← All models
Compare

Claude Fable 5 vs DeepSeek-V4-Pro

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

Claude Fable 5DeepSeek-V4-Pro
Claude Fable 5Anthropic · 18 in the newsDeepSeek-V4-ProDeepSeek · 3 in the news
Scores
Intelligence (ECI)161150
Coding10076
Math9791
Reasoning & Knowledge9768
Agentic & Tools9792
Specifications
DeveloperAnthropicDeepSeek
FamilyClaudeDeepSeek
ReleasedJun 9, 2026Apr 24, 2026
Parameters1.6T
AvailabilityAPI accessOpen weights (unrestricted)
Context window1M1M
Price — $/M input$10.00$0.43
Price — $/M output$50.00$0.87
Inputstext, image, filetext
Outputstexttext
Benchmarks
AIME 2024/2025100%97%
APEX45%
GPQA Diamond93%90%
Humanity's Last Exam53%36%
SciCode60%50%
SimpleBench82%61%
SimpleQA Verified68%57%
WebDev Arena16541464
WeirdML88%49%
τ²-bench99%96%
SWE-bench Verified78%

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.