Gemini 3.1 Pro vs Claude Opus 5
Wins 3 of 8 areas
Facts · Long documents · Following instructions
Wins 5 of 8 areas
Coding · Agents · Reasoning · Images and charts · Math
Claude Opus 5 is the stronger all-rounder.Gemini 3.1 Pro is cheaper and better at facts.
Scores updated · 51 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 software17Claude Opus 57 of 8 tests
- ReasoningHard problems that need careful thinking06Claude Opus 56 of 7 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own06Claude Opus 56 of 6 tests
- MathCompetition and research-level math03Claude Opus 53 of 3 tests
- Images and chartsUnderstanding pictures, charts and video02Claude Opus 52 of 3 tests · 1 tie
- FactsGetting facts right instead of making them up21Gemini 3.1 Pro2 of 3 tests
- Long documentsFinding answers in very long texts10Gemini 3.1 Pro1 of 1 test
- Following instructionsDoing exactly what it is asked10Gemini 3.1 Pro1 of 1 test
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 3.1 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 5 pulls ahead
- Real work tasks from 44 professionsGDPVal+46.5points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+46.4points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+45points ahead
Where Gemini 3.1 Pro pulls ahead
- Follows detailed instructions exactlyLiveBench · Instruction Following+15.3points ahead
- Short factual questions, answered correctlySimpleQA Verified+13.6points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+9.9points ahead
Every test, side by side
All 51 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 5
- SWE-bench ProClaude Opus 5 by 2554.279.2+25
- LMArena · WebDevClaude Opus 5 by 249 rating points14461695+249 rating
- LiveBench · Agentic CodingClaude Opus 5 by 21.144.165.2+21.1
- SWE-bench VerifiedClaude Opus 5 by 15.480.696+15.4
- Terminal-Bench 2.1Claude Opus 5 by 15.373.889.1+15.3
- SWE-bench MultilingualClaude Opus 5 by 12.676.989.5+12.6
- LiveBench · CodingClaude Opus 5 by 576.581.5+5
- SciCodeGemini 3.1 Pro by 2.358.756.4+2.3
AgentsClaude Opus 5
- GDPValClaude Opus 5 by 46.514.761.2+46.5
- Terminal-Bench 4.0Claude Opus 5 by 45449+45
- τ-Bench V3 · BankingClaude Opus 5 by 20.721.442.1+20.7
- MCP AtlasClaude Opus 5 by 16.669.285.8+16.6
- OSWorld-VerifiedClaude Opus 5 by 7.276.283.4+7.2
- BrowseCompClaude Opus 5 by 4.985.990.8+4.9
ReasoningClaude Opus 5
- ARC-AGI-3Claude Opus 5 by 29.80.430.2+29.8
- ARC-AGI-2Claude Opus 5 by 13.377.190.4+13.3
- CritPtClaude Opus 5 by 11.417.729.1+11.4
- Humanity's Last ExamClaude Opus 5 by 7.94754.9+7.9
- LiveBench · ReasoningClaude Opus 5 by 7.28491.2+7.2
- SimpleBenchClaude Opus 5 by 179.680.6+1
- GPQA Diamondtie94.193.2tie
FactsGemini 3.1 Pro
- SimpleQA VerifiedGemini 3.1 Pro by 13.673.559.9+13.6
- AA-Omniscience · Non-hallucinationGemini 3.1 Pro by 9.949.139.2+9.9
- AA-Omniscience · AccuracyClaude Opus 5 by 654.960.9+6
Images and chartsClaude Opus 5
- LMArena · VisionClaude Opus 5 by 25 rating points12961321+25 rating
- MMMU-ProClaude Opus 5 by 2.382.484.7+2.3
- CharXiv (RQ)tie83.383.7tie
MathClaude Opus 5
- FrontierMath Tier 4Claude Opus 5 by 46.426.873.2+46.4
- FrontierMath Tiers 1-3 (v2)Claude Opus 5 by 25.959.685.6+25.9
- LiveBench · MathematicsClaude Opus 5 by 4.79195.7+4.7
Following instructionsGemini 3.1 Pro
- LiveBench · Instruction FollowingGemini 3.1 Pro by 15.379.163.8+15.3
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 v2Claude Opus 5 by 862 rating points9621824+862 rating
- GDPval-AA v2 EloClaude Opus 5 by 859 rating points9651824+859 rating
- GDP (Surge AI)Claude Opus 5 by 68.816.785.5+68.8
- DeepSWE 1.1Claude Opus 5 by 56.81268.8+56.8
- AA Agentic IndexClaude Opus 5 by 45.910.356.2+45.9
- Program BenchClaude Opus 5 by 45.939.585.4+45.9
- GDPval-AA (Elo)Claude Opus 5 by 391 rating points13171708+391 rating
- HiL-Bench (Tools-allowed)Claude Opus 5 by 21.735.357+21.7
- AA IntelligenceClaude Opus 5 by 21.129.750.8+21.1
- HLE (with tools)Claude Opus 5 by 12.251.463.6+12.2
- Legal Agent BenchmarkClaude Opus 5 by 11.7011.7+11.7
- ProteinGym HardClaude Opus 5 by 10.73747.7+10.7
- Artificial Analysis Coding IndexClaude Opus 5 by 9.268.878+9.2
- LVBenchClaude Opus 5 by 9.266.275.4+9.2
- OfficeQA ProGemini 3.1 Pro by 5.672.566.9+5.6
- AA-OmniscienceClaude Opus 5 by 5.231.937.1+5.2
- livebench_data_analysisGemini 3.1 Pro by 3.978.574.5+3.9
- livebench_languageClaude Opus 5 by 3.385.488.7+3.3
- ARC-AGI-1tie9897.5tie
Questions people ask
Which is better, Gemini 3.1 Pro or Claude Opus 5?
Claude Opus 5 wins five of the eight areas we test: coding, agents, reasoning, images and charts and math. Gemini 3.1 Pro wins facts, long documents and following instructions, and costs 53% less.
Which is better for coding?
Claude Opus 5. It wins 7 of the 8 coding tests both models report; Gemini 3.1 Pro wins 1.
Which is cheaper?
Gemini 3.1 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; Claude Opus 5 costs $5.00 and $25.00. That makes Gemini 3.1 Pro about 53% cheaper for the same work.
How do you compare the two?
We use the 51 benchmark tests both models have published scores on. The verdict counts the 32 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.