Gemini 3.7 Flash vs Claude Opus 5
Wins 3 of 8 areas
Images and charts · Long documents · Following instructions
Wins 5 of 8 areas
Coding · Agents · Reasoning · Facts · Math
Claude Opus 5 is the stronger all-rounder.Gemini 3.7 Flash is cheaper and better at images and charts.
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 software04Claude Opus 54 of 5 tests · 1 tie
- ReasoningHard problems that need careful thinking14Claude Opus 54 of 5 tests
- AgentsCarrying out multi-step tasks on its own03Claude Opus 53 of 3 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 video10Gemini 3.7 Flash1 of 3 tests · 2 ties
- Long documentsFinding answers in very long texts10Gemini 3.7 Flash1 of 1 test
- Following instructionsDoing exactly what it is asked10Gemini 3.7 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 3.7 Flash costs 85% 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 Opus 5 pulls ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+36.6points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+35.4points ahead
- Real work tasks from 44 professionsGDPVal+16.6points ahead
Where Gemini 3.7 Flash pulls ahead
- Follows detailed instructions exactlyLiveBench · Instruction Following+16.1points ahead
- Short factual questions, answered correctlySimpleQA Verified+9.3points ahead
- Reasoning about charts from research papersCharXiv (RQ)+5points 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
- LMArena · WebDevClaude Opus 5 by 100 rating points15921692+100 rating
- LiveBench · Agentic CodingClaude Opus 5 by 6.958.365.2+6.9
- Terminal-Bench 2.1Claude Opus 5 by 3.385.889.1+3.3
- LiveBench · CodingClaude Opus 5 by 2.678.981.5+2.6
- SciCodetie57.256.4tie
AgentsClaude Opus 5
- Terminal-Bench 4.0Claude Opus 5 by 35.413.649+35.4
- GDPValClaude Opus 5 by 16.644.661.2+16.6
- τ-Bench V3 · BankingClaude Opus 5 by 9.332.842.1+9.3
ReasoningClaude Opus 5
- CritPtClaude Opus 5 by 14.814.329.1+14.8
- Humanity's Last ExamClaude Opus 5 by 747.954.9+7
- ARC-AGI-2Claude Opus 5 by 5.884.690.4+5.8
- LiveBench · ReasoningClaude Opus 5 by 3.487.891.2+3.4
- GPQA DiamondGemini 3.7 Flash by 1.394.593.2+1.3
FactsClaude Opus 5
- SimpleQA VerifiedGemini 3.7 Flash by 9.369.259.9+9.3
- AA-Omniscience · AccuracyClaude Opus 5 by 5.655.360.9+5.6
- AA-Omniscience · Non-hallucinationClaude Opus 5 by 3.735.539.2+3.7
Images and chartsGemini 3.7 Flash
- CharXiv (RQ)Gemini 3.7 Flash by 588.783.7+5
- MMMU-Protie85.584.7tie
- LMArena · Visiontie13151321tie
MathClaude Opus 5
- FrontierMath Tier 4Claude Opus 5 by 36.636.673.2+36.6
- FrontierMath Tiers 1-3 (v2)Claude Opus 5 by 1471.685.6+14
- LiveBench · MathematicsClaude Opus 5 by 2.293.595.7+2.2
Following instructionsGemini 3.7 Flash
- LiveBench · Instruction FollowingGemini 3.7 Flash by 16.179.963.8+16.1
Other results18 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 Opus 5 by 51.53485.5+51.5
- Terminal-Bench 4.0Claude Opus 5 by 40.611.251.8+40.6
- GDPval-AA v2 EloClaude Opus 5 by 342 rating points14821824+342 rating
- GDPval-AA v2Claude Opus 5 by 299 rating points15251824+299 rating
- OSWorld 2.0 (partial)Claude Opus 5 by 24.850.675.4+24.8
- OSWorld 2.0Claude Opus 5 by 22.747.970.6+22.7
- AA Agentic IndexClaude Opus 5 by 19.836.456.2+19.8
- AA IntelligenceClaude Opus 5 by 11.739.150.8+11.7
- AA-OmniscienceClaude Opus 5 by 10.626.537.1+10.6
- LVBenchGemini 3.7 Flash by 1085.475.4+10
- livebench_data_analysisClaude Opus 5 by 6.66874.5+6.6
- Agents' Last ExamClaude Opus 5 by 5.326.331.6+5.3
- DeepSWE 1.1Claude Opus 5 by 3.565.368.8+3.5
- livebench_languageClaude Opus 5 by 3.285.588.7+3.2
- GDP.PDF (All pass rate)Claude Opus 5 by 33437+3
- ARC-AGI-1Claude Opus 5 by 295.597.5+2
- Artificial Analysis Coding IndexClaude Opus 5 by 1.976.178+1.9
- HLE-Verifiedtie53.654.4tie
Questions people ask
Which is better, Gemini 3.7 Flash or Claude Opus 5?
Claude Opus 5 wins five of the eight areas we test: coding, agents, reasoning, facts and math. Gemini 3.7 Flash wins images and charts, long documents and following instructions, and costs 85% less.
Which is better for coding?
Claude Opus 5. It wins 4 of the 5 coding tests both models report; Gemini 3.7 Flash wins none, and 1 is a tie.
Which is cheaper?
Gemini 3.7 Flash costs $0.75 per million input tokens and $3.75 per million output tokens; Claude Opus 5 costs $5.00 and $25.00. That makes Gemini 3.7 Flash about 85% 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 24 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 18 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.