Muse Spark 1.1vsClaude Fable 5
Across 6 shared benchmarks, Claude Fable 5 leads overall: Muse Spark 1.1 wins 2, Claude Fable 5 wins 4, with 0 ties and an average score difference of -6.63.
Facebook AI研究实验室 · 2026-07-09 · Reasoning model
Anthropic · 2026-06-09 · Reasoning model
Benchmark scores
Grouped by capability, sorted by largest gap within each. 6 shared benchmarks.
AI Agent - Tool Usage
Claude Fable 5 2/3| Benchmark | Muse Spark 1.1 | Claude Fable 5 | Diff |
|---|---|---|---|
| Terminal-Bench 2.1 | 8019 / 44Thinking (With Tools) | 884 / 44Deep Thinking (With Tools) | -8 |
| MCP-Atlas | 88.101 / 38Thinking (With Tools) | 83.305 / 38Normal (With Tools) | +4.80 |
| OSWorld-Verified | 80.807 / 26Thinking (With Tools) | 851 / 26Thinking High (With Tools) | -4.20 |
Coding and Software Engineer
Claude Fable 5 2/2| Benchmark | Muse Spark 1.1 | Claude Fable 5 | Diff |
|---|---|---|---|
| SWE-Bench Pro - Public | 61.5011 / 57Thinking (With Tools) | 80.301 / 57Deep Thinking (With Tools) | -18.80 |
| DeepSWE | 53.3017 / 27Thinking (With Tools) | 702 / 27Deep Thinking (With Tools) | -16.70 |
General Knowledge
Muse Spark 1.1 1/1| Benchmark | Muse Spark 1.1 | Claude Fable 5 | Diff |
|---|---|---|---|
| HLE | 62.104 / 181Thinking (With Tools) | 595 / 181Deep Thinking (No Tools) | +3.10 |
Specs
| Field | Muse Spark 1.1 | Claude Fable 5 |
|---|---|---|
| Publisher | Facebook AI研究实验室 | Anthropic |
| Release date | 2026-07-09 | 2026-06-09 |
| Model type | Reasoning model | Reasoning model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | 1M | 1M |
| Max output | Not available | 128K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Muse Spark 1.1 | Claude Fable 5 |
|---|---|---|
| Text input | Not public | $10 / 1M tokens |
| Text output | Not public | $50 / 1M tokens |
| Cache read | Not public | $1 / 1M tokens |
| Cache write | Not public | $12.5 / 1M tokens |
One or both models have incomplete public pricing.
Summary
- Muse Spark 1.1leads in:General Knowledge (1/1)
- Claude Fable 5leads in:AI Agent - Tool Usage (2/3), Coding and Software Engineer (2/2)
On average across the 6 shared benchmarks, Claude Fable 5 scores 6.63 higher.
Largest single-benchmark gap: SWE-Bench Pro - Public — Muse Spark 1.1 61.50 vs Claude Fable 5 80.30 (-18.80).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.