Model comparison
Kimi K2 Thinking Turbo vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.6 to 45.8 on the Noometry Index.
Last verified . 18 shared benchmarks.
MetaSummary
- They share 18 benchmarks with published results for both. Kimi K2 Thinking Turbo scores higher in 0 categories and Muse Spark in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 50.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 83.1% for Kimi K2 Thinking Turbo and 88.9% for Muse Spark.
- Kimi K2 Thinking Turbo has downloadable open weights; the other is API-only.
Side by side
| Kimi K2 Thinking Turbo | Muse Spark | |
|---|---|---|
| Provider | Moonshot AI | Meta |
| Noometry Index | 45.8 | 50.6 |
| Released | 2025-11-06 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
Kimi K2 Thinking Turbo: 38.4 (#178), Muse Spark: 46.2 (#69)
| Benchmark | Kimi K2 Thinking Turbo | Muse Spark |
|---|---|---|
| LMArena Coding | 1454 | 1481 |
| LMArena WebDev | 1322 | — |
| SciCode | — | 51.5% |
Reasoning Muse Spark leads
Kimi K2 Thinking Turbo: 32.5 (#75), Muse Spark: 35.9 (#67)
| Benchmark | Kimi K2 Thinking Turbo | Muse Spark |
|---|---|---|
| LMArena Hard Prompts | 1428 | 1474 |
| CritPt | — | 11.3% |
| Chess Puzzles | 20% | — |
| Epoch Capabilities Index | — | 152.04 |
Math Too close to call
Kimi K2 Thinking Turbo: 47.4 (#68), Muse Spark: 47.8 (#66)
| Benchmark | Kimi K2 Thinking Turbo | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.1% | 88.9% |
| LMArena Math | 1429 | 1455 |
| ProofBench | — | 17% |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Muse Spark leads
Kimi K2 Thinking Turbo: 50.9 (#69), Muse Spark: 65.7 (#13)
| Benchmark | Kimi K2 Thinking Turbo | Muse Spark |
|---|---|---|
| GPQA Diamond | 84.2% | 89.8% |
| LMArena Expert | 1439 | 1457 |
| Humanity's Last Exam | — | 40.6% |
Multimodal Not comparable
Kimi K2 Thinking Turbo: —, Muse Spark: 43.4 (#24)
| Benchmark | Kimi K2 Thinking Turbo | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |
Multilingual Muse Spark leads
Kimi K2 Thinking Turbo: 51.4 (#109), Muse Spark: 56.1 (#24)
| Benchmark | Kimi K2 Thinking Turbo | Muse Spark |
|---|---|---|
| LMArena Non-English | 1398 | 1464 |
| LMArena Chinese | 1456 | 1509 |
| LMArena French | 1425 | 1497 |
| LMArena German | 1390 | 1497 |
| LMArena Korean | 1330 | 1459 |
| LMArena Russian | 1391 | 1466 |
| LMArena Spanish | 1406 | 1472 |
| LMArena Japanese | 1357 | — |
Instruction Following Muse Spark leads
Kimi K2 Thinking Turbo: 74.0 (#109), Muse Spark: 75.9 (#51)
| Benchmark | Kimi K2 Thinking Turbo | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1403 | 1442 |
Long Context Muse Spark leads
Kimi K2 Thinking Turbo: 43.2 (#102), Muse Spark: 44.4 (#69)
| Benchmark | Kimi K2 Thinking Turbo | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1415 | 1451 |
Writing & Preference Muse Spark leads
Kimi K2 Thinking Turbo: 60.0 (#104), Muse Spark: 66.0 (#39)
| Benchmark | Kimi K2 Thinking Turbo | Muse Spark |
|---|---|---|
| LMArena Text | 1415 | 1474 |
| LMArena Creative Writing | 1374 | 1459 |
| LMArena Multi-Turn | 1414 | 1477 |
Frequently asked questions
Is Kimi K2 Thinking Turbo better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.6 to 45.8 on the Noometry Index.
Is Kimi K2 Thinking Turbo or Muse Spark better for coding?
Muse Spark scores higher on coding benchmarks: 46.2 versus 38.4 in the Noometry coding category.
How many benchmarks do Kimi K2 Thinking Turbo and Muse Spark share?
18 benchmarks have published results for both models. Kimi K2 Thinking Turbo has 21 scored results on Noometry and Muse Spark has 27.