Claude Opus 4.6 vs Gemini 3.5 Flash
Wins 2 of 8 areas
Math · Long documents
Wins 5 of 8 areas
Agents · Reasoning · Facts · Images and charts · Following instructions
Gemini 3.5 Flash is the stronger all-rounder.Claude Opus 4.6 is better at math.
Scores updated · 50 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.
- ReasoningHard problems that need careful thinking14Gemini 3.5 Flash4 of 6 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own13Gemini 3.5 Flash3 of 4 tests
- FactsGetting facts right instead of making them up02Gemini 3.5 Flash2 of 3 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video02Gemini 3.5 Flash2 of 3 tests · 1 tie
- Following instructionsDoing exactly what it is asked02Gemini 3.5 Flash2 of 2 tests
- MathCompetition and research-level math30Claude Opus 4.63 of 5 tests · 2 ties
- Long documentsFinding answers in very long texts20Claude Opus 4.62 of 2 tests
- CodingWriting and fixing software22Even2 each · 2 ties
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 65% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Gemini 3.5 Flash pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+23.2points ahead
- Multi-step tasks using many real software toolsMCP Atlas+20.9points ahead
- Short factual questions, answered correctlySimpleQA Verified+19.2points ahead
Where Claude Opus 4.6 pulls ahead
- Finds one of eight look-alike replies in a long chatMRCR v2 8 needle 128k (average)+57.4points ahead
- Real work tasks from 44 professionsGDPVal+20.7points ahead
- Fresh logic puzzles that change regularlyLiveBench · Reasoning+6.7points ahead
Every test, side by side
All 50 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingEven
- Terminal-Bench HardClaude Opus 4.6 by 5.346.240.9+5.3
- LMArena · WebDevClaude Opus 4.6 by 47 rating points15461499+47 rating
- SciCodeGemini 3.5 Flash by 251.953.9+2
- SWE-bench ProGemini 3.5 Flash by 1.753.455.1+1.7
- LiveBench · Agentic Codingtie4949tie
- LiveBench · Codingtie78.278.2tie
AgentsGemini 3.5 Flash
- MCP AtlasGemini 3.5 Flash by 20.962.783.6+20.9
- GDPValClaude Opus 4.6 by 20.755.935.2+20.7
- AA ApexAgentsGemini 3.5 Flash by 14.13347.1+14.1
- OSWorld-VerifiedGemini 3.5 Flash by 5.772.778.4+5.7
ReasoningGemini 3.5 Flash
- SimpleBenchGemini 3.5 Flash by 9.167.676.7+9.1
- LiveBench · ReasoningClaude Opus 4.6 by 6.788.782+6.7
- ARC-AGI-2Gemini 3.5 Flash by 3.368.872.1+3.3
- Humanity's Last ExamGemini 3.5 Flash by 2.839.942.7+2.8
- GPQA DiamondGemini 3.5 Flash by 2.689.692.2+2.6
- CritPttie12.613.1tie
FactsGemini 3.5 Flash
- SimpleQA VerifiedGemini 3.5 Flash by 19.24766.2+19.2
- AA-Omniscience · AccuracyGemini 3.5 Flash by 4.44751.4+4.4
- AA-Omniscience · Non-hallucinationtie37.237.8tie
Images and chartsGemini 3.5 Flash
- MMMU-ProGemini 3.5 Flash by 8.975.484.3+8.9
- CharXiv (RQ)Gemini 3.5 Flash by 6.877.484.2+6.8
- LMArena · Visiontie13161310tie
MathClaude Opus 4.6
- FrontierMath Tiers 1-3 (v2)Claude Opus 4.6 by 3.26662.8+3.2
- AIME 2026Claude Opus 4.6 by 1.796.795+1.7
- LiveBench · MathematicsClaude Opus 4.6 by 1.189.388.2+1.1
- HMMT Feb. 2026tie96.295.5tie
- FrontierMath Tier 4tie26.826.8tie
Long documentsClaude Opus 4.6
- MRCR v2 8 needle 128k (average)Claude Opus 4.6 by 57.48426.6+57.4
- AA-LCRClaude Opus 4.6 by 4.77873.3+4.7
Following instructionsGemini 3.5 Flash
- IFBenchGemini 3.5 Flash by 23.253.176.3+23.2
- LiveBench · Instruction FollowingGemini 3.5 Flash by 12.363.375.6+12.3
Other results19 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.
- AA Agentic IndexClaude Opus 4.6 by 40.367.627.3+40.3
- Artificial Analysis Coding IndexGemini 3.5 Flash by 2248.170.1+22
- matharena_visual_math_overallGemini 3.5 Flash by 17.672.389.9+17.6
- LVBenchGemini 3.5 Flash by 13.36376.3+13.3
- Terminal-Bench 2.0Gemini 3.5 Flash by 10.865.476.2+10.8
- HiL-Bench (Tools-allowed)Claude Opus 4.6 by 10.638.327.7+10.6
- frontiermath_tier_4_v1Claude Opus 4.6 by 8.322.914.6+8.3
- AA-OmniscienceGemini 3.5 Flash by 7.513.721.2+7.5
- livebench_data_analysisClaude Opus 4.6 by 569.964.9+5
- GDPval-AA (Elo)Gemini 3.5 Flash by 37 rating points16191656+37 rating
- Legal Agent BenchmarkClaude Opus 4.6 by 3.44.20.8+3.4
- τ²-Bench Telecom (AA run)Gemini 3.5 Flash by 3.292.195.3+3.2
- Finance AgentClaude Opus 4.6 by 2.860.757.9+2.8
- LiveBenchClaude Opus 4.6 by 1.376.375+1.3
- livebench_languageGemini 3.5 Flash by 1.383.384.6+1.3
- AA Intelligencetie31.932.6tie
- ARC-AGI-1tie9392.5tie
- Toolathlontie56.856.5tie
- CharXiv Reasoning (With tools)tie84.784.9tie
Questions people ask
Which is better, Claude Opus 4.6 or Gemini 3.5 Flash?
Gemini 3.5 Flash wins five of the eight areas we test: agents, reasoning, facts, images and charts and following instructions. Claude Opus 4.6 wins math and long documents. They are level on coding.
Which is better for coding?
Neither. They win 2 coding tests each of the 6 both models report, and 2 are ties.
Which is cheaper?
Claude Opus 4.6 costs $5.00 per million input tokens and $25.00 per million output tokens; Gemini 3.5 Flash costs $1.50 and $9.00. That makes Gemini 3.5 Flash about 65% cheaper for the same work.
How do you compare the two?
We use the 50 benchmark tests both models have published scores on. The verdict counts the 31 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 19 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.