Up to four models
Hy4 preview vs Muse Spark 1.2
On the index (GPT-4 = 100), Hy4 preview scores 173 and Muse Spark 1.2 162. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
173154–192
WeightsOpen
ReleasedAug 2026
Price in / out$0.83 / $2.5
Context1.05M
Core tests taken2 of 9
162146–178
WeightsClosed
ReleasedAug 2026
Price in / out$1.25 / $4.25
Context1.05M
Core tests taken3 of 9
Hy4 preview and Muse Spark 1.2 are too close to call (11 points apart, within the uncertainty), ahead on 1 of 2 shared core tests, and costs 1.6× less.
Test by testthird-party results
Every result as a table
| Test | Hy4 preview | Muse Spark 1.2 |
|---|---|---|
| Maths | ||
| ProofBench v1.1 | 75.0% | 43.0% |
| Coding | ||
| Terminal-Bench 4.0 | 39.4% | 6.1% |
| Code Migration | 47.4% | 29.9% |
| CyberBench v1.1 | 65.4% | 69.5% |
| IOI | 59.3% | 21.8% |
| ProgramBench | 0.0% | 0.5% |
| Vibe Code Bench v1.1 | 81.0% | 79.1% |
| Agents | ||
| BioMysteryBench | 69.3% | 64.8% |
| SRE Bench | 2.3% | 0.0% |
| Professional work | ||
| Finance Agent (v2) | 55.1% | 60.6% |
| EMB | 58.1% | 57.0% |
| LegalBench | 83.8% | 85.3% |
| Legal Research Bench | 45.2% | 43.8% |
| MedCode | 43.3% | 49.4% |
| MedScribe | 83.6% | 90.1% |
| Public Benefits Bench v1.1 | 68.6% | 68.5% |
| Tax Agent Bench | 34.4% | 32.8% |
Tests at least two of these models have taken. Bold rows are the core tests.