Model comparison
Kimi K2.7 Code vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.3 to 43.0 on the Noometry Index.
Last verified . 5 shared benchmarks.
MetaSummary
- They share 5 benchmarks with published results for both. Kimi K2.7 Code scores higher in 2 categories and Muse Spark in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 53.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Kimi K2.7 Code and 88.9% for Muse Spark.
- Kimi K2.7 Code has downloadable open weights; the other is API-only.
Side by side
| Kimi K2.7 Code | Muse Spark | |
|---|---|---|
| Provider | Moonshot AI | Meta |
| Noometry Index | 43.0 | 50.3 |
| Released | 2026-06-12 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.95 | — |
| Output $ / M tokens | $4 | — |
| Results tracked | 19 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
Kimi K2.7 Code: 42.4 (#92), Muse Spark: 45.6 (#65)
| Benchmark | Kimi K2.7 Code | Muse Spark |
|---|---|---|
| SciCode | 47.5% | 51.5% |
| DeepSWE | 30.5% | — |
| FrontierCode | 30.1% | — |
| LMArena WebDev | 1473 | — |
| WeirdML | 54.1% | — |
| LMArena Coding | — | 1482 |
| ALE-Bench | 886.23 | — |
Agentic & Tool Use Not comparable
Kimi K2.7 Code: 23.9 (#115), Muse Spark: —
| Benchmark | Kimi K2.7 Code | Muse Spark |
|---|---|---|
| APEX-Agents | 37.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 5,083 | — |
Reasoning Kimi K2.7 Code leads
Kimi K2.7 Code: 38.2 (#56), Muse Spark: 34.9 (#61)
| Benchmark | Kimi K2.7 Code | Muse Spark |
|---|---|---|
| CritPt | 10% | 11.3% |
| Epoch Capabilities Index | 150.01 | 152.09 |
| SimpleBench | 57.9% | — |
| Chess Puzzles | 21% | — |
| LMArena Hard Prompts | — | 1475 |
| Surface Evolver Bench | 48.8% | — |
Math Kimi K2.7 Code leads
Kimi K2.7 Code: 52.6 (#39), Muse Spark: 46.8 (#57)
| Benchmark | Kimi K2.7 Code | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 88.9% |
| FrontierMath (Tiers 1-3) | 54% | — |
| FrontierMath Tier 4 | 12.2% | — |
| ProofBench | — | 17% |
| LMArena Math | — | 1455 |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Muse Spark leads
Kimi K2.7 Code: 53.6 (#51), Muse Spark: 65.7 (#12)
| Benchmark | Kimi K2.7 Code | Muse Spark |
|---|---|---|
| GPQA Diamond | 87.9% | 89.8% |
| Humanity's Last Exam | — | 40.6% |
| SimpleQA Verified | 36.5% | — |
| LMArena Expert | — | 1458 |
Multimodal Not comparable
Kimi K2.7 Code: —, Muse Spark: 42.7 (#23)
| Benchmark | Kimi K2.7 Code | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |
Multilingual Not comparable
Kimi K2.7 Code: —, Muse Spark: 56.3 (#23)
| Benchmark | Kimi K2.7 Code | Muse Spark |
|---|---|---|
| LMArena Non-English | — | 1464 |
| LMArena Chinese | — | 1507 |
| LMArena French | — | 1497 |
| LMArena German | — | 1497 |
| LMArena Korean | — | 1457 |
| LMArena Russian | — | 1467 |
| LMArena Spanish | — | 1471 |
Instruction Following Not comparable
Kimi K2.7 Code: —, Muse Spark: 76.1 (#47)
| Benchmark | Kimi K2.7 Code | Muse Spark |
|---|---|---|
| LMArena Instruction Following | — | 1443 |
Long Context Not comparable
Kimi K2.7 Code: —, Muse Spark: 44.4 (#65)
| Benchmark | Kimi K2.7 Code | Muse Spark |
|---|---|---|
| LMArena Longer Query | — | 1451 |
Writing & Preference Not comparable
Kimi K2.7 Code: —, Muse Spark: 66.2 (#37)
| Benchmark | Kimi K2.7 Code | Muse Spark |
|---|---|---|
| LMArena Text | — | 1474 |
| LMArena Creative Writing | — | 1460 |
| LMArena Multi-Turn | — | 1477 |
Frequently asked questions
Is Kimi K2.7 Code better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.3 to 43.0 on the Noometry Index.
Is Kimi K2.7 Code or Muse Spark better for coding?
Muse Spark scores higher on coding benchmarks: 45.6 versus 42.4 in the Noometry coding category.
How many benchmarks do Kimi K2.7 Code and Muse Spark share?
5 benchmarks have published results for both models. Kimi K2.7 Code has 19 scored results on Noometry and Muse Spark has 27.