23.6points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+23.5points ahead
Where Claude 3.5 Sonnet pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 35 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4
- SWE-bench VerifiedClaude Opus 4 by 23.54972.5+23.5
- LiveCodeBench v6Claude Opus 4 by 10.237.247.4+10.2
- SciCodeClaude Opus 4 by 8.231.639.8+8.2
ReasoningClaude Opus 4
- SimpleBenchClaude Opus 4 by 31.327.558.8+31.3
- GPQA DiamondClaude Opus 4 by 23.65679.6+23.6
- Humanity's Last ExamClaude Opus 4 by 9.13.212.3+9.1
Images and chartsClaude Opus 4
- LMArena · VisionClaude Opus 4 by 72 rating points11201192+72 rating
- MMMUClaude Opus 4 by 5.468.373.7+5.4
Other results26 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 Opus 4 by 72.23.375.5+72.2
- HMMT Feb. 2025Claude Opus 4 by 58.31.760+58.3
- CNMO 2024Claude Opus 4 by 44.513.157.6+44.5
- LiveCodeBenchClaude Opus 4 by 37.632.870.4+37.6
- AIME 2024Claude Opus 4 by 32.21648.2+32.2
- Aider-PolyglotClaude Opus 4 by 25.445.370.7+25.4
- MATH-500 (EM)Claude Opus 4 by 16.178.394.4+16.1
- metr_re_benchClaude Opus 4 by 15520+15
- TAU-bench (airline)Claude Opus 4 by 13.64659.6+13.6
- AA IntelligenceClaude Opus 4 by 13.47.220.6+13.4
- TAU-bench (retail)Claude Opus 4 by 12.269.281.4+12.2
- MMLU-ProClaude Opus 4 by 977.686.6+9
- SuperGPQAClaude Opus 4 by 8.348.256.5+8.3
- Artificial Analysis Coding IndexClaude Opus 4 by 82634+8
- HarmBenchClaude 3.5 Sonnet by 6.498.191.7+6.4
- SimpleQAClaude 3.5 Sonnet by 5.628.422.8+5.6
- MMLU-ReduxClaude Opus 4 by 5.388.994.2+5.3
- frontiermath_tier_4_v1Claude Opus 4 by 4.204.2+4.2
- MMLUClaude Opus 4 by 4.288.792.9+4.2
- bbqClaude Opus 4 by 2.294.997.1+2.2
- XSTestClaude Opus 4 by 1.495.697+1.4
- metr_swaaClaude Opus 4 by 1.198.799.8+1.1
- anthropic_red_teamtie99.898.9tie
- IFEvaltie86.587.4tie
- AIR-Bench 2024tie85.985.7tie
- simple_safety_teststie100100tie
Questions people ask
Which is better, Claude 3.5 Sonnet or Claude Opus 4?
Claude Opus 4 wins all four areas where both have results: coding, reasoning, images and charts and long documents. Claude 3.5 Sonnet wins none, but costs 80% less.
Which is better for coding?
Claude Opus 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 Opus 4 costs $15.00 and $75.00. That makes Claude 3.5 Sonnet about 80% cheaper for the same work.
How do you compare the two?
We use the 35 benchmark tests both models have published scores on. The verdict counts the 9 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 26 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.