Claude Fable 5 vs Claude Opus 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 Opus 4.5 is cheaper.
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 software80Claude Fable 58 of 8 tests
- ReasoningHard problems that need careful thinking50Claude Fable 55 of 5 tests
- AgentsCarrying out multi-step tasks on its own40Claude Fable 54 of 4 tests
- MathCompetition and research-level math30Claude Fable 53 of 3 tests
- Following instructionsDoing exactly what it is asked20Claude 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
Images and charts 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.
Claude Opus 4.5 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+85.3points ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+79.6points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+52.6points ahead
Where Claude Opus 4.5 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+2.6points 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 MultilingualClaude Fable 5 by 79.686.67+79.6
- SWE-bench ProClaude Fable 5 by 288052+28
- LiveBench · Agentic CodingClaude Fable 5 by 22.562.239.7+22.5
- Terminal-Bench HardClaude Fable 5 by 15.962.947+15.9
- LMArena · WebDevClaude Fable 5 by 155 rating points16241469+155 rating
- SWE-bench VerifiedClaude Fable 5 by 14.19580.9+14.1
- SciCodeClaude Fable 5 by 11.56149.5+11.5
- LiveBench · CodingClaude Fable 5 by 6.38679.7+6.3
AgentsClaude Fable 5
- BrowseCompClaude Fable 5 by 50.487.437+50.4
- MCP AtlasClaude Fable 5 by 22.484.762.3+22.4
- OSWorld-VerifiedClaude Fable 5 by 18.78566.3+18.7
- GDPValClaude Fable 5 by 8.355.647.3+8.3
ReasoningClaude Fable 5
- ARC-AGI-2Claude Fable 5 by 51.689.237.6+51.6
- Humanity's Last ExamClaude Fable 5 by 25.455.530.1+25.4
- CritPtClaude Fable 5 by 2428.64.6+24
- LiveBench · ReasoningClaude Fable 5 by 9.689.780.1+9.6
- GPQA DiamondClaude Fable 5 by 692.686.6+6
FactsClaude Fable 5
- SimpleQA VerifiedClaude Fable 5 by 2570.745.7+25
- AA-Omniscience · AccuracyClaude Fable 5 by 18.865.346.6+18.8
- AA-Omniscience · Non-hallucinationClaude Opus 4.5 by 2.636.439+2.6
Images and chartsClaude Fable 5
- MMMU-ProClaude Fable 5 by 10.284.274+10.2
MathClaude Fable 5
- FrontierMath Tier 4Claude Fable 5 by 85.390.24.9+85.3
- FrontierMath Tiers 1-3 (v2)Claude Fable 5 by 52.68734.4+52.6
- LiveBench · MathematicsClaude Fable 5 by 5.69690.4+5.6
Following instructionsClaude Fable 5
- LiveBench · Instruction FollowingClaude Fable 5 by 13.275.862.5+13.2
- IFBenchClaude Fable 5 by 5.563.558+5.5
Other results13 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 29.343.314+29.3
- Artificial Analysis Coding IndexClaude Fable 5 by 28.776.547.8+28.7
- HLE (with tools)Claude Fable 5 by 20.663.843.2+20.6
- AA IntelligenceClaude Fable 5 by 20.549.629.1+20.5
- ToolathlonClaude Fable 5 by 18.261.743.5+18.2
- DeepSearchQA (F1)Claude Fable 5 by 18.194.276.1+18.1
- ARC-AGI-1Claude Fable 5 by 16.598.582+16.5
- PaperBenchClaude Fable 5 by 15.988.872.9+15.9
- livebench_languageClaude Fable 5 by 9.490.781.3+9.4
- τ²-Bench Telecom (AA run)Claude Fable 5 by 998.589.5+9
- AA Agentic IndexClaude Opus 4.5 by 8.65159.6+8.6
- livebench_data_analysisClaude Fable 5 by 6.180.574.4+6.1
- LiveBenchClaude Fable 5 by 2.378.376+2.3
Questions people ask
Which is better, Claude Fable 5 or Claude Opus 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 Opus 4.5 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 4.5 wins none.
Which is cheaper?
Claude Fable 5 costs $10.00 per million input tokens and $50.00 per million output tokens; Claude Opus 4.5 costs $5.00 and $25.00. That makes Claude Opus 4.5 about 50% 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 27 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 13 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.