Claude Fable 5 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 Fable 5 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 Fable 57 of 7 tests
- ReasoningHard problems that need careful thinking50Claude Fable 55 of 5 tests
- AgentsCarrying out multi-step tasks on its own40Claude Fable 54 of 4 tests
- MathCompetition and research-level math30Claude Fable 53 of 3 tests
- Images and chartsUnderstanding pictures, charts and video20Claude Fable 52 of 2 tests
- Long documentsFinding answers in very long texts10Claude Fable 51 of 1 test
- Following instructionsDoing exactly what it is asked10Claude Fable 51 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 95% 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 Fable 5 pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+78.9points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+61points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+41.4points ahead
Where Gemini 3.5 Flash Lite pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+29.2points 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 Fable 5
- Terminal-Bench 2.1Claude Fable 5 by 3184.653.6+31
- SWE-bench ProClaude Fable 5 by 25.88054.2+25.8
- SWE-bench VerifiedClaude Fable 5 by 209575+20
- SciCodeClaude Fable 5 by 19.76141.3+19.7
- LMArena · WebDevClaude Fable 5 by 184 rating points16241440+184 rating
- LiveBench · Agentic CodingClaude Fable 5 by 16.962.245.3+16.9
- LiveBench · CodingClaude Fable 5 by 9.98676.1+9.9
AgentsClaude Fable 5
- Terminal-Bench 4.0Claude Fable 5 by 41.442.41+41.4
- GDPValClaude Fable 5 by 31.355.624.3+31.3
- τ-Bench V3 · BankingClaude Fable 5 by 20.638.117.5+20.6
- OSWorld-VerifiedClaude Fable 5 by 118574+11
ReasoningClaude Fable 5
- ARC-AGI-2Claude Fable 5 by 78.989.210.3+78.9
- Humanity's Last ExamClaude Fable 5 by 36.755.518.8+36.7
- LiveBench · ReasoningClaude Fable 5 by 29.589.760.2+29.5
- CritPtClaude Fable 5 by 28.628.60+28.6
- GPQA DiamondClaude Fable 5 by 8.892.683.8+8.8
FactsEven
- AA-Omniscience · AccuracyClaude Fable 5 by 35.965.329.5+35.9
- AA-Omniscience · Non-hallucinationGemini 3.5 Flash Lite by 29.236.465.6+29.2
Images and chartsClaude Fable 5
- LMArena · VisionClaude Fable 5 by 59 rating points13251266+59 rating
- MMMU-ProClaude Fable 5 by 5.284.279+5.2
MathClaude Fable 5
- FrontierMath Tier 4Claude Fable 5 by 90.290.20+90.2
- FrontierMath Tiers 1-3 (v2)Claude Fable 5 by 618726+61
- LiveBench · MathematicsClaude Fable 5 by 22.39673.7+22.3
Following instructionsClaude Fable 5
- LiveBench · Instruction FollowingClaude Fable 5 by 8.675.867.2+8.6
Other results12 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 Fable 5 by 583 rating points17231140+583 rating
- ARC-AGI-1Claude Fable 5 by 4598.553.5+45
- AA-OmniscienceClaude Fable 5 by 38.143.35.2+38.1
- AA Agentic IndexClaude Fable 5 by 35.15115.9+35.1
- AA IntelligenceClaude Fable 5 by 27.449.622.2+27.4
- Artificial Analysis Coding IndexClaude Fable 5 by 27.276.549.3+27.2
- livebench_data_analysisClaude Fable 5 by 27.280.553.3+27.2
- SWEBench Pro PublicClaude Fable 5 by 25.88054.2+25.8
- HLE (with tools)Claude Fable 5 by 21.363.842.5+21.3
- Toolathlon VerifiedClaude Fable 5 by 20.877.957.1+20.8
- livebench_languageClaude Fable 5 by 18.990.771.8+18.9
- τ³-Bench BankingClaude Fable 5 by 10.326.816.5+10.3
Questions people ask
Which is better, Claude Fable 5 or Gemini 3.5 Flash Lite?
Claude Fable 5 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 95% less. They are level on facts.
Which is better for coding?
Claude Fable 5. It wins 7 of the 7 coding tests both models report; Gemini 3.5 Flash Lite wins none.
Which is cheaper?
Claude Fable 5 costs $10.00 per million input tokens and $50.00 per million output tokens; Gemini 3.5 Flash Lite costs $0.30 and $2.50. That makes Gemini 3.5 Flash Lite about 95% 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 25 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 12 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.