← All models
Compare

Claude Fable 5 vs Gemma 4 31B IT

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

Claude Fable 5Gemma 4 31B IT
AttributeClaude Fable 5Anthropic · 42 in the newsGemma 4 31B ITGoogle DeepMind
Scores
Intelligence (ECI)162142
Coding9932
Math95
Reasoning & Knowledge9625
Agentic & Tools98
Specifications
DeveloperAnthropicGoogle DeepMind
FamilyClaudeGemma
ReleasedJun 9, 2026Apr 2, 2026
Parameters
AvailabilityAPI accessOpen weights (restricted use)
Context window1M262K
Price — $/M input$10.00$0.10
Price — $/M output$50.00$0.35
Inputstext, image, fileimage, text, video
Outputstexttext
Benchmarks
AIME 2024/2025100%
APEX45%
GPQA Diamond93%
Humanity's Last Exam53%
SciCode60%
SimpleBench82%
SimpleQA Verified68%10%
WebDev Arena16541380
WeirdML92%52%
τ²-bench99%

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.