Claude Sonnet 4 vs Gemini 3 Pro
Wins 1 of 7 areas
Facts
Wins 6 of 7 areas
Coding · Agents · Reasoning · Images and charts · Long documents · Following instructions
Gemini 3 Pro is the stronger all-rounder.Claude Sonnet 4 is better at facts.
Scores updated · 47 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 software05Gemini 3 Pro5 of 6 tests · 1 tie
- ReasoningHard problems that need careful thinking05Gemini 3 Pro5 of 5 tests
- AgentsCarrying out multi-step tasks on its own02Gemini 3 Pro2 of 2 tests
- Images and chartsUnderstanding pictures, charts and video02Gemini 3 Pro2 of 2 tests
- Following instructionsDoing exactly what it is asked02Gemini 3 Pro2 of 2 tests
- Long documentsFinding answers in very long texts01Gemini 3 Pro1 of 1 test
- FactsGetting facts right instead of making them up21Claude Sonnet 42 of 3 tests
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 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 Pro pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+47points ahead
- Recent programming contest problemsLiveCodeBench v6+38.9points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+33.1points ahead
Where Claude Sonnet 4 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+62.4points ahead
Every test, side by side
All 47 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 3 Pro
- LiveCodeBench v6Gemini 3 Pro by 38.948.587.4+38.9
- SciCodeGemini 3 Pro by 16.14056.1+16.1
- Terminal-Bench HardGemini 3 Pro by 10.631.141.7+10.6
- SWE-bench MultilingualGemini 3 Pro by 8.156.965+8.1
- SWE-bench VerifiedGemini 3 Pro by 3.572.776.2+3.5
- SWE-bench Protie42.743.3tie
AgentsGemini 3 Pro
- BrowseCompGemini 3 Pro by 4712.259.2+47
- GDPValGemini 3 Pro by 24.59.734.2+24.5
ReasoningGemini 3 Pro
- SimpleBenchGemini 3 Pro by 30.945.576.4+30.9
- Humanity's Last ExamGemini 3 Pro by 2910.739.7+29
- ARC-AGI-2Gemini 3 Pro by 25.25.931.1+25.2
- GPQA DiamondGemini 3 Pro by 13.177.790.8+13.1
- CritPtGemini 3 Pro by 8.80.39.1+8.8
FactsClaude Sonnet 4
- AA-Omniscience · Non-hallucinationClaude Sonnet 4 by 62.470.98.5+62.4
- AA-Omniscience · AccuracyGemini 3 Pro by 33.122.755.8+33.1
- Vectara HHEM hallucination ratelower is betterClaude Sonnet 4 by 3.310.313.6+3.3
Images and chartsGemini 3 Pro
- MMMU-ProGemini 3 Pro by 18.461.880.2+18.4
- LMArena · VisionGemini 3 Pro by 114 rating points11911305+114 rating
Following instructionsGemini 3 Pro
- IFBenchGemini 3 Pro by 15.754.770.4+15.7
- Multi-ChallengeGemini 3 Pro by 8.657.165.7+8.6
Other results26 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.
- SimpleQAGemini 3 Pro by 56.215.972.1+56.2
- τ²-BenchGemini 3 Pro by 52.845.298+52.8
- ARC-AGI-1Gemini 3 Pro by 354075+35
- AA Agentic IndexGemini 3 Pro by 34.417.652+34.4
- AIME 2025Gemini 3 Pro by 29.570.5100+29.5
- HarmBenchClaude Sonnet 4 by 25.59872.5+25.5
- HLE (with tools)Gemini 3 Pro by 25.520.345.8+25.5
- LiveCodeBenchGemini 3 Pro by 23.568.592+23.5
- τ²-Bench Telecom (AA run)Gemini 3 Pro by 22.564.687.1+22.5
- frontiermath_tier_4_v1Gemini 3 Pro by 18.8018.8+18.8
- AA-OmniscienceGemini 3 Pro by 15.10.215.3+15.1
- AIR-Bench 2024Claude Sonnet 4 by 15.188.373.2+15.1
- τ²-Bench (Retail)Gemini 3 Pro by 10.37585.3+10.3
- AA IntelligenceGemini 3 Pro by 9.118.928+9.1
- Artificial Analysis Coding IndexGemini 3 Pro by 8.937.646.5+8.9
- Multi-SWE-BenchGemini 3 Pro by 735.742.7+7
- MMLU-ProGemini 3 Pro by 6.483.790.1+6.4
- MMMLUGemini 3 Pro by 5.386.591.8+5.3
- vectara_avg_summary_lengthClaude Sonnet 4 by 43.9 rating points145.8101.9+43.9 rating
- vectara_factual_consistencyClaude Sonnet 4 by 3.389.786.4+3.3
- simple_safety_testsClaude Sonnet 4 by 2.510097.5+2.5
- anthropic_red_teamClaude Sonnet 4 by 2.199.297+2.1
- bbqGemini 3 Pro by 1.896.698.4+1.8
- LiveBenchClaude Sonnet 4 by 1.474.873.4+1.4
- vectara_answer_ratetie98.699.4tie
- XSTesttie96.697.3tie
Questions people ask
Which is better, Claude Sonnet 4 or Gemini 3 Pro?
Gemini 3 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 facts.
Which is better for coding?
Gemini 3 Pro. It wins 5 of the 6 coding tests both models report; Claude Sonnet 4 wins none, and 1 is a tie.
Which is cheaper?
Claude Sonnet 4 costs $3.00 per million input tokens and $15.00 per million output tokens; Gemini 3 Pro costs $2.00 and $12.00. That makes Gemini 3 Pro about 22% cheaper for the same work.
How do you compare the two?
We use the 47 benchmark tests both models have published scores on. The verdict counts the 21 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 26 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.