Claude Fable 5.1 vs GPT-5.2
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-5.2 is cheaper.
Scores updated · 34 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
- 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
- AgentsCarrying out multi-step tasks on its own20Claude Fable 5.12 of 2 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-5.2 costs 74% 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+56.1points ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+51.3points ahead
- Common-sense trick questionsSimpleBench+40.8points ahead
Where GPT-5.2 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 34 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Fable 5.1
- SWE-bench ProClaude Fable 5.1 by 51.381.229.9+51.3
- LMArena · WebDevClaude Fable 5.1 by 325 rating points17421417+325 rating
- SWE-bench MultilingualClaude Fable 5.1 by 22.489.166.7+22.4
- LiveBench · Agentic CodingClaude Fable 5.1 by 15.866.150.3+15.8
- SciCodeClaude Fable 5.1 by 1163.152.1+11
- LiveBench · CodingClaude Fable 5.1 by 10.386.476.1+10.3
AgentsClaude Fable 5.1
- τ-Bench V3 · BankingClaude Fable 5.1 by 36.147.211.1+36.1
- GDPValClaude Fable 5.1 by 14.462.748.3+14.4
ReasoningClaude Fable 5.1
- SimpleBenchClaude Fable 5.1 by 40.886.645.8+40.8
- ARC-AGI-2Claude Fable 5.1 by 37.19052.9+37.1
- Humanity's Last ExamClaude Fable 5.1 by 21.459.137.7+21.4
- CritPtClaude Fable 5.1 by 18.129.711.6+18.1
- LiveBench · ReasoningClaude Fable 5.1 by 8.591.783.2+8.5
- GPQA DiamondClaude Fable 5.1 by 3.493.790.3+3.4
FactsClaude Fable 5.1
- SimpleQA VerifiedClaude Fable 5.1 by 33.770.837.1+33.7
- AA-Omniscience · AccuracyClaude Fable 5.1 by 22.967.244.3+22.9
- AA-Omniscience · Non-hallucinationClaude Fable 5.1 by 8.627.418.8+8.6
Images and chartsClaude Fable 5.1
- LMArena · VisionClaude Fable 5.1 by 73 rating points13191246+73 rating
MathClaude Fable 5.1
- FrontierMath Tier 4Claude Fable 5.1 by 56.187.831.7+56.1
- FrontierMath Tiers 1-3 (v2)Claude Fable 5.1 by 22.890.267.4+22.8
- LiveBench · MathematicsClaude Fable 5.1 by 3.89793.2+3.8
Following instructionsClaude Fable 5.1
- LiveBench · Instruction FollowingClaude Fable 5.1 by 11.27361.8+11.2
Other results11 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 5.1 by 44.443.5-0.9+44.4
- Artificial Analysis Coding IndexClaude Fable 5.1 by 32.981.648.7+32.9
- GDPval-AA (Elo)Claude Fable 5.1 by 273 rating points17351462+273 rating
- AA IntelligenceClaude Fable 5.1 by 2353.430.4+23
- HLE (with tools)Claude Fable 5.1 by 20.165.645.5+20.1
- HealthBench Professional length-adjustedClaude Fable 5.1 by 16.262.145.9+16.2
- ARC-AGI-1Claude Fable 5.1 by 11.397.586.2+11.3
- livebench_languageClaude Fable 5.1 by 9.789.579.8+9.7
- HealthBench length-adjustedClaude Fable 5.1 by 3.26056.8+3.2
- AA Agentic IndexGPT-5.2 by 2.25860.2+2.2
- livebench_data_analysisClaude Fable 5.1 by 2.180.378.2+2.1
Questions people ask
Which is better, Claude Fable 5.1 or GPT-5.2?
Claude Fable 5.1 wins all eight areas we test: coding, agents, reasoning, facts, images and charts, math, long documents and following instructions. GPT-5.2 wins none, but costs 74% less.
Which is better for coding?
Claude Fable 5.1. It wins 6 of the 6 coding tests both models report; GPT-5.2 wins none.
Which is cheaper?
Claude Fable 5.1 costs $10.00 per million input tokens and $50.00 per million output tokens; GPT-5.2 costs $1.75 and $14.00. That makes GPT-5.2 about 74% cheaper for the same work.
How do you compare the two?
We use the 34 benchmark tests both models have published scores on. The verdict counts the 23 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 11 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.