← All models
Compare

Claude Fable 5 vs GPT-5.2

Add, remove, or swap models to compare them side by side.

Claude Fable 5GPT-5.2
AttributeClaude Fable 5Anthropic · 52 in the newsGPT-5.2OpenAI · 7 in the news
Scores
Intelligence (ECI)163153
Coding9662
Math9577
Reasoning & Knowledge8953
Agentic & Tools9466
Specifications
DeveloperAnthropicOpenAI
FamilyClaudeGPT
ReleasedJun 9, 2026Dec 11, 2025
Parameters
AvailabilityAPI accessAPI access
Context window1M400K
Price — $/M input$10.00$1.75
Price — $/M output$50.00$14.00
Inputstext, image, filefile, image, text
Outputstexttext
Benchmarks
AIME 2024/2025100%96%
APEX64%34%
ARC-AGI99%86%
ARC-AGI-289%53%
GPQA Diamond86%91%
Humanity's Last Exam56%28%
SciCode61%52%
SimpleBench82%46%
SimpleQA Verified71%37%
WebDev Arena16281480
WeirdML92%72%
τ²-bench99%85%
FrontierMath41%
FrontierMath Tier 419%
GDPval (win/tie rate)71%
GSO (code optimization)27%
LiveCodeBench89%
METR task horizon5.9 h
MMLU-Pro87%
SWE-bench Verified74%
Terminal-Bench65%

Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.

Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.