Claude Fable 5.2 vs Muse Wonder
Claude Fable 5.2 leads Muse Wonder by 15.5 points on the Shogo Agent Index. Claude Fable 5.2 wins 13 and Muse Wonder wins 0 of 13 shared benchmarks. Muse Wonder is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | Claude Fable 5.2 | Muse Wonder |
|---|---|---|
| Agentic coding | 86 | 68 |
| Long-horizon autonomy | 78 | 70 |
| Knowledge-work agents | 67 | 50 |
| Computer use | 77 | 50 |
| Security & context learning | 65 | 57 |
Shared benchmarks
| Benchmark | Claude Fable 5.2 | Muse Wonder |
|---|---|---|
| APEX-Agentsindex | 80.1% | 66.1% |
| Vending-Bench 2index | $9,628 | $9,432 |
| CursorBenchindex | 60.0% | 50.4% |
| PostTrainBenchindex | 44.6% | 24.2% |
| CritPt | 35.7% | 28.3% |
| DTBench | 99.2% | 95.2% |
| FrontierMath Tier 4 | 100.0% | 70.7% |
| FrontierMath Tiers 1-3 | 95.1% | 82.1% |
| LMCA | 70.6% | 56.8% |
| OTIS Mock AIME | 99.7% | 99.4% |
| ProofBench | 100.0% | 84.0% |
| SciCode | 67.7% | 60.3% |
| WeirdML v3 | 43.1% | 15.1% |
Specs and price
| Claude Fable 5.2 | Muse Wonder | |
|---|---|---|
| Agent Index | 76.4 (#1) | 60.9 (#15) |
| Agent $/M | $3.21 | $1.69 |
| Input / output $/M | $8.00 / $40.00 | $4.00 / $20.00 |
| Context | 1M | 1M |
| Released | Nov 9, 2026 | Oct 12, 2026 |
| Weights | Closed | Closed |
| API hosts | 4 | 2 |
Don’t pick one. Route.
Shogo can run Claude Fable 5.2 and Muse Wonder side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo