Claude 3.5 Sonnet vs Gemini 2.5 Flash
Wins 0 of 3 areas
—
Wins 2 of 3 areas
Reasoning · Images and charts
Gemini 2.5 Flash is the stronger all-rounder.
Scores updated · 24 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.
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.
Gemini 2.5 Flash costs 84% 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 Gemini 2.5 Flash pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+23points ahead
- Harder college exam questions with imagesMMMU-Pro+14.4points ahead
- Common-sense trick questionsSimpleBench+13.7points ahead
Where Claude 3.5 Sonnet pulls ahead
- Code for real scientific research problemsSciCode+2.5points ahead
Every test, side by side
All 24 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingEven
- SWE-bench VerifiedGemini 2.5 Flash by 11.44960.4+11.4
- SciCodeClaude 3.5 Sonnet by 2.531.629.1+2.5
ReasoningGemini 2.5 Flash
- GPQA DiamondGemini 2.5 Flash by 235679+23
- SimpleBenchGemini 2.5 Flash by 13.727.541.2+13.7
- Humanity's Last ExamGemini 2.5 Flash by 8.93.212.1+8.9
Images and chartsGemini 2.5 Flash
- MMMU-ProGemini 2.5 Flash by 14.454.769.1+14.4
- LMArena · VisionGemini 2.5 Flash by 115 rating points11201235+115 rating
- MMMUGemini 2.5 Flash by 11.468.379.7+11.4
Other results16 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 2025Gemini 2.5 Flash by 68.73.372+68.7
- AIME 2024Gemini 2.5 Flash by 66.31682.3+66.3
- HMMT Feb. 2025Gemini 2.5 Flash by 62.51.764.2+62.5
- LiveCodeBenchGemini 2.5 Flash by 43.432.876.2+43.4
- HarmBenchClaude 3.5 Sonnet by 35.598.162.6+35.5
- LiveCodeBench (v5)Gemini 2.5 Flash by 2538.963.9+25
- AIR-Bench 2024Claude 3.5 Sonnet by 17.285.968.7+17.2
- Aider-PolyglotGemini 2.5 Flash by 16.645.361.9+16.6
- AA IntelligenceGemini 2.5 Flash by 5.97.213.1+5.9
- frontiermath_tier_4_v1Gemini 2.5 Flash by 4.204.2+4.2
- Artificial Analysis Coding IndexClaude 3.5 Sonnet by 3.82622.2+3.8
- XSTestGemini 2.5 Flash by 3.295.698.8+3.2
- bbqGemini 2.5 Flash by 2.894.997.7+2.8
- simple_safety_testsClaude 3.5 Sonnet by 210098+2
- SimpleQAClaude 3.5 Sonnet by 1.528.426.9+1.5
- anthropic_red_teamClaude 3.5 Sonnet by 199.898.8+1
Questions people ask
Which is better, Claude 3.5 Sonnet or Gemini 2.5 Flash?
Gemini 2.5 Flash wins two of the three areas where both have results: reasoning and images and charts. Claude 3.5 Sonnet wins none. They are level on coding.
Which is better for coding?
Neither. They win 1 coding test each of the 2 both models report.
Which is cheaper?
Claude 3.5 Sonnet costs $3.00 per million input tokens and $15.00 per million output tokens; Gemini 2.5 Flash costs $0.30 and $2.50. That makes Gemini 2.5 Flash about 84% cheaper for the same work.
How do you compare the two?
We use the 24 benchmark tests both models have published scores on. The verdict counts the 8 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 16 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.