Claude Fable 5.1 vs Claude Sonnet 4.6
Wins 8 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents · Following instructions
Wins 0 of 8 areas
—
Claude Fable 5.1 is the stronger all-rounder.Claude Sonnet 4.6 is cheaper.
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 software60Claude Fable 5.16 of 6 tests
- ReasoningHard problems that need careful thinking50Claude Fable 5.15 of 5 tests
- AgentsCarrying out multi-step tasks on its own40Claude Fable 5.14 of 4 tests
- FactsGetting facts right instead of making them up21Claude Fable 5.12 of 3 tests
- Images and chartsUnderstanding pictures, charts and video10Claude Fable 5.11 of 1 test
- MathCompetition and research-level math10Claude Fable 5.11 of 1 test
- Long documentsFinding answers in very long texts10Claude Fable 5.11 of 1 test
- Following instructionsDoing exactly what it is asked10Claude Fable 5.11 of 1 test
Images and charts, math, 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.
Claude Sonnet 4.6 costs 70% 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 5.1 pulls ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+49points ahead
- Short factual questions, answered correctlySimpleQA Verified+38points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+31.7points ahead
Where Claude Sonnet 4.6 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+24.2points 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 5.1
- LiveBench · Agentic CodingClaude Fable 5.1 by 23.566.142.6+23.5
- SWE-bench ProClaude Fable 5.1 by 23.181.258.1+23.1
- LMArena · WebDevClaude Fable 5.1 by 218 rating points17411523+218 rating
- Terminal-Bench 2.1Claude Fable 5.1 by 20.291.471.2+20.2
- SciCodeClaude Fable 5.1 by 1363.150.1+13
- LiveBench · CodingClaude Fable 5.1 by 7.186.479.3+7.1
AgentsClaude Fable 5.1
- Terminal-Bench 4.0Claude Fable 5.1 by 49523+49
- GDPValClaude Fable 5.1 by 26.162.736.6+26.1
- τ-Bench V3 · BankingClaude Fable 5.1 by 12.847.234.4+12.8
- AA IT-Bench SREClaude Fable 5.1 by 9.749.539.8+9.7
ReasoningClaude Fable 5.1
- ARC-AGI-2Claude Fable 5.1 by 31.79058.3+31.7
- CritPtClaude Fable 5.1 by 26.629.73.1+26.6
- Humanity's Last ExamClaude Fable 5.1 by 25.559.133.6+25.5
- LiveBench · ReasoningClaude Fable 5.1 by 6.991.784.8+6.9
- GPQA DiamondClaude Fable 5.1 by 6.293.787.5+6.2
FactsClaude Fable 5.1
- SimpleQA VerifiedClaude Fable 5.1 by 3870.832.8+38
- AA-Omniscience · AccuracyClaude Fable 5.1 by 26.367.240.9+26.3
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.6 by 24.227.451.6+24.2
Images and chartsClaude Fable 5.1
- LMArena · VisionClaude Fable 5.1 by 36 rating points13181282+36 rating
Following instructionsClaude Fable 5.1
- LiveBench · Instruction FollowingClaude Fable 5.1 by 9.87363.2+9.8
Other results17 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 5.1 by 458 rating points18531395+458 rating
- DeepSWE 1.1Claude Fable 5.1 by 37.467.430+37.4
- AA-OmniscienceClaude Fable 5.1 by 31.343.512.2+31.3
- AA Agentic IndexClaude Fable 5.1 by 24.95833.1+24.9
- AA IntelligenceClaude Fable 5.1 by 23.353.430.1+23.3
- Artificial Analysis Coding IndexClaude Fable 5.1 by 18.681.663+18.6
- HLE (with tools)Claude Fable 5.1 by 18.26546.8+18.2
- HealthBench ProfessionalClaude Fable 5.1 by 17.962.144.2+17.9
- OfficeQA ProClaude Fable 5.1 by 15.66953.4+15.6
- livebench_languageClaude Fable 5.1 by 13.489.576.1+13.4
- ARC-AGI-1Claude Fable 5.1 by 11.597.586+11.5
- OfficeQAClaude Fable 5.1 by 11.580.268.7+11.5
- Legal Agent Benchmark (LAB) all-pass rateClaude Fable 5.1 by 11.119.18+11.1
- GDP (Surge AI)Claude Fable 5.1 by 6.585.178.6+6.5
- GDPval-AA (Elo)Claude Fable 5.1 by 59 rating points17351676+59 rating
- Legal Agent Benchmark (LAB) mean criterion-pass rateClaude Fable 5.1 by 2.390.888.5+2.3
- livebench_data_analysisClaude Fable 5.1 by 2.380.378+2.3
Questions people ask
Which is better, Claude Fable 5.1 or Claude Sonnet 4.6?
Claude Fable 5.1 wins all eight areas we test: coding, agents, reasoning, facts, images and charts, math, long documents and following instructions. Claude Sonnet 4.6 wins none, but costs 70% less.
Which is better for coding?
Claude Fable 5.1. It wins 6 of the 6 coding tests both models report; Claude Sonnet 4.6 wins none.
Which is cheaper?
Claude Fable 5.1 costs $10.00 per million input tokens and $50.00 per million output tokens; Claude Sonnet 4.6 costs $3.00 and $15.00. That makes Claude Sonnet 4.6 about 70% 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 22 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 17 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.