Claude Fable 5 vs Claude Opus 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 is the stronger all-rounder.Claude Opus 4.6 is cheaper.
Scores updated · 51 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 software80Claude Fable 58 of 8 tests
- ReasoningHard problems that need careful thinking60Claude Fable 56 of 6 tests
- AgentsCarrying out multi-step tasks on its own40Claude Fable 54 of 5 tests · 1 tie
- MathCompetition and research-level math30Claude Fable 53 of 3 tests
- FactsGetting facts right instead of making them up20Claude Fable 52 of 3 tests · 1 tie
- Following instructionsDoing exactly what it is asked20Claude Fable 52 of 2 tests
- Images and chartsUnderstanding pictures, charts and video10Claude Fable 51 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts10Claude Fable 51 of 1 test
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.
Claude Opus 4.6 costs 50% 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 pulls ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+63.4points ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+26.6points ahead
- Short factual questions, answered correctlySimpleQA Verified+23.7points ahead
Where Claude Opus 4.6 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 51 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 26.68053.4+26.6
- Terminal-Bench HardClaude Fable 5 by 16.762.946.2+16.7
- SWE-bench VerifiedClaude Fable 5 by 14.29580.8+14.2
- LiveBench · Agentic CodingClaude Fable 5 by 13.262.249+13.2
- SciCodeClaude Fable 5 by 9.16151.9+9.1
- SWE-bench MultilingualClaude Fable 5 by 8.886.677.8+8.8
- LiveBench · CodingClaude Fable 5 by 7.88678.2+7.8
- LMArena · WebDevClaude Fable 5 by 78 rating points16241546+78 rating
AgentsClaude Fable 5
- MCP AtlasClaude Fable 5 by 2284.762.7+22
- OSWorld-VerifiedClaude Fable 5 by 12.38572.7+12.3
- AA ApexAgentsClaude Fable 5 by 10.343.333+10.3
- BrowseCompClaude Fable 5 by 3.487.484+3.4
- GDPValtie55.655.9tie
ReasoningClaude Fable 5
- ARC-AGI-2Claude Fable 5 by 20.489.268.8+20.4
- CritPtClaude Fable 5 by 1628.612.6+16
- Humanity's Last ExamClaude Fable 5 by 15.655.539.9+15.6
- SimpleBenchClaude Fable 5 by 14.381.967.6+14.3
- GPQA DiamondClaude Fable 5 by 392.689.6+3
- LiveBench · ReasoningClaude Fable 5 by 189.788.7+1
FactsClaude Fable 5
- SimpleQA VerifiedClaude Fable 5 by 23.770.747+23.7
- AA-Omniscience · AccuracyClaude Fable 5 by 18.465.347+18.4
- AA-Omniscience · Non-hallucinationtie36.437.2tie
Images and chartsClaude Fable 5
- MMMU-ProClaude Fable 5 by 8.884.275.4+8.8
- LMArena · Visiontie13251316tie
MathClaude Fable 5
- FrontierMath Tier 4Claude Fable 5 by 63.490.226.8+63.4
- FrontierMath Tiers 1-3 (v2)Claude Fable 5 by 218766+21
- LiveBench · MathematicsClaude Fable 5 by 6.79689.3+6.7
Following instructionsClaude Fable 5
- LiveBench · Instruction FollowingClaude Fable 5 by 12.575.863.3+12.5
- IFBenchClaude Fable 5 by 10.463.553.1+10.4
Other results21 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 (Elo)Claude Fable 5 by 313 rating points19321619+313 rating
- AA-OmniscienceClaude Fable 5 by 29.643.313.7+29.6
- Artificial Analysis Coding IndexClaude Fable 5 by 28.476.548.1+28.4
- SWE-bench MultimodalClaude Fable 5 by 2754.127.1+27
- JobBenchClaude Fable 5 by 20.857.436.6+20.8
- HiL-Bench (Tools-allowed)Claude Fable 5 by 1856.338.3+18
- AA IntelligenceClaude Fable 5 by 17.749.631.9+17.7
- AA Agentic IndexClaude Opus 4.6 by 16.65167.6+16.6
- livebench_data_analysisClaude Fable 5 by 10.680.569.9+10.6
- HLE (with tools)Claude Fable 5 by 10.563.853.3+10.5
- Legal Agent BenchmarkClaude Fable 5 by 9.113.34.2+9.1
- Toolathlon Pass@∞Claude Fable 5 by 8.455.647.2+8.4
- livebench_languageClaude Fable 5 by 7.490.783.3+7.4
- τ²-Bench Telecom (AA run)Claude Fable 5 by 6.498.592.1+6.4
- ARC-AGI-1Claude Fable 5 by 5.598.593+5.5
- ToolathlonClaude Fable 5 by 4.961.756.8+4.9
- charxiv_rq_with_pythonClaude Fable 5 by 4.789.484.7+4.7
- DeepSearchQA (F1)Claude Fable 5 by 2.994.291.3+2.9
- Toolathlon Avg turnsClaude Fable 5 by 2.919.816.9+2.9
- LiveBenchClaude Fable 5 by 278.376.3+2
- OfficeQA Protie57.957.1tie
Questions people ask
Which is better, Claude Fable 5 or Claude Opus 4.6?
Claude Fable 5 wins all eight areas we test: coding, agents, reasoning, facts, images and charts, math, long documents and following instructions. Claude Opus 4.6 wins none, but costs 50% less.
Which is better for coding?
Claude Fable 5. It wins 8 of the 8 coding tests both models report; Claude Opus 4.6 wins none.
Which is cheaper?
Claude Fable 5 costs $10.00 per million input tokens and $50.00 per million output tokens; Claude Opus 4.6 costs $5.00 and $25.00. That makes Claude Opus 4.6 about 50% cheaper for the same work.
How do you compare the two?
We use the 51 benchmark tests both models have published scores on. The verdict counts the 30 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 21 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.