Claude Fable 5

openai.com · 官方发布比较 · 2

Claude Fable 5 · Published page gpt6-astra-official; row FrontierMath Tier 4 (v2); preserve page footnotes and task-specific settings · 2026-09-29公开

openai.com · 官方发布比较 · Diamond

Claude Fable 5 · Official published comparison; GPQA Diamond; exact column Claude Fable 5. Footnotes and all competing runs retained in source. · 2026-09-29公开

Vals AI · 独立评测 · 0.1.0

Claude Fable 5 / Mini-SWE-agent · Current displayed evaluator row. Mini-SWE-agent. Scores are not pooled across harnesses; source methodology and repeat counts retained.

huggingface.co · 官方发布比较 · current published task suite

Claude Fable 5 (max, w/ fallback) · Official published comparison; APEX-Agents; exact column Claude Fable 5 (max, w/ fallback). Footnotes and all competing runs retained in source.

Vals AI · 独立评测 · 4.0

Claude Fable 5 / Mini-SWE-agent · Current displayed evaluator row. Mini-SWE-agent. Scores are not pooled across harnesses; source methodology and repeat counts retained.

www.anthropic.com · 官方发布比较 · current published task suite

Fable 5 · Published page anthropic-fable51; row Business workflows AutomationBench; preserve page footnotes and task-specific settings

Scale AI · 独立评测 · 1000 tasks

Claude Fable 5 · scale-mcp-reviewed-method-20261029

openai.com · 官方发布比较 · 1.1

Claude Fable 5 · Published page gpt6-astra-official; row DeepSWE v1.1; preserve page footnotes and task-specific settings · 2026-09-29公开

qwen.ai · 官方发布比较 · current published task suite

Fable5 · Published page qwen38-max; row IFBench; preserve page footnotes and task-specific settings

openai.com · 官方发布比较 · current published task suite

Claude Fable 5 · Published page openai56; row gdp.pdf; preserve page footnotes and task-specific settings · 2026-07-09公开

Scale AI · 独立评测 · current published task suite

Claude-Fable-5 (max) · scale-hss-reviewed-method-20261029

qwen.ai · 官方发布比较 · Standard 10

Fable5 · Published page qwen38-max; row MMMU-Pro; preserve page footnotes and task-specific settings