Claude Opus 4.6 vs Gemini 3 Pro
Wins 4 of 8 areas
Coding · Agents · Math · Long documents
Wins 2 of 8 areas
Images and charts · Following instructions
Claude Opus 4.6 wins more areas, narrowly.Gemini 3 Pro is cheaper and better at images and charts.
Scores updated · 62 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 software61Claude Opus 4.66 of 7 tests
- AgentsCarrying out multi-step tasks on its own40Claude Opus 4.64 of 4 tests
- Long documentsFinding answers in very long texts20Claude Opus 4.62 of 2 tests
- MathCompetition and research-level math21Claude Opus 4.62 of 3 tests
- Images and chartsUnderstanding pictures, charts and video13Gemini 3 Pro3 of 4 tests
- Following instructionsDoing exactly what it is asked02Gemini 3 Pro2 of 2 tests
- ReasoningHard problems that need careful thinking22Even2 each · 1 tie
- FactsGetting facts right instead of making them up22Even2 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 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 4.6 pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+37.7points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+28.7points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+24.8points ahead
Where Gemini 3 Pro pulls ahead
- Keeps track of context across a multi-turn chatMulti-Challenge+28.5points ahead
- Short factual questions, answered correctlySimpleQA Verified+25.9points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+17.3points ahead
Every test, side by side
All 62 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4.6
- SWE-bench MultilingualClaude Opus 4.6 by 12.877.865+12.8
- LMArena · WebDevClaude Opus 4.6 by 106 rating points15461440+106 rating
- SWE-bench ProClaude Opus 4.6 by 10.153.443.3+10.1
- SWE-bench VerifiedClaude Opus 4.6 by 4.680.876.2+4.6
- Terminal-Bench HardClaude Opus 4.6 by 4.546.241.7+4.5
- SciCodeGemini 3 Pro by 4.251.956.1+4.2
- LiveCodeBench v6Claude Opus 4.6 by 1.488.887.4+1.4
AgentsClaude Opus 4.6
- BrowseCompClaude Opus 4.6 by 24.88459.2+24.8
- GDPValClaude Opus 4.6 by 21.755.934.2+21.7
- AA ApexAgentsClaude Opus 4.6 by 14.63318.4+14.6
- MCP AtlasClaude Opus 4.6 by 8.662.754.1+8.6
ReasoningEven
- ARC-AGI-2Claude Opus 4.6 by 37.768.831.1+37.7
- SimpleBenchGemini 3 Pro by 8.867.676.4+8.8
- CritPtClaude Opus 4.6 by 3.512.69.1+3.5
- GPQA DiamondGemini 3 Pro by 1.289.690.8+1.2
- Humanity's Last Examtie39.939.7tie
FactsEven
- AA-Omniscience · Non-hallucinationClaude Opus 4.6 by 28.737.28.5+28.7
- SimpleQA VerifiedGemini 3 Pro by 25.94772.9+25.9
- AA-Omniscience · AccuracyGemini 3 Pro by 8.84755.8+8.8
- Vectara HHEM hallucination ratelower is betterClaude Opus 4.6 by 1.412.213.6+1.4
Images and chartsGemini 3 Pro
- OCRBenchv2Gemini 3 Pro by 1548.463.4+15
- MMMU-ProGemini 3 Pro by 4.875.480.2+4.8
- CharXiv (RQ)Gemini 3 Pro by 477.481.4+4
- LMArena · VisionClaude Opus 4.6 by 11 rating points13161305+11 rating
MathClaude Opus 4.6
- HMMT Feb. 2026Claude Opus 4.6 by 9.896.286.4+9.8
- IMOAnswerBenchGemini 3 Pro by 7.875.383.1+7.8
- AIME 2026Claude Opus 4.6 by 596.791.7+5
Long documentsClaude Opus 4.6
- MRCR v2 8 needle 128k (average)Claude Opus 4.6 by 78477+7
- AA-LCRClaude Opus 4.6 by 27876+2
Following instructionsGemini 3 Pro
- Multi-ChallengeGemini 3 Pro by 28.537.165.7+28.5
- IFBenchGemini 3 Pro by 17.353.170.4+17.3
Other results31 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.
- Vending-Bench 2Claude Opus 4.6 by 253943 rating points801759547816+253943 rating
- GDPval-AA (Elo)Claude Opus 4.6 by 424 rating points16191195+424 rating
- DeepSearchQA (F1)Claude Opus 4.6 by 28.191.363.2+28.1
- browsecomp_with_context_managerClaude Opus 4.6 by 24.88459.2+24.8
- MATH-VisionGemini 3 Pro by 20.665.586.1+20.6
- ToolathlonClaude Opus 4.6 by 20.456.836.4+20.4
- ARC-AGI-1Claude Opus 4.6 by 189375+18
- AA Agentic IndexClaude Opus 4.6 by 15.667.652+15.6
- ScreenSpot-Pro (No tools)Gemini 3 Pro by 1557.772.7+15
- matharena_visual_math_overallGemini 3 Pro by 11.972.384.2+11.9
- Terminal-Bench 2.0Claude Opus 4.6 by 11.265.454.2+11.2
- LVBenchGemini 3 Pro by 10.56373.5+10.5
- HLE (with tools)Claude Opus 4.6 by 7.553.345.8+7.5
- τ²-Bench (Retail)Claude Opus 4.6 by 6.691.985.3+6.6
- τ²-Bench Telecom (AA run)Claude Opus 4.6 by 592.187.1+5
- frontiermath_tier_4_v1Claude Opus 4.6 by 4.122.918.8+4.1
- OCRBench v2 (Chinese)Gemini 3 Pro by 459.863.8+4
- AA IntelligenceClaude Opus 4.6 by 3.931.928+3.9
- vectara_avg_summary_lengthClaude Opus 4.6 by 35.7 rating points137.6101.9+35.7 rating
- LiveCodeBenchGemini 3 Pro by 3.288.892+3.2
- HMMT Nov. 2025Claude Opus 4.6 by 396.393.3+3
- LiveBenchClaude Opus 4.6 by 2.976.373.4+2.9
- AA-OmniscienceGemini 3 Pro by 1.613.715.3+1.6
- Artificial Analysis Coding IndexClaude Opus 4.6 by 1.648.146.5+1.6
- vectara_factual_consistencyClaude Opus 4.6 by 1.487.886.4+1.4
- metr_swaaGemini 3 Pro by 198.599.5+1
- MMLU-ProGemini 3 Pro by 189.190.1+1
- MMMLUtie91.191.8tie
- AIME25 no toolstie95.696tie
- vectara_answer_ratetie99.899.4tie
- AIME 2025tie99.8100tie
Questions people ask
Which is better, Claude Opus 4.6 or Gemini 3 Pro?
Claude Opus 4.6 wins four of the eight areas we test: coding, agents, math and long documents. Gemini 3 Pro wins images and charts and following instructions, and costs 53% less. They are level on reasoning and facts.
Which is better for coding?
Claude Opus 4.6. It wins 6 of the 7 coding tests both models report; Gemini 3 Pro wins 1.
Which is cheaper?
Claude Opus 4.6 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 62 benchmark tests both models have published scores on. The verdict counts the 31 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 31 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.