Claude Fable 5 vs Qwen3.8 Flash Next
Wins 5 of 8 areas
Coding · Reasoning · Images and charts · Math · Long documents
Wins 1 of 8 areas
Following instructions
Claude Fable 5 is the stronger all-rounder.Qwen3.8 Flash Next is cheaper and better at following instructions.
Both rank among the ten best models we track in coding.
Scores updated · 40 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 software51Claude Fable 55 of 8 tests · 2 ties
- ReasoningHard problems that need careful thinking30Claude Fable 53 of 4 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video10Claude Fable 51 of 1 test
- MathCompetition and research-level math10Claude Fable 51 of 1 test
- Long documentsFinding answers in very long texts10Claude Fable 51 of 1 test
- Following instructionsDoing exactly what it is asked02Qwen3.8 Flash Next2 of 2 tests
- AgentsCarrying out multi-step tasks on its own22Even2 each · 1 tie
- FactsGetting facts right instead of making them up11Even1 each
Images and charts, math and long documents 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.
Qwen3.8 Flash Next costs 99% 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
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+40.9points ahead
- Completes tasks by operating a computer desktopOSWorld-Verified+29.2points ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+17.5points ahead
Where Qwen3.8 Flash Next pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+18.3points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+17.8points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+7.3points ahead
Every test, side by side
All 40 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Fable 5
- SWE-bench ProClaude Fable 5 by 17.58062.5+17.5
- SWE-bench VerifiedClaude Fable 5 by 16.39578.7+16.3
- LiveBench · CodingClaude Fable 5 by 13.48672.5+13.4
- SciCodeClaude Fable 5 by 10.46150.6+10.4
- SWE-bench MultilingualClaude Fable 5 by 5.686.681+5.6
- Terminal-Bench 2.1Qwen3.8 Flash Next by 1.584.686.1+1.5
- LiveBench · Agentic Codingtie62.261.6tie
- LMArena · WebDevtie16251630tie
AgentsEven
- OSWorld-VerifiedClaude Fable 5 by 29.28555.8+29.2
- Terminal-Bench 4.0Claude Fable 5 by 17.142.425.3+17.1
- τ-Bench V3 · BankingQwen3.8 Flash Next by 7.338.145.4+7.3
- BrowseCompQwen3.8 Flash Next by 1.687.489+1.6
- GDPValtie55.556.4tie
ReasoningClaude Fable 5
- CritPtClaude Fable 5 by 17.528.611.1+17.5
- Humanity's Last ExamClaude Fable 5 by 17.555.538+17.5
- LiveBench · ReasoningClaude Fable 5 by 2.389.787.4+2.3
- GPQA Diamondtie92.692.3tie
FactsEven
- AA-Omniscience · AccuracyClaude Fable 5 by 40.965.324.5+40.9
- AA-Omniscience · Non-hallucinationQwen3.8 Flash Next by 18.336.454.7+18.3
Images and chartsClaude Fable 5
- MMMU-ProClaude Fable 5 by 4.484.279.8+4.4
Following instructionsQwen3.8 Flash Next
- IFBenchQwen3.8 Flash Next by 17.863.581.3+17.8
- LiveBench · Instruction FollowingQwen3.8 Flash Next by 1.375.877.1+1.3
Other results16 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 5343.3-9.7+53
- OSWorld 2.0Claude Fable 5 by 46.766.119.4+46.7
- Agents' Last ExamQwen3.8 Flash Next by 25.525.751.2+25.5
- OSWorld 2.0 (partial)Claude Fable 5 by 20.672.952.3+20.6
- τ³-Bench BankingQwen3.8 Flash Next by 17.726.844.5+17.7
- OSWorld 2.0 (strict)Claude Fable 5 by 16.736.119.4+16.7
- GDPval-AA v2Claude Fable 5 by 162 rating points17231561+162 rating
- livebench_languageClaude Fable 5 by 16.190.774.6+16.1
- ToolathlonQwen3.8 Flash Next by 11.861.773.5+11.8
- DeepSWE 1.1Claude Fable 5 by 11.37058.7+11.3
- AA IntelligenceClaude Fable 5 by 9.849.639.8+9.8
- livebench_data_analysisClaude Fable 5 by 6.380.574.2+6.3
- AA Agentic IndexQwen3.8 Flash Next by 5.45156.4+5.4
- Toolathlon VerifiedClaude Fable 5 by 4.477.973.5+4.4
- Artificial Analysis Coding IndexClaude Fable 5 by 3.476.573.1+3.4
- JobBenchClaude Fable 5 by 1.757.455.7+1.7
Questions people ask
Which is better, Claude Fable 5 or Qwen3.8 Flash Next?
Claude Fable 5 wins five of the eight areas we test: coding, reasoning, images and charts, math and long documents. Qwen3.8 Flash Next wins following instructions, and costs 99% less. They are level on agents and facts.
Which is better for coding?
Claude Fable 5. It wins 5 of the 8 coding tests both models report; Qwen3.8 Flash Next wins 1, and 2 are ties.
Which is cheaper?
Claude Fable 5 costs $10.00 per million input tokens and $50.00 per million output tokens; Qwen3.8 Flash Next costs $0.15 and $0.47. That makes Qwen3.8 Flash Next about 99% cheaper for the same work.
How do you compare the two?
We use the 40 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 16 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.