Claude Opus 4.1 vs Gemini 3 Pro
Wins 0 of 7 areas
—
Wins 5 of 7 areas
Coding · Agents · Reasoning · Images and charts · Following instructions
Gemini 3 Pro is the stronger all-rounder.
Scores updated · 29 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.
- CodingWriting and fixing software04Gemini 3 Pro4 of 4 tests
- ReasoningHard problems that need careful thinking03Gemini 3 Pro3 of 3 tests
- Following instructionsDoing exactly what it is asked02Gemini 3 Pro2 of 2 tests
- AgentsCarrying out multi-step tasks on its own01Gemini 3 Pro1 of 1 test
- Images and chartsUnderstanding pictures, charts and video01Gemini 3 Pro1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
Agents, images and charts 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 3 Pro 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 3 Pro pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+38.1points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+27.2points ahead
- Code for real scientific research problemsSciCode+15.2points ahead
Where Claude Opus 4.1 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 29 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 3 Pro
- SciCodeGemini 3 Pro by 15.240.956.1+15.2
- Terminal-Bench HardGemini 3 Pro by 7.434.341.7+7.4
- LMArena · WebDevGemini 3 Pro by 50 rating points13901440+50 rating
- SWE-bench VerifiedGemini 3 Pro by 1.774.576.2+1.7
ReasoningGemini 3 Pro
- Humanity's Last ExamGemini 3 Pro by 27.212.539.7+27.2
- GPQA DiamondGemini 3 Pro by 9.980.990.8+9.9
- CritPtGemini 3 Pro by 9.109.1+9.1
FactsEven
- SimpleQA VerifiedGemini 3 Pro by 38.134.872.9+38.1
- Vectara HHEM hallucination ratelower is betterClaude Opus 4.1 by 1.811.813.6+1.8
Images and chartsGemini 3 Pro
- MMMU-ProGemini 3 Pro by 12.367.980.2+12.3
Following instructionsGemini 3 Pro
- IFBenchGemini 3 Pro by 1555.470.4+15
- Multi-ChallengeGemini 3 Pro by 8.557.265.7+8.5
Other results15 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.
- τ²-BenchGemini 3 Pro by 26.571.598+26.5
- AIME 2025Gemini 3 Pro by 2278100+22
- metr_re_benchGemini 3 Pro by 201535+20
- τ²-Bench Telecom (AA run)Gemini 3 Pro by 15.771.487.1+15.7
- frontiermath_tier_4_v1Gemini 3 Pro by 14.64.218.8+14.6
- metr_hcastGemini 3 Pro by 10.760.671.3+10.7
- Artificial Analysis Coding IndexGemini 3 Pro by 1036.546.5+10
- Terminal-Bench 2.0Gemini 3 Pro by 7.746.554.2+7.7
- vectara_answer_rateGemini 3 Pro by 792.499.4+7
- AA IntelligenceGemini 3 Pro by 5.222.828+5.2
- vectara_avg_summary_lengthClaude Opus 4.1 by 27.2 rating points129.1101.9+27.2 rating
- MMMLUGemini 3 Pro by 2.389.591.8+2.3
- vectara_factual_consistencyClaude Opus 4.1 by 1.888.286.4+1.8
- τ²-Bench (Retail)Claude Opus 4.1 by 1.586.885.3+1.5
- metr_swaatie10099.5tie
Questions people ask
Which is better, Claude Opus 4.1 or Gemini 3 Pro?
Gemini 3 Pro wins five of the seven areas where both have results: coding, agents, reasoning, images and charts and following instructions. Claude Opus 4.1 wins none. They are level on facts and long documents.
Which is better for coding?
Gemini 3 Pro. It wins 4 of the 4 coding tests both models report; Claude Opus 4.1 wins none.
Which is cheaper?
Claude Opus 4.1 costs $15.00 per million input tokens and $75.00 per million output tokens; Gemini 3 Pro costs $2.00 and $12.00. That makes Gemini 3 Pro about 84% cheaper for the same work.
How do you compare the two?
We use the 29 benchmark tests both models have published scores on. The verdict counts the 14 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 15 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.