Claude 3 Opus wins more areas, narrowly.
Scores updated · 16 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.
Coding 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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Claude 3 Opus pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+16.5points ahead
- Code for real scientific research problemsSciCode+5.2points ahead
Where Gemini 1.5 Flash (001) pulls ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.6points ahead
Every test, side by side
All 16 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningEven
- GPQA DiamondClaude 3 Opus by 16.548.932.4+16.5
- Humanity's Last ExamGemini 1.5 Flash (001) by 1.62.84.4+1.6
Other results13 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.
- GSM8KClaude 3 Opus by 62.29532.8+62.2
- NarrativeQAGemini 1.5 Flash (001) by 39.535.174.6+39.5
- MATHGemini 1.5 Flash (001) by 30.760.190.8+30.7
- MMLUClaude 3 Opus by 18.986.867.9+18.9
- HarmBenchClaude 3 Opus by 17.497.480+17.4
- AIR-Bench 2024Claude 3 Opus by 17.384.467.1+17.3
- naturalquestions_closedbookClaude 3 Opus by 11.84432.3+11.8
- OpenBookQAClaude 3 Opus by 4.295.691.4+4.2
- simple_safety_testsClaude 3 Opus by 310097+3
- AA IntelligenceClaude 3 Opus by 2.88.75.9+2.8
- bbqtie9494.7tie
- XSTesttie92.592.1tie
- anthropic_red_teamtie99.899.9tie
Questions people ask
Which is better, Claude 3 Opus or Gemini 1.5 Flash (001)?
Claude 3 Opus wins one of the two areas where both have results: coding. Gemini 1.5 Flash (001) wins none. They are level on reasoning.
Which is better for coding?
Claude 3 Opus. It wins the one coding test both models report.
How do you compare the two?
We use the 16 benchmark tests both models have published scores on. The verdict counts the 3 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 13 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.