Claude Sonnet 5 vs Gemini 3.5 Flash
Wins 4 of 8 areas
Coding · Agents · Math · Long documents
Wins 4 of 8 areas
Reasoning · Facts · Images and charts · Following instructions
The two are evenly matched.Claude Sonnet 5 is better at coding and agents; Gemini 3.5 Flash at reasoning and facts.
Scores updated · 42 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 software50Claude Sonnet 55 of 6 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own40Claude Sonnet 54 of 4 tests
- MathCompetition and research-level math30Claude Sonnet 53 of 3 tests
- Long documentsFinding answers in very long texts20Claude Sonnet 52 of 2 tests
- ReasoningHard problems that need careful thinking23Gemini 3.5 Flash3 of 5 tests
- FactsGetting facts right instead of making them up12Gemini 3.5 Flash2 of 3 tests
- Images and chartsUnderstanding pictures, charts and video12Gemini 3.5 Flash2 of 3 tests
- Following instructionsDoing exactly what it is asked01Gemini 3.5 Flash1 of 1 test
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 3.5 Flash costs 13% 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
- Finds one of eight look-alike replies in a long chatMRCR v2 8 needle 128k (average)+54.9points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+22.8points ahead
- Real work tasks from 44 professionsGDPVal+13.1points ahead
Where Gemini 3.5 Flash pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+32.5points ahead
- Common-sense trick questionsSimpleBench+16.1points ahead
- Follows detailed instructions exactlyLiveBench · Instruction Following+11.7points ahead
Every test, side by side
All 42 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 10.459.449+10.4
- SWE-bench ProClaude Sonnet 5 by 8.163.255.1+8.1
- LMArena · WebDevClaude Sonnet 5 by 42 rating points15411499+42 rating
- LiveBench · CodingClaude Sonnet 5 by 2.580.778.2+2.5
- Terminal-Bench 2.1Claude Sonnet 5 by 1.880.578.7+1.8
- SciCodetie54.353.9tie
AgentsClaude Sonnet 5
- GDPValClaude Sonnet 5 by 13.148.335.2+13.1
- Terminal-Bench 4.0Claude Sonnet 5 by 7.514.16.6+7.5
- τ-Bench V3 · BankingClaude Sonnet 5 by 5.137.332.2+5.1
- OSWorld-VerifiedClaude Sonnet 5 by 2.881.278.4+2.8
ReasoningGemini 3.5 Flash
- SimpleBenchGemini 3.5 Flash by 16.160.676.7+16.1
- LiveBench · ReasoningClaude Sonnet 5 by 6.788.782+6.7
- CritPtClaude Sonnet 5 by 3.816.913.1+3.8
- Humanity's Last ExamGemini 3.5 Flash by 1.441.342.7+1.4
- GPQA DiamondGemini 3.5 Flash by 1.191.192.2+1.1
FactsGemini 3.5 Flash
- SimpleQA VerifiedGemini 3.5 Flash by 32.533.766.2+32.5
- AA-Omniscience · Non-hallucinationClaude Sonnet 5 by 22.860.637.8+22.8
- AA-Omniscience · AccuracyGemini 3.5 Flash by 11.34051.4+11.3
Images and chartsGemini 3.5 Flash
- MMMU-ProGemini 3.5 Flash by 777.384.3+7
- CharXiv (RQ)Claude Sonnet 5 by 4.188.384.2+4.1
- LMArena · VisionGemini 3.5 Flash by 35 rating points12751310+35 rating
MathClaude Sonnet 5
- LiveBench · MathematicsClaude Sonnet 5 by 4.792.988.2+4.7
- FrontierMath Tiers 1-3 (v2)Claude Sonnet 5 by 2.865.662.8+2.8
- FrontierMath Tier 4Claude Sonnet 5 by 2.529.326.8+2.5
Long documentsClaude Sonnet 5
- MRCR v2 8 needle 128k (average)Claude Sonnet 5 by 54.981.526.6+54.9
- AA-LCRClaude Sonnet 5 by 8.78273.3+8.7
Following instructionsGemini 3.5 Flash
- LiveBench · Instruction FollowingGemini 3.5 Flash by 11.763.975.6+11.7
Other results15 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 Sonnet 5 by 269 rating points16181349+269 rating
- GDPval-AA v2 EloClaude Sonnet 5 by 235 rating points15841349+235 rating
- MLE-BenchClaude Sonnet 5 by 17.266.949.7+17.2
- AA Agentic IndexClaude Sonnet 5 by 1744.327.3+17
- DeepSWE 1.1Claude Sonnet 5 by 175437+17
- livebench_languageGemini 3.5 Flash by 9.67584.6+9.6
- LVBenchGemini 3.5 Flash by 7.868.576.3+7.8
- livebench_data_analysisClaude Sonnet 5 by 6.871.764.9+6.8
- AA IntelligenceClaude Sonnet 5 by 5.638.232.6+5.6
- Legal Agent BenchmarkClaude Sonnet 5 by 55.80.8+5
- AA-OmniscienceGemini 3.5 Flash by 4.716.421.2+4.7
- Terminal-Bench 2.0Claude Sonnet 5 by 4.280.476.2+4.2
- CharXiv Reasoning (With tools)Claude Sonnet 5 by 3.488.384.9+3.4
- ToolathlonGemini 3.5 Flash by 2.254.356.5+2.2
- Artificial Analysis Coding IndexClaude Sonnet 5 by 1.471.570.1+1.4
Questions people ask
Which is better, Claude Sonnet 5 or Gemini 3.5 Flash?
Claude Sonnet 5 and Gemini 3.5 Flash each win four of the eight areas we test. Claude Sonnet 5 wins coding, agents, math and long documents; Gemini 3.5 Flash wins reasoning, facts, images and charts and following instructions. Gemini 3.5 Flash costs 13% less.
Which is better for coding?
Claude Sonnet 5. It wins 5 of the 6 coding tests both models report; Gemini 3.5 Flash wins none, and 1 is a tie.
Which is cheaper?
Claude Sonnet 5 costs $2.00 per million input tokens and $10.00 per million output tokens; Gemini 3.5 Flash costs $1.50 and $9.00. That makes Gemini 3.5 Flash about 13% cheaper for the same work.
How do you compare the two?
We use the 42 benchmark tests both models have published scores on. The verdict counts the 27 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 15 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.