Claude Opus 4.8 vs Gemini 3.5 Flash Lite
Wins 7 of 8 areas
Coding · Agents · Reasoning · Images and charts · Math · Long documents · Following instructions
Wins 0 of 8 areas
—
Claude Opus 4.8 is the stronger all-rounder.Gemini 3.5 Flash Lite is cheaper.
Scores updated · 37 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 software70Claude Opus 4.87 of 7 tests
- ReasoningHard problems that need careful thinking50Claude Opus 4.85 of 5 tests
- MathCompetition and research-level math50Claude Opus 4.85 of 5 tests
- AgentsCarrying out multi-step tasks on its own40Claude Opus 4.84 of 4 tests
- Images and chartsUnderstanding pictures, charts and video20Claude Opus 4.82 of 2 tests
- Long documentsFinding answers in very long texts10Claude Opus 4.81 of 1 test
- Following instructionsDoing exactly what it is asked10Claude Opus 4.81 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
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 Lite costs 91% 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 4.8 pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+61.8points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+54points ahead
- Harvard-MIT high-school math contest problemsHMMT Feb. 2026+31.9points ahead
Where Gemini 3.5 Flash Lite pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+4.9points ahead
Every test, side by side
All 37 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4.8
- Terminal-Bench 2.1Claude Opus 4.8 by 3184.653.6+31
- SWE-bench ProClaude Opus 4.8 by 1569.254.2+15
- SWE-bench VerifiedClaude Opus 4.8 by 13.688.675+13.6
- SciCodeClaude Opus 4.8 by 13.154.441.3+13.1
- LMArena · WebDevClaude Opus 4.8 by 116 rating points15561440+116 rating
- LiveBench · CodingClaude Opus 4.8 by 5.781.876.1+5.7
- LiveBench · Agentic CodingClaude Opus 4.8 by 5.250.545.3+5.2
AgentsClaude Opus 4.8
- GDPValClaude Opus 4.8 by 23.547.824.3+23.5
- Terminal-Bench 4.0Claude Opus 4.8 by 20.721.71+20.7
- τ-Bench V3 · BankingClaude Opus 4.8 by 16.734.217.5+16.7
- OSWorld-VerifiedClaude Opus 4.8 by 9.483.474+9.4
ReasoningClaude Opus 4.8
- ARC-AGI-2Claude Opus 4.8 by 61.872.110.3+61.8
- Humanity's Last ExamClaude Opus 4.8 by 29.948.718.8+29.9
- LiveBench · ReasoningClaude Opus 4.8 by 2989.260.2+29
- CritPtClaude Opus 4.8 by 20.920.90+20.9
- GPQA DiamondClaude Opus 4.8 by 8.29283.8+8.2
FactsEven
- AA-Omniscience · AccuracyClaude Opus 4.8 by 19.348.829.5+19.3
- AA-Omniscience · Non-hallucinationGemini 3.5 Flash Lite by 4.960.765.6+4.9
Images and chartsClaude Opus 4.8
- CharXiv (RQ)Claude Opus 4.8 by 13.489.976.5+13.4
- LMArena · VisionClaude Opus 4.8 by 29 rating points12951266+29 rating
MathClaude Opus 4.8
- FrontierMath Tier 4Claude Opus 4.8 by 56.156.10+56.1
- FrontierMath Tiers 1-3 (v2)Claude Opus 4.8 by 548026+54
- HMMT Feb. 2026Claude Opus 4.8 by 31.995.563.6+31.9
- LiveBench · MathematicsClaude Opus 4.8 by 20.694.373.7+20.6
- AIME 2026Claude Opus 4.8 by 17.810082.2+17.8
Following instructionsClaude Opus 4.8
- LiveBench · Instruction FollowingClaude Opus 4.8 by 4.87267.2+4.8
Other results10 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 4.8 by 453 rating points15931140+453 rating
- ARC-AGI-1Claude Opus 4.8 by 3992.553.5+39
- AA Agentic IndexClaude Opus 4.8 by 26.742.615.9+26.7
- Artificial Analysis Coding IndexClaude Opus 4.8 by 2574.349.3+25
- AA-OmniscienceClaude Opus 4.8 by 23.628.85.2+23.6
- Toolathlon VerifiedClaude Opus 4.8 by 22.879.957.1+22.8
- AA IntelligenceClaude Opus 4.8 by 19.641.822.2+19.6
- HLE (with tools)Claude Opus 4.8 by 15.457.942.5+15.4
- livebench_data_analysisClaude Opus 4.8 by 12.76653.3+12.7
- livebench_languageClaude Opus 4.8 by 7.979.771.8+7.9
Questions people ask
Which is better, Claude Opus 4.8 or Gemini 3.5 Flash Lite?
Claude Opus 4.8 wins seven of the eight areas we test: coding, agents, reasoning, images and charts, math, long documents and following instructions. Gemini 3.5 Flash Lite wins none, but costs 91% less. They are level on facts.
Which is better for coding?
Claude Opus 4.8. It wins 7 of the 7 coding tests both models report; Gemini 3.5 Flash Lite wins none.
Which is cheaper?
Claude Opus 4.8 costs $5.00 per million input tokens and $25.00 per million output tokens; Gemini 3.5 Flash Lite costs $0.30 and $2.50. That makes Gemini 3.5 Flash Lite about 91% cheaper for the same work.
How do you compare the two?
We use the 37 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 10 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.