Anthropic · closed · 2026-06
Claude Fable 5
not ranked n/a
the takeThe most capable Claude, and top of the independent intelligence index at launch. It is off the board here because Anthropic stopped publishing the comparable suite, and because its safety classifiers refuse enough real work that even benchmarking it is a fight. Powerful, gated, expensive.
Not ranked: Anthropic doesn't publish enough comparable public benchmarks to place it fairly. How ranking works.
MMLU-Pro
—
- Context
- 1M
- Input
- $10/M
- Output
- $50/M
- Speed
- —
- Modality
- text, image
- Highest-capability Claude, #1 on the AA index at launch
- Built for long-horizon autonomous work
- 1M context, always-on adaptive thinking
- Most expensive Claude ($50 output)
- Safety classifiers refuse legitimate work
- No comparable public benchmarks