Claude Sonnet 4 vs Gemini 3.1 Pro
Wins 0 of 7 areas
—
Wins 6 of 7 areas
Coding · Agents · Reasoning · Images and charts · Long documents · Following instructions
Gemini 3.1 Pro is the stronger all-rounder.
Scores updated · 40 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 software07Gemini 3.1 Pro7 of 7 tests
- ReasoningHard problems that need careful thinking05Gemini 3.1 Pro5 of 5 tests
- AgentsCarrying out multi-step tasks on its own04Gemini 3.1 Pro4 of 4 tests
- Images and chartsUnderstanding pictures, charts and video02Gemini 3.1 Pro2 of 2 tests
- Following instructionsDoing exactly what it is asked02Gemini 3.1 Pro2 of 2 tests
- Long documentsFinding answers in very long texts01Gemini 3.1 Pro1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each · 1 tie
Long documents 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 3.1 Pro costs 22% 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 3.1 Pro pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+73.7points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+71.2points ahead
- Recent programming contest problemsLiveCodeBench v6+43.2points ahead
Where Claude Sonnet 4 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+21.8points ahead
Every test, side by side
All 40 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 3.1 Pro
- LiveCodeBench v6Gemini 3.1 Pro by 43.248.591.7+43.2
- Terminal-Bench 2.1Gemini 3.1 Pro by 37.536.373.8+37.5
- Terminal-Bench HardGemini 3.1 Pro by 22.731.153.8+22.7
- SWE-bench MultilingualGemini 3.1 Pro by 2056.976.9+20
- SciCodeGemini 3.1 Pro by 18.74058.7+18.7
- SWE-bench ProGemini 3.1 Pro by 11.542.754.2+11.5
- SWE-bench VerifiedGemini 3.1 Pro by 7.972.780.6+7.9
AgentsGemini 3.1 Pro
- BrowseCompGemini 3.1 Pro by 73.712.285.9+73.7
- OSWorld-VerifiedGemini 3.1 Pro by 3442.276.2+34
- GDPValGemini 3.1 Pro by 59.714.7+5
- τ-Bench V3 · BankingGemini 3.1 Pro by 4.716.721.4+4.7
ReasoningGemini 3.1 Pro
- ARC-AGI-2Gemini 3.1 Pro by 71.25.977.1+71.2
- Humanity's Last ExamGemini 3.1 Pro by 36.310.747+36.3
- SimpleBenchGemini 3.1 Pro by 34.145.579.6+34.1
- CritPtGemini 3.1 Pro by 17.40.317.7+17.4
- GPQA DiamondGemini 3.1 Pro by 16.477.794.1+16.4
FactsEven
- AA-Omniscience · AccuracyGemini 3.1 Pro by 32.222.754.9+32.2
- AA-Omniscience · Non-hallucinationClaude Sonnet 4 by 21.870.949.1+21.8
- Vectara HHEM hallucination ratelower is bettertie10.310.4tie
Images and chartsGemini 3.1 Pro
- MMMU-ProGemini 3.1 Pro by 20.661.882.4+20.6
- LMArena · VisionGemini 3.1 Pro by 105 rating points11911296+105 rating
Following instructionsGemini 3.1 Pro
- IFBenchGemini 3.1 Pro by 22.454.777.1+22.4
- Multi-ChallengeGemini 3.1 Pro by 14.357.171.4+14.3
Other results16 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.
- ARC-AGI-1Gemini 3.1 Pro by 584098+58
- AA-OmniscienceGemini 3.1 Pro by 31.70.231.9+31.7
- Artificial Analysis Coding IndexGemini 3.1 Pro by 31.237.668.8+31.2
- HLE (with tools)Gemini 3.1 Pro by 31.120.351.4+31.1
- τ²-Bench Telecom (AA run)Gemini 3.1 Pro by 3164.695.6+31
- LiveCodeBenchGemini 3.1 Pro by 23.268.591.7+23.2
- frontiermath_tier_4_v1Gemini 3.1 Pro by 16.7016.7+16.7
- AA IntelligenceGemini 3.1 Pro by 10.818.929.7+10.8
- AA Agentic IndexClaude Sonnet 4 by 7.317.610.3+7.3
- MMLU-ProGemini 3.1 Pro by 7.383.791+7.3
- MMMLUGemini 3.1 Pro by 6.186.592.6+6.1
- LiveBenchGemini 3.1 Pro by 5.174.879.9+5.1
- vectara_avg_summary_lengthClaude Sonnet 4 by 38.1 rating points145.8107.7+38.1 rating
- MMLUGemini 3.1 Pro by 1.191.592.6+1.1
- vectara_answer_ratetie98.699.4tie
- vectara_factual_consistencytie89.789.6tie
Questions people ask
Which is better, Claude Sonnet 4 or Gemini 3.1 Pro?
Gemini 3.1 Pro wins six of the seven areas where both have results: coding, agents, reasoning, images and charts, long documents and following instructions. Claude Sonnet 4 wins none. They are level on facts.
Which is better for coding?
Gemini 3.1 Pro. It wins 7 of the 7 coding tests both models report; Claude Sonnet 4 wins none.
Which is cheaper?
Claude Sonnet 4 costs $3.00 per million input tokens and $15.00 per million output tokens; Gemini 3.1 Pro costs $2.00 and $12.00. That makes Gemini 3.1 Pro about 22% cheaper for the same work.
How do you compare the two?
We use the 40 benchmark tests both models have published scores on. The verdict counts the 24 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 16 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.