Up to four models
Muse Spark 1.2 vs Muse Spark 1.1
On the index (GPT-4 = 100), Muse Spark 1.2 scores 162 and Muse Spark 1.1 161. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
162146–178
WeightsClosed
ReleasedAug 2026
Price in / out$1.25 / $4.25
Context1.05M
Core tests taken3 of 9
161145–177
WeightsClosed
ReleasedJul 2026
Price in / out$1.25 / $4.25
Context1.05M
Core tests taken2 of 9
Muse Spark 1.2 and Muse Spark 1.1 are too close to call (1 point apart, within the uncertainty), ahead on 2 of 2 shared core tests, at a similar price.
Test by testthird-party results
Every result as a table
| Test | Muse Spark 1.2 | Muse Spark 1.1 |
|---|---|---|
| Reasoning & knowledge | ||
| LiveBench Data Analysis | 76.5% | 72.5% |
| LiveBench IF | 74.3% | 69.6% |
| LiveBench Language | 78.6% | 74.3% |
| LiveBench Reasoning | 90.0% | 87.7% |
| MMLU Pro | 88.3% | 88.7% |
| MMMU Pro | 86.1% | 86.6% |
| SimpleQA Verified | 60.3% | 57.8% |
| Maths | ||
| LiveBench Mathematics | 91.2% | 87.1% |
| Chess puzzles | 27.0% | 34.0% |
| Coding | ||
| LiveBench Agentic Coding | 57.6% | 58.5% |
| LiveBench Coding | 77.5% | 77.2% |
| Code Migration | 29.9% | 31.1% |
| ProgramBench | 0.5% | 0.0% |
| SWE-bench | 86.6% | 82.0% |
| Vibe Code Bench v1.1 | 79.1% | 72.2% |
| DeepSWE | 54.9% | 53.3% |
| Agents | ||
| APEX-Agents | 45.4% | 31.8% |
| SkillsBench | 53.0% | 59.2% |
| DTBench | 94.7% | 94.4% |
| LMCA | 48.4% | 49.9% |
| Professional work | ||
| Finance Agent (v2) | 60.6% | 57.2% |
| CorpFin v2 | 70.9% | 71.3% |
| EMB | 57.0% | 56.4% |
| LegalBench | 85.3% | 85.0% |
| Legal Research Bench | 43.8% | 38.0% |
| MedScribe | 90.1% | 88.9% |
| MortgageTax | 65.4% | 66.1% |
| Public Benefits Bench v1.1 | 68.5% | 61.3% |
| TaxEval v2 | 80.4% | 79.7% |
Tests at least two of these models have taken. Bold rows are the core tests.