Claude Opus 4 is the stronger all-rounder.
Scores updated · 15 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.
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 Opus 4 pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+59points ahead
- Common-sense trick questionsSimpleBench+28.1points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+5.4points ahead
Where Gemini 2.0 Flash (Reasoning) pulls ahead
- College exam questions with charts, maps and diagramsMMMU+1.7points ahead
Every test, side by side
All 15 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningClaude Opus 4
- SimpleBenchClaude Opus 4 by 28.158.830.7+28.1
- GPQA DiamondClaude Opus 4 by 5.479.674.2+5.4
Images and chartsEven
- LMArena · VisionClaude Opus 4 by 34 rating points11921158+34 rating
- MMMUGemini 2.0 Flash (Reasoning) by 1.773.775.4+1.7
Other results10 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 4875.527.5+48
- HMMT Feb. 2025Claude Opus 4 by 46.76013.3+46.7
- LiveCodeBenchClaude Opus 4 by 35.370.435.1+35.3
- HarmBenchClaude Opus 4 by 25.591.766.2+25.5
- AIR-Bench 2024Claude Opus 4 by 19.585.766.2+19.5
- MMLU-ProClaude Opus 4 by 10.286.676.4+10.2
- bbqClaude Opus 4 by 1.797.195.4+1.7
- XSTestClaude Opus 4 by 1.79795.3+1.7
- simple_safety_testsClaude Opus 4 by 1.510098.5+1.5
- anthropic_red_teamtie98.999.4tie
Questions people ask
Which is better, Claude Opus 4 or Gemini 2.0 Flash (Reasoning)?
Claude Opus 4 wins two of the three areas where both have results: coding and reasoning. Gemini 2.0 Flash (Reasoning) wins none. They are level on images and charts.
Which is better for coding?
Claude Opus 4. It wins the one coding test both models report.
How do you compare the two?
We use the 15 benchmark tests both models have published scores on. The verdict counts the 5 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 10 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.