Claude Sonnet 4 is the stronger all-rounder.
Scores updated · 11 tests both models report · How we compare
Where each one wins
Tests won in each of the two 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.
Reasoning and images and charts 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.
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
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+2.3points ahead
- College exam questions with charts, maps and diagramsMMMU+1.2points ahead
Where Grok 3 Beta pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 11 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Images and chartsClaude Sonnet 4
- MMMUClaude Sonnet 4 by 1.274.473.2+1.2
Other results9 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.
- HarmBenchClaude Sonnet 4 by 52.79845.3+52.7
- AIR-Bench 2024Claude Sonnet 4 by 3788.351.3+37
- SimpleQAGrok 3 Beta by 27.715.943.6+27.7
- Aider-PolyglotClaude Sonnet 4 by 17.470.753.3+17.4
- LiveCodeBenchClaude Sonnet 4 by 11.568.557+11.5
- MMLU-ProClaude Sonnet 4 by 3.883.779.9+3.8
- anthropic_red_teamClaude Sonnet 4 by 3.799.295.5+3.7
- simple_safety_testsClaude Sonnet 4 by 3.210096.8+3.2
- XSTesttie96.696.4tie
Questions people ask
Which is better, Claude Sonnet 4 or Grok 3 Beta?
Claude Sonnet 4 wins all two areas where both have results: reasoning and images and charts. Grok 3 Beta wins none.
Which is cheaper?
Claude Sonnet 4 costs $3.00 per million input tokens and $15.00 per million output tokens; Grok 3 Beta 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 11 benchmark tests both models have published scores on. The verdict counts the 2 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 9 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.