Gemini 3.1 Pro vs Claude Sonnet 5.5
Wins 1 of 8 areas
Following instructions
Wins 4 of 8 areas
Coding · Agents · Reasoning · Math
Claude Sonnet 5.5 wins more areas, narrowly.Gemini 3.1 Pro is better at following instructions.
Scores updated · 34 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 software06Claude Sonnet 5.56 of 6 tests
- ReasoningHard problems that need careful thinking15Claude Sonnet 5.55 of 6 tests
- MathCompetition and research-level math03Claude Sonnet 5.53 of 3 tests
- AgentsCarrying out multi-step tasks on its own02Claude Sonnet 5.52 of 2 tests
- Following instructionsDoing exactly what it is asked10Gemini 3.1 Pro1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each · 1 tie
- Images and chartsUnderstanding pictures, charts and video00Even0 each · 1 tie
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
Images and charts, 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.
Claude Sonnet 5.5 costs 14% 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 Sonnet 5.5 pulls ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+59.6points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+53.7points ahead
- Real work tasks from 44 professionsGDPVal+52.3points ahead
Where Gemini 3.1 Pro pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+27points ahead
- Follows detailed instructions exactlyLiveBench · Instruction Following+22.3points ahead
- Common-sense trick questionsSimpleBench+3.7points ahead
Every test, side by side
All 34 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 5.5
- LMArena · WebDevClaude Sonnet 5.5 by 323 rating points14471770+323 rating
- SWE-bench ProClaude Sonnet 5.5 by 27.154.281.3+27.1
- LiveBench · CodingClaude Sonnet 5.5 by 14.976.591.4+14.9
- SWE-bench MultilingualClaude Sonnet 5.5 by 13.476.990.3+13.4
- LiveBench · Agentic CodingClaude Sonnet 5.5 by 12.244.156.3+12.2
- SciCodeClaude Sonnet 5.5 by 2.358.761+2.3
AgentsClaude Sonnet 5.5
- Terminal-Bench 4.0Claude Sonnet 5.5 by 59.6463.6+59.6
- GDPValClaude Sonnet 5.5 by 52.314.666.9+52.3
ReasoningClaude Sonnet 5.5
- ARC-AGI-3Claude Sonnet 5.5 by 23.90.424.3+23.9
- CritPtClaude Sonnet 5.5 by 13.717.731.4+13.7
- Humanity's Last ExamClaude Sonnet 5.5 by 84755+8
- LiveBench · ReasoningClaude Sonnet 5.5 by 7.68491.6+7.6
- ARC-AGI-2Claude Sonnet 5.5 by 6.877.183.9+6.8
- SimpleBenchGemini 3.1 Pro by 3.779.675.9+3.7
FactsEven
- SimpleQA VerifiedGemini 3.1 Pro by 2773.546.5+27
- AA-Omniscience · Non-hallucinationClaude Sonnet 5.5 by 3.949.153+3.9
- AA-Omniscience · Accuracytie54.954tie
MathClaude Sonnet 5.5
- FrontierMath Tier 4Claude Sonnet 5.5 by 53.726.880.5+53.7
- FrontierMath Tiers 1-3 (v2)Claude Sonnet 5.5 by 29.159.688.8+29.1
- LiveBench · MathematicsClaude Sonnet 5.5 by 5.19196.1+5.1
Following instructionsGemini 3.1 Pro
- LiveBench · Instruction FollowingGemini 3.1 Pro by 22.379.156.8+22.3
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.
- DeepSWE 1.1Claude Sonnet 5.5 by 591271+59
- Program BenchClaude Sonnet 5.5 by 40.239.579.7+40.2
- AA IntelligenceClaude Sonnet 5.5 by 26.329.756+26.3
- ArXivMath without toolsClaude Sonnet 5.5 by 20.86686.8+20.8
- livebench_data_analysisGemini 3.1 Pro by 1978.559.5+19
- HLE (with tools)Claude Sonnet 5.5 by 13.151.464.5+13.1
- Legal Agent BenchmarkClaude Sonnet 5.5 by 11.7011.7+11.7
- livebench_languageGemini 3.1 Pro by 7.485.478+7.4
- OfficeQA ProGemini 3.1 Pro by 6.972.565.6+6.9
- ARC-AGI-1Gemini 3.1 Pro by 1.59896.5+1.5
- AA-Omnisciencetie31.932.3tie
Questions people ask
Which is better, Gemini 3.1 Pro or Claude Sonnet 5.5?
Claude Sonnet 5.5 wins four of the eight areas we test: coding, agents, reasoning and math. Gemini 3.1 Pro wins following instructions. They are level on facts, images and charts and long documents.
Which is better for coding?
Claude Sonnet 5.5. It wins 6 of the 6 coding tests both models report; Gemini 3.1 Pro wins none.
Which is cheaper?
Gemini 3.1 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; Claude Sonnet 5.5 costs $2.00 and $10.00. That makes Claude Sonnet 5.5 about 14% cheaper for the same work.
How do you compare the two?
We use the 34 benchmark tests both models have published scores on. The verdict counts the 23 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.