Claude Fable 5.1vsClaude Fable 5
Across 6 shared benchmarks, Claude Fable 5.1 leads overall: Claude Fable 5.1 wins 6, Claude Fable 5 wins 0, with 0 ties and an average score difference of +27.89.
Claude Fable 5.1
Anthropic · 2026-09-01 · Reasoning model
Claude Fable 5
Anthropic · 2026-06-09 · Reasoning model
Claude Fable 5.16 wins(100%)(0%)0 winsClaude Fable 5
Benchmark scores
Grouped by capability, sorted by largest gap within each. 6 shared benchmarks.
AI Agent - Tool Usage
Claude Fable 5.1 2/2| Benchmark | Claude Fable 5.1 | Claude Fable 5 | Diff |
|---|---|---|---|
| Terminal-Bench-Science 0.1 | 52.601 / 10Max (With Tools) | 21.404 / 10Max (With Tools) | +31.20 |
| Terminal-Bench 4.0 | 55.801 / 11Max (With Tools) | 44.553 / 11Max (With Tools) | +11.25 |
General Knowledge
Claude Fable 5.1 2/2| Benchmark | Claude Fable 5.1 | Claude Fable 5 | Diff |
|---|---|---|---|
| HLE | 651 / 188Max (With Tools) | 597 / 188Deep Thinking (No Tools) | +6 |
| AA Intelligence Index | 661 / 27Max (With Tools) | 625 / 27Max (With Tools) | +4 |
Coding and Software Engineer
Claude Fable 5.1 1/1| Benchmark | Claude Fable 5.1 | Claude Fable 5 | Diff |
|---|---|---|---|
| CursorBench 3.2 | 73.401 / 5Max (With Tools) | 70.502 / 5Max (With Tools) | +2.90 |
Productivity Knowledge
Claude Fable 5.1 1/1| Benchmark | Claude Fable 5.1 | Claude Fable 5 | Diff |
|---|---|---|---|
| GDPval-AA v2 | 1,8532 / 23Max (With Tools) | 1,7416 / 23Max (With Tools) | +112 |
Specs
| Field | Claude Fable 5.1 | Claude Fable 5 |
|---|---|---|
| Publisher | Anthropic | Anthropic |
| Release date | 2026-09-01 | 2026-06-09 |
| Model type | Reasoning model | Reasoning model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | 1M | 1M |
| Max output | 128K | 128K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Claude Fable 5.1 | Claude Fable 5 |
|---|---|---|
| Text input | $10 / 1M tokens | $10 / 1M tokens |
| Text output | $50 / 1M tokens | $50 / 1M tokens |
| Cache read | $0.25 / 1M tokens | $1 / 1M tokens |
| Cache write | $12.5 / 1M tokens | $12.5 / 1M tokens |
Summary
- Claude Fable 5.1leads in:AI Agent - Tool Usage (2/2), General Knowledge (2/2), Coding and Software Engineer (1/1), Productivity Knowledge (1/1)
On average across the 6 shared benchmarks, Claude Fable 5.1 scores 27.89 higher.
Largest single-benchmark gap: GDPval-AA v2 — Claude Fable 5.1 1,853 vs Claude Fable 5 1,741 (+112).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.