Up to four models
Grok 4.7 vs Muse Spark Open
On the index (GPT-4 = 100), Grok 4.7 scores 168 and Muse Spark Open 167. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Grok 4.7
168151–184
WeightsClosed
ReleasedSep 2026
Price in / out$2.0 / $6.0
Context500K
Core tests taken6 of 9
Muse Spark Open167151–184
WeightsOpen
ReleasedOct 2026
Price in / out$1.25 / $4.25
Context1.05M
Core tests taken6 of 9
Grok 4.7 and Muse Spark Open are too close to call (0 points apart, within the uncertainty), ahead on 4 of 6 shared core tests, at 1.5× the price.
Test by testthird-party results
Grok 4.7Muse Spark Open
Muse Spark OpenEvery result as a table
| Test | Grok 4.7 | Muse Spark Open |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 92.7% | 88.6% |
| SimpleQA Verified | 56.0% | 56.6% |
| Maths | ||
| FrontierMath (tiers 1-3) | 53.0% | 69.8% |
| AIME-style maths (OTIS mock) | 98.1% | 98.1% |
| FrontierMath (tier 4) | 17.1% | 31.7% |
| Coding | ||
| Terminal-Bench 4.0 | 28.8% | 6.6% |
| Code Migration | 44.8% | 21.2% |
| Vibe Code Bench v1.1 | 86.2% | 76.2% |
| Agents | ||
| APEX-Agents | 54.6% | 33.4% |
| Professional work | ||
| Finance Agent (v2) | 52.3% | 61.3% |
| EMB | 67.0% | 53.7% |
| HLAB-Vals-1.1 | 18.3% | 25.0% |
| Legal Research Bench | 47.1% | 38.5% |
| Tax Agent Bench | 34.2% | 26.3% |
| Novel problems | ||
| ARC-AGI-2 | 61.4% | 57.5% |
| ARC-AGI-1 | 90.2% | 89.0% |
Tests at least two of these models have taken. Bold rows are the core tests.
