← All models
Compare

Claude Mythos Preview vs DeepSeek-V4-Pro-0813

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

Claude Mythos PreviewDeepSeek-V4-Pro-0813
AttributeClaude Mythos PreviewAnthropic · 3 in the newsDeepSeek-V4-Pro-0813DeepSeek · 1 in the news
Scores
Intelligence (ECI)155
Coding78
Math89
Reasoning & Knowledge70
Agentic & Tools
Specifications
DeveloperAnthropicDeepSeek
FamilyClaudeDeepSeek
ReleasedApr 7, 2026Aug 13, 2026
Parameters1.6T
AvailabilityUnreleasedOpen weights (unrestricted)
Context window1M
Price — $/M input$0.58
Price — $/M output$1.74
Inputstext
Outputstext
Benchmarks
AIME 2024/202599%
ARC-AGI91%
ARC-AGI-261%
GPQA Diamond92%
Humanity's Last Exam41%
SciCode51%
SimpleQA Verified53%
WebDev Arena1582
WeirdML66%

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.