Claude Fable 5 vs Qwen3.8 Max Preview
Wins 5 of 8 areas
Reasoning · Facts · Images and charts · Math · Long documents
Wins 1 of 8 areas
Agents
Claude Fable 5 is the stronger all-rounder.Qwen3.8 Max Preview is cheaper and better at agents.
Both rank among the ten best models we track in agents.
Scores updated · 44 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.
- ReasoningHard problems that need careful thinking30Claude Fable 53 of 4 tests · 1 tie
- MathCompetition and research-level math30Claude Fable 53 of 3 tests
- Images and chartsUnderstanding pictures, charts and video20Claude Fable 52 of 2 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
- AgentsCarrying out multi-step tasks on its own13Qwen3.8 Max Preview3 of 5 tests · 1 tie
- CodingWriting and fixing software33Even3 each
- Following instructionsDoing exactly what it is asked11Even1 each
Long documents rests on a single test.
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.
Qwen3.8 Max Preview costs 87% 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+43.9points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+33.7points ahead
- Short factual questions, answered correctlySimpleQA Verified+23.4points ahead
Where Qwen3.8 Max Preview pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+34.8points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+19.3points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+9.7points ahead
Every test, side by side
All 44 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingEven
- LiveBench · CodingClaude Fable 5 by 13.18672.9+13.1
- SWE-bench ProClaude Fable 5 by 12.38067.7+12.3
- SciCodeClaude Fable 5 by 8.96152.1+8.9
- LMArena · WebDevQwen3.8 Max Preview by 47 rating points16251672+47 rating
- Terminal-Bench 2.1Qwen3.8 Max Preview by 4.284.688.8+4.2
- LiveBench · Agentic CodingQwen3.8 Max Preview by 2.562.264.7+2.5
AgentsQwen3.8 Max Preview
- τ-Bench V3 · BankingQwen3.8 Max Preview by 9.738.147.8+9.7
- Terminal-Bench 4.0Claude Fable 5 by 3.542.438.9+3.5
- GDPValQwen3.8 Max Preview by 2.855.558.3+2.8
- OSWorld-VerifiedQwen3.8 Max Preview by 1.18586.1+1.1
- AA ApexAgentstie43.342.4tie
ReasoningClaude Fable 5
- Humanity's Last ExamClaude Fable 5 by 12.455.543.1+12.4
- CritPtClaude Fable 5 by 10.928.617.7+10.9
- LiveBench · ReasoningClaude Fable 5 by 1.589.788.2+1.5
- GPQA Diamondtie92.692.8tie
FactsClaude Fable 5
- AA-Omniscience · Non-hallucinationQwen3.8 Max Preview by 34.836.471.2+34.8
- AA-Omniscience · AccuracyClaude Fable 5 by 33.765.331.7+33.7
- SimpleQA VerifiedClaude Fable 5 by 23.470.747.3+23.4
Images and chartsClaude Fable 5
- MMMU-ProClaude Fable 5 by 1.484.282.8+1.4
- LMArena · VisionClaude Fable 5 by 10 rating points13241314+10 rating
MathClaude Fable 5
- FrontierMath Tier 4Claude Fable 5 by 43.990.246.3+43.9
- FrontierMath Tiers 1-3 (v2)Claude Fable 5 by 12.38774.7+12.3
- LiveBench · MathematicsClaude Fable 5 by 4.79691.3+4.7
Following instructionsEven
- IFBenchQwen3.8 Max Preview by 19.363.582.8+19.3
- LiveBench · Instruction FollowingClaude Fable 5 by 1.775.874.1+1.7
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.
- AA-OmniscienceClaude Fable 5 by 31.343.312+31.3
- Agents' Last ExamQwen3.8 Max Preview by 26.725.752.4+26.7
- DeepSWEClaude Fable 5 by 13.47056.6+13.4
- DeepSWE 1.1Claude Fable 5 by 13.47056.6+13.4
- livebench_languageClaude Fable 5 by 1190.779.7+11
- ToolathlonQwen3.8 Max Preview by 10.861.772.5+10.8
- AndroidBenchClaude Fable 5 by 9.484.575.1+9.4
- MLS Bench Litelower is betterQwen3.8 Max Preview by 8.949.941+8.9
- HLE (with tools)Claude Fable 5 by 7.663.856.2+7.6
- Toolathlon VerifiedClaude Fable 5 by 5.477.972.5+5.4
- Artificial Analysis Coding IndexClaude Fable 5 by 4.776.571.8+4.7
- AA IntelligenceClaude Fable 5 by 4.249.645.4+4.2
- PaperBenchQwen3.8 Max Preview by 4.288.893+4.2
- JobBenchClaude Fable 5 by 457.453.4+4
- livebench_data_analysisClaude Fable 5 by 2.180.578.4+2.1
- GDPval-AA v2Qwen3.8 Max Preview by 16 rating points17231739+16 rating
- AA Agentic IndexClaude Fable 5 by 1.45149.6+1.4
- WideSearchtie81.281.9tie
Questions people ask
Which is better, Claude Fable 5 or Qwen3.8 Max Preview?
Claude Fable 5 wins five of the eight areas we test: reasoning, facts, images and charts, math and long documents. Qwen3.8 Max Preview wins agents, and costs 87% less. They are level on coding and following instructions.
Which is better for coding?
Neither. They win 3 coding tests each of the 6 both models report.
Which is cheaper?
Claude Fable 5 costs $10.00 per million input tokens and $50.00 per million output tokens; Qwen3.8 Max Preview costs $2.00 and $6.00. That makes Qwen3.8 Max Preview about 87% cheaper for the same work.
How do you compare the two?
We use the 44 benchmark tests both models have published scores on. The verdict counts the 26 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.