Claude 3.5 Sonnet vs o3
Wins 0 of 4 areas
—
Wins 4 of 4 areas
Coding · Reasoning · Images and charts · Long documents
o3 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 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.
o3 costs 44% 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 o3 pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+26.7points ahead
- Common-sense trick questionsSimpleBench+25.6points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+20.1points 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.
Reasoningo3
- GPQA Diamondo3 by 26.75682.7+26.7
- SimpleBencho3 by 25.627.553.1+25.6
- Humanity's Last Examo3 by 16.93.220.1+16.9
Images and chartso3
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.
- AIME 2025o3 by 83.13.386.4+83.1
- HMMT Feb. 2025o3 by 75.81.777.5+75.8
- AIME 2024o3 by 75.61691.6+75.6
- LiveCodeBencho3 by 51.932.884.7+51.9
- Aider-Polygloto3 by 3645.381.3+36
- metr_hcasto3 by 2440.764.7+24
- SimpleQAo3 by 2128.449.4+21
- MATH-500 (EM)o3 by 19.878.398.1+19.8
- AA Intelligenceo3 by 137.220.2+13
- Artificial Analysis Coding Indexo3 by 12.42638.4+12.4
- metr_re_bencho3 by 10515+10
- MMLU-Proo3 by 7.477.685+7.4
- TAU-bench (airline)o3 by 64652+6
- TAU-bench (retail)o3 by 4.769.273.9+4.7
- bbqo3 by 394.997.9+3
- frontiermath_tier_4_v1o3 by 2.102.1+2.1
- XSTesto3 by 1.795.697.3+1.7
- anthropic_red_teamClaude 3.5 Sonnet by 1.599.898.3+1.5
- AIR-Bench 2024Claude 3.5 Sonnet by 1.485.984.5+1.4
- simple_safety_testsClaude 3.5 Sonnet by 110099+1
- HarmBenchtie98.198.4tie
Questions people ask
Which is better, Claude 3.5 Sonnet or o3?
o3 wins all four areas where both have results: coding, reasoning, images and charts and long documents. Claude 3.5 Sonnet wins none.
Which is better for coding?
o3. 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; o3 costs $2.00 and $8.00. That makes o3 about 44% cheaper for the same work.
How do you compare the two?
We use the 30 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 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.