Claude Opus 4.7 vs Gemini 2.5 Pro
Wins 7 of 8 areas
Coding · Agents · Reasoning · Images and charts · Math · Long documents · Following instructions
Wins 0 of 8 areas
—
Claude Opus 4.7 is the stronger all-rounder.Gemini 2.5 Pro is cheaper.
Scores updated · 36 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- CodingWriting and fixing software50Claude Opus 4.75 of 5 tests
- ReasoningHard problems that need careful thinking50Claude Opus 4.75 of 5 tests
- AgentsCarrying out multi-step tasks on its own30Claude Opus 4.73 of 3 tests
- MathCompetition and research-level math20Claude Opus 4.72 of 2 tests
- Images and chartsUnderstanding pictures, charts and video21Claude Opus 4.72 of 4 tests · 1 tie
- Long documentsFinding answers in very long texts10Claude Opus 4.71 of 1 test
- Following instructionsDoing exactly what it is asked10Claude Opus 4.71 of 1 test
- FactsGetting facts right instead of making them up22Even2 each
Long documents and following instructions 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 63% 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 Claude Opus 4.7 pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+70.9points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+69.4points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+54.6points ahead
Where Gemini 2.5 Pro pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+4.3points ahead
- Reads and reasons about text in imagesOCRBenchv2+2.4points 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.
CodingClaude Opus 4.7
- Terminal-Bench 2.1Claude Opus 4.7 by 54.683.128.5+54.6
- LMArena · WebDevClaude Opus 4.7 by 333 rating points15571224+333 rating
- Terminal-Bench HardClaude Opus 4.7 by 2551.526.5+25
- SWE-bench VerifiedClaude Opus 4.7 by 24.487.663.2+24.4
- SciCodeClaude Opus 4.7 by 8.254.546.3+8.2
AgentsClaude Opus 4.7
- BrowseCompClaude Opus 4.7 by 69.479.39.9+69.4
- GDPValClaude Opus 4.7 by 42.842.80+42.8
- τ-Bench V3 · BankingClaude Opus 4.7 by 24.934.69.7+24.9
ReasoningClaude Opus 4.7
- ARC-AGI-2Claude Opus 4.7 by 70.975.84.9+70.9
- Humanity's Last ExamClaude Opus 4.7 by 24.342.318+24.3
- SimpleBenchClaude Opus 4.7 by 10.161.751.6+10.1
- CritPtClaude Opus 4.7 by 9.4122.6+9.4
- GPQA DiamondClaude Opus 4.7 by 7.891.483.6+7.8
FactsEven
- AA-Omniscience · Non-hallucinationClaude Opus 4.7 by 48.657.79.1+48.6
- AA-Omniscience · AccuracyClaude Opus 4.7 by 9.848.939+9.8
- Vectara HHEM hallucination ratelower is betterGemini 2.5 Pro by 5127+5
- SimpleQA VerifiedGemini 2.5 Pro by 4.351.756+4.3
Images and chartsClaude Opus 4.7
- LMArena · VisionClaude Opus 4.7 by 50 rating points13131263+50 rating
- MMMU-ProClaude Opus 4.7 by 3.978.874.9+3.9
- OCRBenchv2Gemini 2.5 Pro by 2.456.959.3+2.4
- MathVistatie84.483.9tie
MathClaude Opus 4.7
- FrontierMath Tiers 1-3 (v2)Claude Opus 4.7 by 45.670.224.6+45.6
- FrontierMath Tier 4Claude Opus 4.7 by 31.731.70+31.7
Following instructionsClaude Opus 4.7
- IFBenchClaude Opus 4.7 by 9.958.648.7+9.9
Other results11 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.
- ARC-AGI-1Claude Opus 4.7 by 559237+55
- AA-OmniscienceClaude Opus 4.7 by 43.627.3-16.4+43.6
- AA Agentic IndexClaude Opus 4.7 by 3639.53.5+36
- τ²-Bench Telecom (AA run)Claude Opus 4.7 by 34.588.654.1+34.5
- Artificial Analysis Coding IndexClaude Opus 4.7 by 26.973.646.7+26.9
- HLE (with tools)Claude Opus 4.7 by 26.354.728.4+26.3
- AA IntelligenceClaude Opus 4.7 by 25.740.715+25.7
- frontiermath_tier_4_v1Claude Opus 4.7 by 18.722.94.2+18.7
- vectara_factual_consistencyGemini 2.5 Pro by 58893+5
- vectara_avg_summary_lengthClaude Opus 4.7 by 42.7 rating points149.1106.4+42.7 rating
- vectara_answer_rateGemini 2.5 Pro by 1.19899.1+1.1
Questions people ask
Which is better, Claude Opus 4.7 or Gemini 2.5 Pro?
Claude Opus 4.7 wins seven of the eight areas we test: coding, agents, reasoning, images and charts, math, long documents and following instructions. Gemini 2.5 Pro wins none, but costs 63% less. They are level on facts.
Which is better for coding?
Claude Opus 4.7. It wins 5 of the 5 coding tests both models report; Gemini 2.5 Pro wins none.
Which is cheaper?
Claude Opus 4.7 costs $5.00 per million input tokens and $25.00 per million output tokens; Gemini 2.5 Pro costs $1.25 and $10.00. That makes Gemini 2.5 Pro about 63% 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 25 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 11 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.