Claude Fable 5 vs Gemini 3.8 Flash
Wins 6 of 8 areas
Coding · Agents · Reasoning · Facts · Math · Long documents
Wins 1 of 8 areas
Following instructions
Claude Fable 5 is the stronger all-rounder.Gemini 3.8 Flash is cheaper and better at following instructions.
Both rank among the ten best models we track in reasoning and facts.
Scores updated · 39 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 software41Claude Fable 54 of 5 tests
- MathCompetition and research-level math30Claude Fable 53 of 3 tests
- ReasoningHard problems that need careful thinking21Claude Fable 52 of 6 tests · 3 ties
- AgentsCarrying out multi-step tasks on its own21Claude Fable 52 of 3 tests
- FactsGetting facts right instead of making them up21Claude Fable 52 of 3 tests
- Long documentsFinding answers in very long texts10Claude Fable 51 of 1 test
- Following instructionsDoing exactly what it is asked01Gemini 3.8 Flash1 of 1 test
- Images and chartsUnderstanding pictures, charts and video11Even1 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 3.8 Flash costs 93% 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 Fable 5 pulls ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+68.2points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+22.7points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+18.6points ahead
Where Gemini 3.8 Flash pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+8.4points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+6.8points ahead
- Follows detailed instructions exactlyLiveBench · Instruction Following+5.6points ahead
Every test, side by side
All 39 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Fable 5
- LiveBench · CodingClaude Fable 5 by 13.58672.5+13.5
- LiveBench · Agentic CodingClaude Fable 5 by 862.254.2+8
- SciCodeClaude Fable 5 by 4.46156.6+4.4
- LMArena · WebDevClaude Fable 5 by 39 rating points16251586+39 rating
- Terminal-Bench 2.1Gemini 3.8 Flash by 384.687.6+3
AgentsClaude Fable 5
- Terminal-Bench 4.0Claude Fable 5 by 22.742.419.7+22.7
- GDPValClaude Fable 5 by 8.755.546.8+8.7
- τ-Bench V3 · BankingGemini 3.8 Flash by 6.838.144.9+6.8
ReasoningClaude Fable 5
- CritPtClaude Fable 5 by 10.328.618.3+10.3
- Humanity's Last ExamClaude Fable 5 by 7.755.547.8+7.7
- GPQA DiamondGemini 3.8 Flash by 2.792.695.3+2.7
- SimpleBenchtie81.982.4tie
- LiveBench · Reasoningtie89.789.3tie
- ARC-AGI-2tie89.289.2tie
FactsClaude Fable 5
- AA-Omniscience · AccuracyClaude Fable 5 by 10.865.354.6+10.8
- AA-Omniscience · Non-hallucinationGemini 3.8 Flash by 8.436.444.8+8.4
- SimpleQA VerifiedClaude Fable 5 by 170.769.7+1
Images and chartsEven
- MMMU-ProGemini 3.8 Flash by 1.484.285.6+1.4
- LMArena · VisionClaude Fable 5 by 10 rating points13241314+10 rating
MathClaude Fable 5
- FrontierMath Tier 4Claude Fable 5 by 68.290.221.9+68.2
- FrontierMath Tiers 1-3 (v2)Claude Fable 5 by 18.68768.4+18.6
- LiveBench · MathematicsClaude Fable 5 by 4.49691.6+4.4
Following instructionsGemini 3.8 Flash
- LiveBench · Instruction FollowingGemini 3.8 Flash by 5.675.881.4+5.6
Other results15 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.
- livebench_data_analysisClaude Fable 5 by 26.580.554+26.5
- Terminal-Bench 4.0Claude Fable 5 by 25.444.519.1+25.4
- GDPval-AA v2Claude Fable 5 by 178 rating points17231545+178 rating
- GDPval-AA v2 EloClaude Fable 5 by 178 rating points17231545+178 rating
- HiL-Bench (Tools-allowed)Claude Fable 5 by 14.856.341.5+14.8
- OSWorld 2.0 (partial)Claude Fable 5 by 13.972.959+13.9
- AA-OmniscienceClaude Fable 5 by 13.743.329.6+13.7
- AA Agentic IndexClaude Fable 5 by 9.95141.1+9.9
- AA IntelligenceClaude Fable 5 by 8.749.640.9+8.7
- OSWorld 2.0Claude Fable 5 by 7.166.159+7.1
- GDP (Surge AI)Gemini 3.8 Flash by 5.229.835+5.2
- DeepSWE 1.1Gemini 3.8 Flash by 3.77073.7+3.7
- livebench_languageClaude Fable 5 by 2.990.787.8+2.9
- Artificial Analysis Coding Indextie76.576.3tie
- ARC-AGI-1tie98.598.5tie
Questions people ask
Which is better, Claude Fable 5 or Gemini 3.8 Flash?
Claude Fable 5 wins six of the eight areas we test: coding, agents, reasoning, facts, math and long documents. Gemini 3.8 Flash wins following instructions, and costs 93% less. They are level on images and charts.
Which is better for coding?
Claude Fable 5. It wins 4 of the 5 coding tests both models report; Gemini 3.8 Flash wins 1.
Which is cheaper?
Claude Fable 5 costs $10.00 per million input tokens and $50.00 per million output tokens; Gemini 3.8 Flash costs $0.75 and $3.75. That makes Gemini 3.8 Flash about 93% cheaper for the same work.
How do you compare the two?
We use the 39 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 15 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.