Gemini 3.5 Flash vs Claude Opus 5
Wins 1 of 8 areas
Following instructions
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents
Claude Opus 5 is the stronger all-rounder.Gemini 3.5 Flash is cheaper and better at following instructions.
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 software06Claude Opus 56 of 6 tests
- ReasoningHard problems that need careful thinking06Claude Opus 56 of 6 tests
- AgentsCarrying out multi-step tasks on its own05Claude Opus 55 of 5 tests
- MathCompetition and research-level math03Claude Opus 53 of 3 tests
- FactsGetting facts right instead of making them up12Claude Opus 52 of 3 tests
- Images and chartsUnderstanding pictures, charts and video01Claude Opus 51 of 3 tests · 2 ties
- Long documentsFinding answers in very long texts01Claude Opus 51 of 1 test
- Following instructionsDoing exactly what it is asked10Gemini 3.5 Flash1 of 1 test
Long documents and following instructions rest on a single test each.
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 tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Claude Opus 5 pulls ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+46.4points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+42.4points ahead
- Real work tasks from 44 professionsGDPVal+26points ahead
Where Gemini 3.5 Flash pulls ahead
- Follows detailed instructions exactlyLiveBench · Instruction Following+11.8points ahead
- Short factual questions, answered correctlySimpleQA Verified+6.3points 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 Opus 5
- SWE-bench ProClaude Opus 5 by 24.155.179.2+24.1
- LMArena · WebDevClaude Opus 5 by 193 rating points14991692+193 rating
- LiveBench · Agentic CodingClaude Opus 5 by 16.24965.2+16.2
- Terminal-Bench 2.1Claude Opus 5 by 10.478.789.1+10.4
- LiveBench · CodingClaude Opus 5 by 3.378.281.5+3.3
- SciCodeClaude Opus 5 by 2.553.956.4+2.5
AgentsClaude Opus 5
- Terminal-Bench 4.0Claude Opus 5 by 42.46.649+42.4
- GDPValClaude Opus 5 by 2635.261.2+26
- τ-Bench V3 · BankingClaude Opus 5 by 9.932.242.1+9.9
- OSWorld-VerifiedClaude Opus 5 by 578.483.4+5
- MCP AtlasClaude Opus 5 by 2.283.685.8+2.2
ReasoningClaude Opus 5
- ARC-AGI-2Claude Opus 5 by 18.372.190.4+18.3
- CritPtClaude Opus 5 by 1613.129.1+16
- Humanity's Last ExamClaude Opus 5 by 12.242.754.9+12.2
- LiveBench · ReasoningClaude Opus 5 by 9.28291.2+9.2
- SimpleBenchClaude Opus 5 by 3.976.780.6+3.9
- GPQA DiamondClaude Opus 5 by 192.293.2+1
FactsClaude Opus 5
- AA-Omniscience · AccuracyClaude Opus 5 by 9.551.460.9+9.5
- SimpleQA VerifiedGemini 3.5 Flash by 6.366.259.9+6.3
- AA-Omniscience · Non-hallucinationClaude Opus 5 by 1.437.839.2+1.4
Images and chartsClaude Opus 5
- LMArena · VisionClaude Opus 5 by 11 rating points13101321+11 rating
- CharXiv (RQ)tie84.283.7tie
- MMMU-Protie84.384.7tie
MathClaude Opus 5
- FrontierMath Tier 4Claude Opus 5 by 46.426.873.2+46.4
- FrontierMath Tiers 1-3 (v2)Claude Opus 5 by 22.862.885.6+22.8
- LiveBench · MathematicsClaude Opus 5 by 7.588.295.7+7.5
Following instructionsGemini 3.5 Flash
- LiveBench · Instruction FollowingGemini 3.5 Flash by 11.875.663.8+11.8
Other results14 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 Opus 5 by 475 rating points13491824+475 rating
- GDPval-AA v2 EloClaude Opus 5 by 475 rating points13491824+475 rating
- DeepSWE 1.1Claude Opus 5 by 31.83768.8+31.8
- HiL-Bench (Tools-allowed)Claude Opus 5 by 29.327.757+29.3
- AA Agentic IndexClaude Opus 5 by 28.927.356.2+28.9
- AA IntelligenceClaude Opus 5 by 18.232.650.8+18.2
- AA-OmniscienceClaude Opus 5 by 15.921.237.1+15.9
- Legal Agent BenchmarkClaude Opus 5 by 10.90.811.7+10.9
- livebench_data_analysisClaude Opus 5 by 9.764.974.5+9.7
- Artificial Analysis Coding IndexClaude Opus 5 by 7.970.178+7.9
- GDPval-AA (Elo)Claude Opus 5 by 52 rating points16561708+52 rating
- ARC-AGI-1Claude Opus 5 by 592.597.5+5
- livebench_languageClaude Opus 5 by 4.184.688.7+4.1
- LVBenchtie76.375.4tie
Questions people ask
Which is better, Gemini 3.5 Flash or Claude Opus 5?
Claude Opus 5 wins seven of the eight areas we test: coding, agents, reasoning, facts, images and charts, math and long documents. Gemini 3.5 Flash wins following instructions, and costs 65% less.
Which is better for coding?
Claude Opus 5. It wins 6 of the 6 coding tests both models report; Gemini 3.5 Flash wins none.
Which is cheaper?
Gemini 3.5 Flash costs $1.50 per million input tokens and $9.00 per million output tokens; Claude Opus 5 costs $5.00 and $25.00. That makes Gemini 3.5 Flash about 65% 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 28 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 14 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.