Model comparison
Claude Fable 5.1 vs Muse Spark 1.2
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 50.3 on the Noometry Index. Muse Spark 1.2 costs 10× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.
Last verified . 29 shared benchmarks.
MetaSummary
- They share 29 benchmarks with published results for both. Claude Fable 5.1 scores higher in 10 categories and Muse Spark 1.2 in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5.1 leads 89.6 to 46.4.
- The biggest single-benchmark swing is ProofBench: 100% for Claude Fable 5.1 and 43% for Muse Spark 1.2.
- Muse Spark 1.2 is cheaper at $1.25 / $4.25 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
- Muse Spark 1.2 accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Fable 5.1 | Muse Spark 1.2 | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 69.0 | 50.3 |
| Released | 2026-09-01 | 2026-08-05 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $10 | $1.25 |
| Output $ / M tokens | $50 | $4.25 |
| Results tracked | 52 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Fable 5.1 leads
Claude Fable 5.1: 74.7 (#1), Muse Spark 1.2: 49.2 (#51)
| Benchmark | Claude Fable 5.1 | Muse Spark 1.2 |
|---|---|---|
| LMArena WebDev | 1744 | 1533 |
| FrontierSWE | 56.3% | 12% |
| SciCode | 63.1% | 56.4% |
| WeirdML | 92.9% | 60.3% |
| LMArena Coding | 1528 | 1495 |
| DeepSWE | — | 54.9% |
| FrontierCode | 50.9% | — |
| CursorBench | 51.8% | — |
| GSO | 88.2% | — |
| MirrorCode | 73.3% | — |
| ALE-Bench | 2,143 | — |
Agentic & Tool Use Claude Fable 5.1 leads
Claude Fable 5.1: 50.7 (#5), Muse Spark 1.2: 29.4 (#87)
| Benchmark | Claude Fable 5.1 | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | 68.6% | 36.4% |
| GDP.pdf | 29.6% | 16% |
| Remote Labor Index | 17.9% | — |
| Vending-Bench 2 | 5,422 | — |
Reasoning Claude Fable 5.1 leads
Claude Fable 5.1: 76.7 (#7), Muse Spark 1.2: 51.3 (#34)
| Benchmark | Claude Fable 5.1 | Muse Spark 1.2 |
|---|---|---|
| NYT Connections (extended) | 90% | 79.2% |
| CritPt | 31.1% | 17.7% |
| LMArena Hard Prompts | 1526 | 1486 |
| DTBench | 97.6% | 94.7% |
| LMCA | 65.5% | 48.4% |
| Epoch Capabilities Index | 164.7 | 154.87 |
| ARC-AGI-2 | 90% | — |
| SimpleBench | — | 74.5% |
| ARC-AGI-1 | 97.5% | — |
| Chess Puzzles | 47% | — |
| EBR-Bench | 57.1% | — |
| Mystery Game Puzzles | 58% | — |
Math Claude Fable 5.1 leads
Claude Fable 5.1: 89.6 (#4), Muse Spark 1.2: 46.4 (#70)
| Benchmark | Claude Fable 5.1 | Muse Spark 1.2 |
|---|---|---|
| ProofBench | 100% | 43% |
| LMArena Math | 1525 | 1471 |
| FrontierMath (Tiers 1-3) | 90.2% | — |
| FrontierMath Tier 4 | 87.8% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| FrontierMath Erdős | 0% | — |
Knowledge Claude Fable 5.1 leads
Claude Fable 5.1: 69.6 (#6), Muse Spark 1.2: 54.1 (#53)
| Benchmark | Claude Fable 5.1 | Muse Spark 1.2 |
|---|---|---|
| SimpleQA Verified | 70.8% | 60.3% |
| LMArena Expert | 1535 | 1480 |
| Humanity's Last Exam | 46.5% | — |
Multimodal Claude Fable 5.1 leads
Claude Fable 5.1: 53.9 (#4), Muse Spark 1.2: 43.4 (#25)
| Benchmark | Claude Fable 5.1 | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | 1318 | 1305 |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |
Multilingual Claude Fable 5.1 leads
Claude Fable 5.1: 59.1 (#3), Muse Spark 1.2: 57.1 (#11)
| Benchmark | Claude Fable 5.1 | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1507 | 1478 |
| LMArena Chinese | 1586 | 1511 |
| LMArena French | 1525 | 1513 |
| LMArena Russian | 1521 | 1487 |
| LMArena Spanish | 1516 | 1498 |
| LMArena German | 1500 | — |
| LMArena Japanese | 1543 | — |
| LMArena Korean | 1534 | — |
Instruction Following Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#6), Muse Spark 1.2: 76.7 (#36)
| Benchmark | Claude Fable 5.1 | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1517 | 1461 |
Long Context Claude Fable 5.1 leads
Claude Fable 5.1: 46.7 (#20), Muse Spark 1.2: 45.2 (#48)
| Benchmark | Claude Fable 5.1 | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1522 | 1475 |
Writing & Preference Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#2), Muse Spark 1.2: 72.3 (#14)
| Benchmark | Claude Fable 5.1 | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1510 | 1482 |
| LMArena Creative Writing | 1507 | 1449 |
| EQ-Bench Creative Writing | 2162 | 1840 |
| LMArena Multi-Turn | 1492 | 1494 |
Frequently asked questions
Is Claude Fable 5.1 better than Muse Spark 1.2?
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 50.3 on the Noometry Index. Muse Spark 1.2 costs 10× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.
Which is cheaper, Claude Fable 5.1 or Muse Spark 1.2?
Muse Spark 1.2 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; Claude Fable 5.1 lists at $10 and $50.
Is Claude Fable 5.1 or Muse Spark 1.2 better for coding?
Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 49.2 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.2 does, with 1.05M tokens against 1M.
How many benchmarks do Claude Fable 5.1 and Muse Spark 1.2 share?
29 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and Muse Spark 1.2 has 31.