Statement of Work
solarSystem
13 runs, every one scored by the same deterministic engine under rubric v15.Open the interactive leaderboard for solarSystem →
| # | Run | Date | Composite | Coverage |
|---|---|---|---|---|
| 1 | Mimo v2.5 | Jul 2026 | 75.9 | — |
| 2 | Muse Spark 1.1 | Jul 2026 | 67.2 | — |
| 3 | Gemini Flash 3.6 + Gemini Flash Lite | Jul 2026 | 63.8 | — |
| 4 | Mimo Pro v2.5 + Mimo | Jul 2026 | 63.2 | — |
| 5 | Gemini Flash Lite 3.1 | Jul 2026 | 62.2 | — |
| 6 | Claude Sonnet 5 + Gemini Flash Lite | Jul 2026 | 58.3 | — |
| 7 | Gemini Flash 3.5 + Gemini Flash Lite | Jul 2026 | 57.6 | — |
| 8 | Mimo Pro v2.5 | Jun 2026 | 57.6 | — |
| 9 | Step Flash 3.7 | Jul 2026 | 56.9 | — |
| 10 | Plus qwen3.7 | Jul 2026 | 54.7 | — |
| 11 | Deepseek Flash v4 | Jun 2026 | 50.2 | — |
| 12 | Gemini Flash 3.5 + Gemini Flash Lite | Jul 2026 | 42.6 | — |
| 13 | Gemini Flash 3 (preview) | Jun 2026 | 28.9 | — |
Every run on Favur Evals is scored by the same deterministic engine, on the same Statements of Work. The benchmark is self-funded — no vendor sponsorship, credits, or grants.