Claude Fable 5 vs Claude Sonnet 4.5
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 Sonnet 4.5 is cheaper.
Scores updated · 36 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 software70Claude Fable 57 of 7 tests
- AgentsCarrying out multi-step tasks on its own60Claude Fable 56 of 6 tests
- ReasoningHard problems that need careful thinking50Claude Fable 55 of 5 tests
- MathCompetition and research-level math20Claude Fable 52 of 2 tests
- FactsGetting facts right instead of making them up21Claude Fable 52 of 3 tests
- Images and chartsUnderstanding pictures, charts and video10Claude Fable 51 of 1 test
- Long documentsFinding answers in very long texts10Claude Fable 51 of 1 test
- Following instructionsDoing exactly what it is asked10Claude Fable 51 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.
Claude Sonnet 4.5 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 pulls ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+87.8points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+75.6points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+63.3points ahead
Where Claude Sonnet 4.5 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+14.5points ahead
Every test, side by side
All 36 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 36.48043.6+36.4
- Terminal-Bench 2.1Claude Fable 5 by 28.884.655.8+28.8
- Terminal-Bench HardClaude Fable 5 by 27.362.935.6+27.3
- LMArena · WebDevClaude Fable 5 by 230 rating points16241394+230 rating
- SWE-bench MultilingualClaude Fable 5 by 19.686.667+19.6
- SWE-bench VerifiedClaude Fable 5 by 17.89577.2+17.8
- SciCodeClaude Fable 5 by 15.36145.7+15.3
AgentsClaude Fable 5
- BrowseCompClaude Fable 5 by 63.387.424.1+63.3
- Terminal-Bench 4.0Claude Fable 5 by 42.442.40+42.4
- MCP AtlasClaude Fable 5 by 40.984.743.8+40.9
- GDPValClaude Fable 5 by 35.155.620.5+35.1
- OSWorld-VerifiedClaude Fable 5 by 23.68561.4+23.6
- τ-Bench V3 · BankingClaude Fable 5 by 13.638.124.5+13.6
ReasoningClaude Fable 5
- ARC-AGI-2Claude Fable 5 by 75.689.213.6+75.6
- Humanity's Last ExamClaude Fable 5 by 37.755.517.8+37.7
- SimpleBenchClaude Fable 5 by 27.681.954.3+27.6
- CritPtClaude Fable 5 by 27.528.61.1+27.5
- GPQA DiamondClaude Fable 5 by 9.292.683.4+9.2
FactsClaude Fable 5
- SimpleQA VerifiedClaude Fable 5 by 4070.730.7+40
- AA-Omniscience · AccuracyClaude Fable 5 by 32.565.332.9+32.5
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.5 by 14.536.450.9+14.5
Images and chartsClaude Fable 5
- MMMU-ProClaude Fable 5 by 15.584.268.7+15.5
MathClaude Fable 5
- FrontierMath Tier 4Claude Fable 5 by 87.890.22.4+87.8
- FrontierMath Tiers 1-3 (v2)Claude Fable 5 by 63.18723.9+63.1
Following instructionsClaude Fable 5
- IFBenchClaude Fable 5 by 6.263.557.3+6.2
Other results10 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 43.443.3-0.1+43.4
- ARC-AGI-1Claude Fable 5 by 34.898.563.7+34.8
- AA Agentic IndexClaude Fable 5 by 33.55117.5+33.5
- HLE (with tools)Claude Fable 5 by 31.863.832+31.8
- AA IntelligenceClaude Fable 5 by 28.949.620.7+28.9
- Toolathlon Pass@∞Claude Fable 5 by 26.955.628.7+26.9
- Artificial Analysis Coding IndexClaude Fable 5 by 24.476.552.1+24.4
- ToolathlonClaude Fable 5 by 20.761.741+20.7
- τ²-Bench Telecom (AA run)Claude Fable 5 by 20.498.578.1+20.4
- Toolathlon Avg turnsClaude Sonnet 4.5 by 12.219.832+12.2
Questions people ask
Which is better, Claude Fable 5 or Claude Sonnet 4.5?
Claude Fable 5 wins all eight areas we test: coding, agents, reasoning, facts, images and charts, math, long documents and following instructions. Claude Sonnet 4.5 wins none, but costs 70% less.
Which is better for coding?
Claude Fable 5. It wins 7 of the 7 coding tests both models report; Claude Sonnet 4.5 wins none.
Which is cheaper?
Claude Fable 5 costs $10.00 per million input tokens and $50.00 per million output tokens; Claude Sonnet 4.5 costs $3.00 and $15.00. That makes Claude Sonnet 4.5 about 70% cheaper for the same work.
How do you compare the two?
We use the 36 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 10 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.