Model comparison
Kimi K2 (Jul 2025) vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.6 to 41.2 on the Noometry Index.
Last verified . 19 shared benchmarks.
MetaSummary
- They share 19 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 0 categories and Muse Spark in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 37.3.
- Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.
Side by side
| Kimi K2 (Jul 2025) | Muse Spark | |
|---|---|---|
| Provider | Moonshot AI | Meta |
| Noometry Index | 41.2 | 50.6 |
| Released | 2025-07-12 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.57 | — |
| Output $ / M tokens | $2.30 | — |
| Results tracked | 42 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
Kimi K2 (Jul 2025): 42.4 (#102), Muse Spark: 46.2 (#69)
| Benchmark | Kimi K2 (Jul 2025) | Muse Spark |
|---|---|---|
| LMArena Coding | 1399 | 1481 |
| SWE-bench Verified (bash only) | 63.4% | — |
| Aider Polyglot | 59.1% | — |
| SciCode | — | 51.5% |
| GSO | 4.9% | — |
| WeirdML | 42.8% | — |
| ALE-Bench | 597.5 | — |
Agentic & Tool Use Not comparable
Kimi K2 (Jul 2025): 32.4 (#64), Muse Spark: —
| Benchmark | Kimi K2 (Jul 2025) | Muse Spark |
|---|---|---|
| Terminal-Bench | 35.7% | — |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| METR Time Horizons | 59.2% | — |
Reasoning Muse Spark leads
Kimi K2 (Jul 2025): 23.3 (#179), Muse Spark: 35.9 (#67)
| Benchmark | Kimi K2 (Jul 2025) | Muse Spark |
|---|---|---|
| LMArena Hard Prompts | 1384 | 1474 |
| Epoch Capabilities Index | 146.01 | 152.04 |
| SimpleBench | 26.3% | — |
| Kagi LLM Benchmark | 64.4% | — |
| CritPt | — | 11.3% |
| ForecastBench | 60.2 | — |
Math Muse Spark leads
Kimi K2 (Jul 2025): 42.7 (#83), Muse Spark: 47.8 (#66)
| Benchmark | Kimi K2 (Jul 2025) | Muse Spark |
|---|---|---|
| LMArena Math | 1397 | 1455 |
| FrontierMath (Feb 2025 set) | 21.4% | 39% |
| FrontierMath Tier 4 (v1) | 0% | 14.6% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 17% |
| Omni-MATH | 65.4% | — |
Knowledge Muse Spark leads
Kimi K2 (Jul 2025): 37.3 (#157), Muse Spark: 65.7 (#13)
| Benchmark | Kimi K2 (Jul 2025) | Muse Spark |
|---|---|---|
| LMArena Expert | 1365 | 1457 |
| GPQA Diamond | — | 89.8% |
| Humanity's Last Exam | — | 40.6% |
| MMLU-Pro | 81.9% | — |
| Confabulations | 20.4% | — |
| Vectara Hallucination Rate | 17.9% | — |
| GPQA (HELM) | 65.3% | — |
Multimodal Not comparable
Kimi K2 (Jul 2025): —, Muse Spark: 43.4 (#24)
| Benchmark | Kimi K2 (Jul 2025) | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |
Multilingual Muse Spark leads
Kimi K2 (Jul 2025): 49.6 (#130), Muse Spark: 56.1 (#24)
| Benchmark | Kimi K2 (Jul 2025) | Muse Spark |
|---|---|---|
| LMArena Non-English | 1372 | 1464 |
| LMArena Chinese | 1415 | 1509 |
| LMArena French | 1379 | 1497 |
| LMArena German | 1387 | 1497 |
| LMArena Korean | 1325 | 1459 |
| LMArena Russian | 1385 | 1466 |
| LMArena Spanish | 1386 | 1472 |
| LMArena Japanese | 1349 | — |
Instruction Following Muse Spark leads
Kimi K2 (Jul 2025): 71.1 (#156), Muse Spark: 75.9 (#51)
| Benchmark | Kimi K2 (Jul 2025) | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1348 | 1442 |
| IFEval | 85% | — |
Long Context Muse Spark leads
Kimi K2 (Jul 2025): 41.2 (#145), Muse Spark: 44.4 (#69)
| Benchmark | Kimi K2 (Jul 2025) | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1353 | 1451 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | 17.6% | — |
Writing & Preference Muse Spark leads
Kimi K2 (Jul 2025): 62.3 (#78), Muse Spark: 66.0 (#39)
| Benchmark | Kimi K2 (Jul 2025) | Muse Spark |
|---|---|---|
| LMArena Text | 1380 | 1474 |
| LMArena Creative Writing | 1350 | 1459 |
| LMArena Multi-Turn | 1371 | 1477 |
| Short-Story Creative Writing | 85.6% | — |
| EQ-Bench Creative Writing | 1666 | — |
| WildBench | 86.2% | — |
Frequently asked questions
Is Kimi K2 (Jul 2025) better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.6 to 41.2 on the Noometry Index.
Is Kimi K2 (Jul 2025) or Muse Spark better for coding?
Muse Spark scores higher on coding benchmarks: 46.2 versus 42.4 in the Noometry coding category.
How many benchmarks do Kimi K2 (Jul 2025) and Muse Spark share?
19 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Muse Spark has 27.