Kimi K3 vs 
Muse Spark 1.3
Both are SOTA right now. Each row is one board’s call, and the marked figure is the one that board places higher. No row is added to another, so there is no overall winner: the boards measure different things, and where they split, that is the finding.Each rank is the board’s own: the rank it publishes, or the model’s place in the board’s own order where it publishes none. Scores from different boards cannot be compared.
| Board | Kimi K3 | Muse Spark 1.3 |
|---|---|---|
| Artificial Analysis LLM Leaderboard Artificial Analysis Intelligence Index | 43.6 No. 18 of 375 | 48.1 No. 9 of 375 |
| Arena — Agent Overall | 0.038 No. 17 of 52 | 0.040 No. 15 of 52 |
| Artificial Analysis Coding Agents Artificial Analysis Coding Agent Index | 0.519 No. 15 of 24 | 0.543 No. 13 of 24 |
| Epoch AI Benchmarking Hub FrontierMath Tiers 1–3 | 72.2% No. 22 of 82 | 74.4% No. 20 of 82 |
| HarnessTax — SWE-bench Lite SWE-bench Lite | 76.7% No. 4 of 7 | — |
| HarnessTax — Terminal-Bench 2.0 Terminal-Bench 2.0 | 73.3% No. 4 of 7 | — |
| Terminal-Bench 4.0 Terminal-Bench 4.0 | — | 14.6% No. 32 of 35 |
| Arena — Code Overall | 1654 No. 14 of 142 | 1657 No. 13 of 142 |
| Arena — Text Overall (style control) | 1488 No. 16 of 414 | 1494 No. 9 of 414 |
| Arena — Vision Overall (style control) | — | 1290 No. 12 of 165 |
At a glance
| Developer | Kimi | Meta |
|---|---|---|
| Weights | open | closed |
| Released | 2026-07-16 | — |
| Price Blended Price, USD per 1M tokens (3:1 input:output) | $6.00 | $2.00 |
| Value: where it sits on the kill line | SOTA | SOTA |
Kimi K3 →Muse Spark 1.3 → How the kill line is drawn →