The two are evenly matched.Claude Sonnet 4 is better at facts; o3-pro at following instructions.
Scores updated · 10 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.
Facts and following instructions 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.
Claude Sonnet 4 costs 82% 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 Sonnet 4 pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+1points ahead
Where o3-pro pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+6.8points ahead
- Keeps track of context across a multi-turn chatMulti-Challenge+5.3points ahead
Every test, side by side
All 10 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningEven
- GPQA Diamondo3-pro by 6.877.784.5+6.8
- ARC-AGI-2Claude Sonnet 4 by 15.94.9+1
FactsClaude Sonnet 4
- Vectara HHEM hallucination ratelower is betterClaude Sonnet 4 by 1310.323.3+13
Following instructionso3-pro
- Multi-Challengeo3-pro by 5.357.162.4+5.3
Other results6 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.
- ARC-AGI-1o3-pro by 19.34059.3+19.3
- Aider-Polygloto3-pro by 14.270.784.9+14.2
- vectara_factual_consistencyClaude Sonnet 4 by 1389.776.7+13
- AA Intelligenceo3-pro by 318.921.9+3
- vectara_avg_summary_lengthClaude Sonnet 4 by 18.4 rating points145.8127.4+18.4 rating
- vectara_answer_rateo3-pro by 1.498.6100+1.4
Questions people ask
Which is better, Claude Sonnet 4 or o3-pro?
Claude Sonnet 4 and o3-pro each win one of the three areas where both have results. Claude Sonnet 4 wins facts; o3-pro wins following instructions. Claude Sonnet 4 costs 82% less. They are level on reasoning.
Which is cheaper?
Claude Sonnet 4 costs $3.00 per million input tokens and $15.00 per million output tokens; o3-pro costs $20.00 and $80.00. That makes Claude Sonnet 4 about 82% cheaper for the same work.
How do you compare the two?
We use the 10 benchmark tests both models have published scores on. The verdict counts the 4 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 6 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.