Claude Fable 5.1 vs GPT-5.4
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-5.4 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 software70Claude Fable 5.17 of 7 tests
- ReasoningHard problems that need careful thinking50Claude Fable 5.15 of 5 tests
- AgentsCarrying out multi-step tasks on its own30Claude Fable 5.13 of 3 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-5.4 costs 71% 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
- Extremely hard research-level math problemsFrontierMath Tier 4+38.8points ahead
- Short factual questions, answered correctlySimpleQA Verified+25.7points ahead
- Real work tasks from 44 professionsGDPVal+25.4points ahead
Where GPT-5.4 pulls ahead
No clear win on a test scored out of 100.
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
- LMArena · WebDevClaude Fable 5.1 by 278 rating points17421464+278 rating
- SWE-bench ProClaude Fable 5.1 by 23.581.257.7+23.5
- SWE-bench MultilingualClaude Fable 5.1 by 17.489.171.7+17.4
- Terminal-Bench 2.1Claude Fable 5.1 by 13.191.478.3+13.1
- LiveBench · Agentic CodingClaude Fable 5.1 by 12.366.153.8+12.3
- LiveBench · CodingClaude Fable 5.1 by 8.986.477.5+8.9
- SciCodeClaude Fable 5.1 by 6.563.156.6+6.5
AgentsClaude Fable 5.1
- GDPValClaude Fable 5.1 by 25.462.737.3+25.4
- AA IT-Bench SREClaude Fable 5.1 by 1549.534.5+15
- τ-Bench V3 · BankingClaude Fable 5.1 by 7.647.239.6+7.6
ReasoningClaude Fable 5.1
- ARC-AGI-2Claude Fable 5.1 by 16.79073.3+16.7
- Humanity's Last ExamClaude Fable 5.1 by 15.459.143.7+15.4
- CritPtClaude Fable 5.1 by 6.329.723.4+6.3
- LiveBench · ReasoningClaude Fable 5.1 by 3.691.788.1+3.6
- GPQA DiamondClaude Fable 5.1 by 1.793.792+1.7
FactsClaude Fable 5.1
- SimpleQA VerifiedClaude Fable 5.1 by 25.770.845.1+25.7
- AA-Omniscience · Non-hallucinationClaude Fable 5.1 by 19.127.48.3+19.1
- AA-Omniscience · AccuracyClaude Fable 5.1 by 16.367.250.9+16.3
Images and chartsClaude Fable 5.1
- LMArena · VisionClaude Fable 5.1 by 16 rating points13191303+16 rating
MathClaude Fable 5.1
- FrontierMath Tier 4Claude Fable 5.1 by 38.887.849+38.8
- FrontierMath Tiers 1-3 (v2)Claude Fable 5.1 by 11.690.278.6+11.6
- LiveBench · MathematicsClaude Fable 5.1 by 2.89794.2+2.8
Following instructionsClaude Fable 5.1
- LiveBench · Instruction FollowingClaude Fable 5.1 by 2.87370.2+2.8
Other results15 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.
- HiL-Bench (Tools-allowed)Claude Fable 5.1 by 51.861.59.7+51.8
- AA-OmniscienceClaude Fable 5.1 by 37.743.55.8+37.7
- OfficeQA ProClaude Fable 5.1 by 17.96951.1+17.9
- DeepSWE 1.1Claude Fable 5.1 by 15.467.452+15.4
- AA IntelligenceClaude Fable 5.1 by 14.453.439+14.4
- HealthBench Professional length-adjustedClaude Fable 5.1 by 1462.148.1+14
- AA Agentic IndexClaude Fable 5.1 by 13.85844.2+13.8
- HLE (with tools)Claude Fable 5.1 by 13.565.652.1+13.5
- OfficeQAClaude Fable 5.1 by 12.180.268.1+12.1
- Artificial Analysis Coding IndexClaude Fable 5.1 by 10.581.671.1+10.5
- livebench_languageClaude Fable 5.1 by 6.989.582.6+6.9
- GDPval-AA (Elo)Claude Fable 5.1 by 61 rating points17351674+61 rating
- HealthBench length-adjustedClaude Fable 5.1 by 66054+6
- ARC-AGI-1Claude Fable 5.1 by 3.897.593.7+3.8
- livebench_data_analysisClaude Fable 5.1 by 180.379.3+1
Questions people ask
Which is better, Claude Fable 5.1 or GPT-5.4?
Claude Fable 5.1 wins all eight areas we test: coding, agents, reasoning, facts, images and charts, math, long documents and following instructions. GPT-5.4 wins none, but costs 71% less.
Which is better for coding?
Claude Fable 5.1. It wins 7 of the 7 coding tests both models report; GPT-5.4 wins none.
Which is cheaper?
Claude Fable 5.1 costs $10.00 per million input tokens and $50.00 per million output tokens; GPT-5.4 costs $2.50 and $15.00. That makes GPT-5.4 about 71% 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 24 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 15 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.