Claude Opus 4.7 vs Gemini 3 Pro
Wins 4 of 8 areas
Coding · Agents · Reasoning · Math
Wins 2 of 8 areas
Images and charts · Following instructions
Claude Opus 4.7 wins more areas, narrowly.Gemini 3 Pro is cheaper and better at images and charts.
Both rank among the ten best models we track in images and charts.
Scores updated · 48 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 software51Claude Opus 4.75 of 6 tests
- AgentsCarrying out multi-step tasks on its own40Claude Opus 4.74 of 4 tests
- ReasoningHard problems that need careful thinking31Claude Opus 4.73 of 5 tests · 1 tie
- MathCompetition and research-level math20Claude Opus 4.72 of 2 tests
- Images and chartsUnderstanding pictures, charts and video13Gemini 3 Pro3 of 5 tests · 1 tie
- Following instructionsDoing exactly what it is asked01Gemini 3 Pro1 of 1 test
- FactsGetting facts right instead of making them up22Even2 each
- Long documentsFinding answers in very long texts11Even1 each
Following instructions 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.
Gemini 3 Pro costs 53% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Claude Opus 4.7 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+49.2points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+44.7points ahead
- Multi-step tasks using many real software toolsMCP Atlas+23.2points ahead
Where Gemini 3 Pro pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+21.2points ahead
- Finds one of eight look-alike replies in a long chatMRCR v2 8 needle 128k (average)+17.7points ahead
- Common-sense trick questionsSimpleBench+14.7points ahead
Every test, side by side
All 48 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4.7
- SWE-bench ProClaude Opus 4.7 by 2164.343.3+21
- SWE-bench MultilingualClaude Opus 4.7 by 15.580.565+15.5
- LMArena · WebDevClaude Opus 4.7 by 118 rating points15581440+118 rating
- SWE-bench VerifiedClaude Opus 4.7 by 11.487.676.2+11.4
- Terminal-Bench HardClaude Opus 4.7 by 9.851.541.7+9.8
- SciCodeGemini 3 Pro by 1.654.556.1+1.6
AgentsClaude Opus 4.7
- MCP AtlasClaude Opus 4.7 by 23.277.354.1+23.2
- BrowseCompClaude Opus 4.7 by 20.179.359.2+20.1
- AA ApexAgentsClaude Opus 4.7 by 15.533.918.4+15.5
- GDPValClaude Opus 4.7 by 8.642.834.2+8.6
ReasoningClaude Opus 4.7
- ARC-AGI-2Claude Opus 4.7 by 44.775.831.1+44.7
- SimpleBenchGemini 3 Pro by 14.761.776.4+14.7
- CritPtClaude Opus 4.7 by 2.9129.1+2.9
- Humanity's Last ExamClaude Opus 4.7 by 2.642.339.7+2.6
- GPQA Diamondtie91.490.8tie
FactsEven
- AA-Omniscience · Non-hallucinationClaude Opus 4.7 by 49.257.78.5+49.2
- SimpleQA VerifiedGemini 3 Pro by 21.251.772.9+21.2
- AA-Omniscience · AccuracyGemini 3 Pro by 6.948.955.8+6.9
- Vectara HHEM hallucination ratelower is betterClaude Opus 4.7 by 1.61213.6+1.6
Images and chartsGemini 3 Pro
- CharXiv (RQ)Claude Opus 4.7 by 9.69181.4+9.6
- OCRBenchv2Gemini 3 Pro by 6.556.963.4+6.5
- MathVistaGemini 3 Pro by 5.484.489.8+5.4
- MMMU-ProGemini 3 Pro by 1.478.880.2+1.4
- LMArena · Visiontie13131305tie
MathClaude Opus 4.7
- HMMT Feb. 2026Claude Opus 4.7 by 7.593.986.4+7.5
- AIME 2026Claude Opus 4.7 by 4.195.891.7+4.1
Long documentsEven
- MRCR v2 8 needle 128k (average)Gemini 3 Pro by 17.759.377+17.7
- AA-LCRClaude Opus 4.7 by 2.778.776+2.7
Following instructionsGemini 3 Pro
- IFBenchGemini 3 Pro by 11.858.670.4+11.8
Other results19 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.
- GDPval-AA (Elo)Claude Opus 4.7 by 558 rating points17531195+558 rating
- Artificial Analysis Coding IndexClaude Opus 4.7 by 27.173.646.5+27.1
- ToolathlonClaude Opus 4.7 by 22.959.336.4+22.9
- ARC-AGI-1Claude Opus 4.7 by 179275+17
- Terminal-Bench 2.0Claude Opus 4.7 by 15.269.454.2+15.2
- SimpleVQAGemini 3 Pro by 13.256.569.7+13.2
- AA IntelligenceClaude Opus 4.7 by 12.740.728+12.7
- AA Agentic IndexGemini 3 Pro by 12.539.552+12.5
- AA-OmniscienceClaude Opus 4.7 by 1227.315.3+12
- WorldVQAGemini 3 Pro by 11.535.947.4+11.5
- HLE (with tools)Claude Opus 4.7 by 8.954.745.8+8.9
- ScreenSpot-Pro (No tools)Claude Opus 4.7 by 6.879.572.7+6.8
- vectara_avg_summary_lengthClaude Opus 4.7 by 47.2 rating points149.1101.9+47.2 rating
- frontiermath_tier_4_v1Claude Opus 4.7 by 4.122.918.8+4.1
- LiveBenchClaude Opus 4.7 by 3.576.973.4+3.5
- vectara_factual_consistencyClaude Opus 4.7 by 1.68886.4+1.6
- τ²-Bench Telecom (AA run)Claude Opus 4.7 by 1.588.687.1+1.5
- vectara_answer_rateGemini 3 Pro by 1.49899.4+1.4
- MMMLUtie91.591.8tie
Questions people ask
Which is better, Claude Opus 4.7 or Gemini 3 Pro?
Claude Opus 4.7 wins four of the eight areas we test: coding, agents, reasoning and math. Gemini 3 Pro wins images and charts and following instructions, and costs 53% less. They are level on facts and long documents.
Which is better for coding?
Claude Opus 4.7. It wins 5 of the 6 coding tests both models report; Gemini 3 Pro wins 1.
Which is cheaper?
Claude Opus 4.7 costs $5.00 per million input tokens and $25.00 per million output tokens; Gemini 3 Pro costs $2.00 and $12.00. That makes Gemini 3 Pro about 53% cheaper for the same work.
How do you compare the two?
We use the 48 benchmark tests both models have published scores on. The verdict counts the 29 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 19 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.