Claude Sonnet 5 vs Gemini 3.6 Flash
Wins 4 of 8 areas
Coding · Agents · Reasoning · Math
Wins 3 of 8 areas
Facts · Images and charts · Following instructions
Claude Sonnet 5 wins more areas, narrowly.Gemini 3.6 Flash is cheaper and better at images and charts.
Scores updated · 43 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 software40Claude Sonnet 54 of 6 tests · 2 ties
- MathCompetition and research-level math30Claude Sonnet 53 of 3 tests
- AgentsCarrying out multi-step tasks on its own31Claude Sonnet 53 of 4 tests
- ReasoningHard problems that need careful thinking21Claude Sonnet 52 of 4 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video03Gemini 3.6 Flash3 of 3 tests
- FactsGetting facts right instead of making them up12Gemini 3.6 Flash2 of 3 tests
- Following instructionsDoing exactly what it is asked01Gemini 3.6 Flash1 of 1 test
- Long documentsFinding answers in very long texts11Even1 each
Following instructions 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 3.6 Flash costs 63% 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 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+16.2points ahead
- Fixes real GitHub issues, working as an agentLiveBench · Agentic Coding+16points ahead
- Real work tasks from 44 professionsGDPVal+9points ahead
Where Gemini 3.6 Flash pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+32.5points ahead
- Follows detailed instructions exactlyLiveBench · Instruction Following+11.5points ahead
- Finds one of eight look-alike replies in a long chatMRCR v2 8 needle 128k (average)+10.3points ahead
Every test, side by side
All 43 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 5
- LiveBench · Agentic CodingClaude Sonnet 5 by 1659.443.4+16
- SWE-bench ProClaude Sonnet 5 by 4.563.258.7+4.5
- Terminal-Bench 2.1Claude Sonnet 5 by 380.577.5+3
- LiveBench · CodingClaude Sonnet 5 by 2.880.777.9+2.8
- SciCodetie54.353.4tie
- LMArena · WebDevtie15411538tie
AgentsClaude Sonnet 5
- GDPValClaude Sonnet 5 by 948.339.3+9
- τ-Bench V3 · BankingClaude Sonnet 5 by 7.437.329.9+7.4
- Terminal-Bench 4.0Claude Sonnet 5 by 714.17.1+7
- OSWorld-VerifiedGemini 3.6 Flash by 1.881.283+1.8
ReasoningClaude Sonnet 5
- CritPtClaude Sonnet 5 by 6.316.910.6+6.3
- LiveBench · ReasoningClaude Sonnet 5 by 3.588.785.2+3.5
- GPQA DiamondGemini 3.6 Flash by 1.791.192.8+1.7
- Humanity's Last Examtie41.340.8tie
FactsGemini 3.6 Flash
- SimpleQA VerifiedGemini 3.6 Flash by 32.533.766.2+32.5
- AA-Omniscience · Non-hallucinationClaude Sonnet 5 by 16.260.644.4+16.2
- AA-Omniscience · AccuracyGemini 3.6 Flash by 9.94050+9.9
Images and chartsGemini 3.6 Flash
- MMMU-ProGemini 3.6 Flash by 5.977.383.2+5.9
- LMArena · VisionGemini 3.6 Flash by 22 rating points12751297+22 rating
- CharXiv (RQ)Gemini 3.6 Flash by 1.188.389.4+1.1
MathClaude Sonnet 5
- FrontierMath Tier 4Claude Sonnet 5 by 7.329.321.9+7.3
- FrontierMath Tiers 1-3 (v2)Claude Sonnet 5 by 6.665.659+6.6
- LiveBench · MathematicsClaude Sonnet 5 by 6.592.986.4+6.5
Long documentsEven
- MRCR v2 8 needle 128k (average)Gemini 3.6 Flash by 10.381.591.8+10.3
- AA-LCRClaude Sonnet 5 by 28280+2
Following instructionsGemini 3.6 Flash
- LiveBench · Instruction FollowingGemini 3.6 Flash by 11.563.975.4+11.5
Other results17 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.
- GDP (Surge AI)Claude Sonnet 5 by 59.681.622+59.6
- HLE-VerifiedGemini 3.6 Flash by 20.23151.2+20.2
- GDPval-AA v2Claude Sonnet 5 by 197 rating points16181421+197 rating
- GDPval-AA v2 EloClaude Sonnet 5 by 162 rating points15841422+162 rating
- LVBenchGemini 3.6 Flash by 15.768.584.2+15.7
- AA Agentic IndexClaude Sonnet 5 by 14.144.330.2+14.1
- Terminal-bench 3.0Claude Sonnet 5 by 9.214.65.4+9.2
- Agent's Last Exam (Pass rate)Claude Sonnet 5 by 9.133.324.2+9.1
- livebench_languageGemini 3.6 Flash by 8.97583.9+8.9
- livebench_data_analysisClaude Sonnet 5 by 8.771.763+8.7
- AA-OmniscienceGemini 3.6 Flash by 5.616.422.1+5.6
- DeepSWE 1.1Claude Sonnet 5 by 55449+5
- AA IntelligenceClaude Sonnet 5 by 4.238.234+4.2
- MLE-BenchClaude Sonnet 5 by 366.963.9+3
- Artificial Analysis Coding IndexClaude Sonnet 5 by 2.371.569.2+2.3
- CharXiv Reasoning (With tools)Gemini 3.6 Flash by 1.188.389.4+1.1
- Code Arena (Elo)tie15411538tie
Questions people ask
Which is better, Claude Sonnet 5 or Gemini 3.6 Flash?
Claude Sonnet 5 wins four of the eight areas we test: coding, agents, reasoning and math. Gemini 3.6 Flash wins facts, images and charts and following instructions, and costs 63% less. They are level on long documents.
Which is better for coding?
Claude Sonnet 5. It wins 4 of the 6 coding tests both models report; Gemini 3.6 Flash wins none, and 2 are ties.
Which is cheaper?
Claude Sonnet 5 costs $2.00 per million input tokens and $10.00 per million output tokens; Gemini 3.6 Flash costs $0.75 and $3.75. That makes Gemini 3.6 Flash about 63% cheaper for the same work.
How do you compare the two?
We use the 43 benchmark tests both models have published scores on. The verdict counts the 26 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 17 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.