Up to four models
Kimi K3.1 Pro vs Muse Ember
On the index (GPT-4 = 100), Kimi K3.1 Pro scores 179 and Muse Ember 179. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Kimi K3.1 Pro
179163–195
WeightsOpen
ReleasedOct 2026
Price in / out$0.24 / $8.4
Context1.05M
Core tests taken4 of 9
179161–196
WeightsClosed
ReleasedNov 2026
Price in / out$0.10 / $0.50
Context1.05M
Core tests taken2 of 9
Kimi K3.1 Pro and Muse Ember are too close to call (1 point apart, within the uncertainty), ahead on 2 of 2 shared core tests, at 11× the price.
Test by testthird-party results
Kimi K3.1 Pro
Muse Ember
Every result as a table
| Test | Kimi K3.1 Pro | Muse Ember |
|---|---|---|
| Coding | ||
| Terminal-Bench 4.0 | 63.6% | 39.4% |
| Vibe Code Bench v1.1 | 84.9% | 83.7% |
| Agents | ||
| APEX-Agents | 65.5% | 64.3% |
| Professional work | ||
| HLAB-Vals-1.1 | 11.7% | 25.0% |
| Legal Research Bench | 37.5% | 49.0% |
| Tax Agent Bench | 24.9% | 38.2% |
Tests at least two of these models have taken. Bold rows are the core tests.