Claude Fable 5.1 vs GPT-5.6 Luna
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.GPT-5.6 Luna is cheaper.
Scores updated · 43 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 thinking60Claude Fable 5.16 of 6 tests
- AgentsCarrying out multi-step tasks on its own40Claude Fable 5.14 of 4 tests
- FactsGetting facts right instead of making them up30Claude Fable 5.13 of 3 tests
- MathCompetition and research-level math30Claude Fable 5.13 of 3 tests
- Images and chartsUnderstanding pictures, charts and video10Claude 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, 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.
GPT-5.6 Luna costs 98% 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+40.4points ahead
- Common-sense trick questionsSimpleBench+39.8points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+30.4points ahead
Where GPT-5.6 Luna pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 43 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Fable 5.1
- LMArena · WebDevClaude Fable 5.1 by 222 rating points17411519+222 rating
- SWE-bench ProClaude Fable 5.1 by 18.581.262.7+18.5
- LiveBench · Agentic CodingClaude Fable 5.1 by 17.766.148.4+17.7
- Terminal-Bench 2.1Claude Fable 5.1 by 10.591.480.9+10.5
- SciCodeClaude Fable 5.1 by 9.563.153.6+9.5
- LiveBench · CodingClaude Fable 5.1 by 3.586.482.9+3.5
AgentsClaude Fable 5.1
- Terminal-Bench 4.0Claude Fable 5.1 by 40.45211.6+40.4
- τ-Bench V3 · BankingClaude Fable 5.1 by 16.147.231.1+16.1
- GDPValClaude Fable 5.1 by 14.762.748+14.7
- AA IT-Bench SREClaude Fable 5.1 by 9.249.540.3+9.2
ReasoningClaude Fable 5.1
- SimpleBenchClaude Fable 5.1 by 39.886.646.8+39.8
- ARC-AGI-2Claude Fable 5.1 by 30.49059.6+30.4
- Humanity's Last ExamClaude Fable 5.1 by 19.659.139.5+19.6
- CritPtClaude Fable 5.1 by 9.129.720.6+9.1
- LiveBench · ReasoningClaude Fable 5.1 by 6.191.785.6+6.1
- GPQA DiamondClaude Fable 5.1 by 2.693.791.1+2.6
FactsClaude Fable 5.1
- SimpleQA VerifiedClaude Fable 5.1 by 29.870.841+29.8
- AA-Omniscience · AccuracyClaude Fable 5.1 by 24.567.242.7+24.5
- AA-Omniscience · Non-hallucinationClaude Fable 5.1 by 2027.47.4+20
Images and chartsClaude Fable 5.1
- LMArena · VisionClaude Fable 5.1 by 60 rating points13181258+60 rating
MathClaude Fable 5.1
- FrontierMath Tier 4Claude Fable 5.1 by 29.387.858.5+29.3
- LiveBench · MathematicsClaude Fable 5.1 by 9.89787.2+9.8
- FrontierMath Tiers 1-3 (v2)Claude Fable 5.1 by 8.190.282.1+8.1
Following instructionsClaude Fable 5.1
- LiveBench · Instruction FollowingClaude Fable 5.1 by 12.97360.1+12.9
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.
- GDP (Surge AI)Claude Fable 5.1 by 62.485.122.7+62.4
- AA-OmniscienceClaude Fable 5.1 by 53.843.5-10.3+53.8
- Terminal-Bench 4.0Claude Fable 5.1 by 38.555.817.3+38.5
- GDPval-AA v2Claude Fable 5.1 by 323 rating points18531530+323 rating
- OSWorld 2.0Claude Fable 5.1 by 32.377.945.6+32.3
- GDPval-AA v2 EloClaude Fable 5.1 by 251 rating points18351584+251 rating
- livebench_languageClaude Fable 5.1 by 16.989.572.6+16.9
- AA IntelligenceClaude Fable 5.1 by 16.153.437.3+16.1
- HLE (with tools)Claude Fable 5.1 by 16.16548.9+16.1
- AA Agentic IndexClaude Fable 5.1 by 15.35842.7+15.3
- Artificial Analysis Coding IndexClaude Fable 5.1 by 10.281.671.4+10.2
- Toolathlon VerifiedClaude Fable 5.1 by 9.977.867.9+9.9
- ARC-AGI-1Claude Fable 5.1 by 6.897.590.7+6.8
- HealthBench ProfessionalClaude Fable 5.1 by 6.462.155.7+6.4
- HealthBench Professional length-adjustedClaude Fable 5.1 by 6.462.155.7+6.4
- HealthBench length-adjustedClaude Fable 5.1 by 4.26055.8+4.2
- livebench_data_analysisClaude Fable 5.1 by 2.380.378+2.3
- DeepSWE 1.1tie67.467tie
Questions people ask
Which is better, Claude Fable 5.1 or GPT-5.6 Luna?
Claude Fable 5.1 wins all eight areas we test: coding, agents, reasoning, facts, images and charts, math, long documents and following instructions. GPT-5.6 Luna wins none, but costs 98% less.
Which is better for coding?
Claude Fable 5.1. It wins 6 of the 6 coding tests both models report; GPT-5.6 Luna wins none.
Which is cheaper?
Claude Fable 5.1 costs $10.00 per million input tokens and $50.00 per million output tokens; GPT-5.6 Luna costs $0.20 and $1.20. That makes GPT-5.6 Luna about 98% cheaper for the same work.
How do you compare the two?
We use the 43 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 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.