Claude 3.7 Sonnet vs Gemini 2.5 Pro
Wins 1 of 7 areas
Agents
Wins 5 of 7 areas
Coding · Reasoning · Images and charts · Long documents · Following instructions
Gemini 2.5 Pro is the stronger all-rounder.Claude 3.7 Sonnet is better at agents.
Scores updated · 36 tests both models report · How we compare
Where each one wins
Tests won in each of the seven 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.
- ReasoningHard problems that need careful thinking04Gemini 2.5 Pro4 of 4 tests
- Images and chartsUnderstanding pictures, charts and video03Gemini 2.5 Pro3 of 3 tests
- CodingWriting and fixing software12Gemini 2.5 Pro2 of 3 tests
- Following instructionsDoing exactly what it is asked01Gemini 2.5 Pro1 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts01Gemini 2.5 Pro1 of 1 test
- AgentsCarrying out multi-step tasks on its own10Claude 3.7 Sonnet1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Agents and long documents 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.
Gemini 2.5 Pro costs 38% 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 Pro pulls ahead
- Reasons across sets of long documentsAA-LCR+17.3points ahead
- Harder college exam questions with imagesMMMU-Pro+14.8points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+11.1points ahead
Where Claude 3.7 Sonnet pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+50.9points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+7.1points ahead
Every test, side by side
All 36 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 2.5 Pro
- SWE-bench VerifiedClaude 3.7 Sonnet by 7.170.363.2+7.1
- SciCodeGemini 2.5 Pro by 640.346.3+6
- Terminal-Bench HardGemini 2.5 Pro by 5.321.226.5+5.3
ReasoningGemini 2.5 Pro
- Humanity's Last ExamGemini 2.5 Pro by 8.39.718+8.3
- GPQA DiamondGemini 2.5 Pro by 6.477.283.6+6.4
- SimpleBenchGemini 2.5 Pro by 5.246.451.6+5.2
- CritPtGemini 2.5 Pro by 1.70.92.6+1.7
FactsEven
- AA-Omniscience · Non-hallucinationClaude 3.7 Sonnet by 50.9609.1+50.9
- AA-Omniscience · AccuracyGemini 2.5 Pro by 11.12839+11.1
Images and chartsGemini 2.5 Pro
- MMMU-ProGemini 2.5 Pro by 14.860.174.9+14.8
- LMArena · VisionGemini 2.5 Pro by 94 rating points11691263+94 rating
- MMMUGemini 2.5 Pro by 4.67579.6+4.6
Following instructionsGemini 2.5 Pro
- Multi-ChallengeGemini 2.5 Pro by 251.653.6+2
- IFBenchtie48.348.7tie
Other results20 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.
- HMMT Feb. 2025Gemini 2.5 Pro by 49.131.780.8+49.1
- AA Agentic IndexClaude 3.7 Sonnet by 33.5373.5+33.5
- AIME 2025Gemini 2.5 Pro by 28.254.883+28.2
- usamo_2025Gemini 2.5 Pro by 20.73.624.4+20.7
- HarmBenchClaude 3.7 Sonnet by 18.984.365.4+18.9
- Aider-PolyglotGemini 2.5 Pro by 16.160.476.5+16.1
- AA-OmniscienceClaude 3.7 Sonnet by 15.6-0.7-16.4+15.6
- TAU-bench (retail)Claude 3.7 Sonnet by 14.281.267+14.2
- Artificial Analysis Coding IndexGemini 2.5 Pro by 10.336.446.7+10.3
- Terminal-BenchClaude 3.7 Sonnet by 9.935.225.3+9.9
- ARC-AGI-1Gemini 2.5 Pro by 8.428.637+8.4
- TAU-bench (airline)Claude 3.7 Sonnet by 8.458.450+8.4
- AIR-Bench 2024Claude 3.7 Sonnet by 8.281.873.6+8.2
- bbqGemini 2.5 Pro by 4.392.196.4+4.3
- simple_safety_testsClaude 3.7 Sonnet by 310097+3
- AA IntelligenceClaude 3.7 Sonnet by 2.717.715+2.7
- MATH-500 (EM)Gemini 2.5 Pro by 2.696.298.8+2.6
- XSTestGemini 2.5 Pro by 2.396.498.7+2.3
- τ²-Bench Telecom (AA run)tie54.754.1tie
- anthropic_red_teamtie99.799.5tie
Questions people ask
Which is better, Claude 3.7 Sonnet or Gemini 2.5 Pro?
Gemini 2.5 Pro wins five of the seven areas where both have results: coding, reasoning, images and charts, long documents and following instructions. Claude 3.7 Sonnet wins agents. They are level on facts.
Which is better for coding?
Gemini 2.5 Pro. It wins 2 of the 3 coding tests both models report; Claude 3.7 Sonnet wins 1.
Which is cheaper?
Claude 3.7 Sonnet costs $3.00 per million input tokens and $15.00 per million output tokens; Gemini 2.5 Pro costs $1.25 and $10.00. That makes Gemini 2.5 Pro about 38% cheaper for the same work.
How do you compare the two?
We use the 36 benchmark tests both models have published scores on. The verdict counts the 16 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 20 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.