Model comparison
Kimi K2.7 Code vs Muse Spark 1.1
Muse Spark 1.1 is the stronger model overall, scoring 49.9 to 43.3 on the Noometry Index.
Last verified . 10 shared benchmarks.
MetaSummary
- They share 10 benchmarks with published results for both. Kimi K2.7 Code scores higher in 2 categories and Muse Spark 1.1 in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in coding, where Muse Spark 1.1 leads 51.3 to 42.9.
- The biggest single-benchmark swing is DeepSWE: 30.5% for Kimi K2.7 Code and 53.3% for Muse Spark 1.1.
- Kimi K2.7 Code is cheaper at $0.95 / $4 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.1.
- Muse Spark 1.1 accepts more context: 1.05M tokens versus 262K.
- Kimi K2.7 Code has downloadable open weights; the other is API-only.
Side by side
| Kimi K2.7 Code | Muse Spark 1.1 | |
|---|---|---|
| Provider | Moonshot AI | Meta |
| Noometry Index | 43.3 | 49.9 |
| Released | 2026-06-12 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | 262K | 1.05M |
| Max output | 262K | 131K |
| Input $ / M tokens | $0.95 | $1.25 |
| Output $ / M tokens | $4 | $4.25 |
| Results tracked | 19 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.1 leads
Kimi K2.7 Code: 42.9 (#95), Muse Spark 1.1: 51.3 (#40)
| Benchmark | Kimi K2.7 Code | Muse Spark 1.1 |
|---|---|---|
| DeepSWE | 30.5% | 53.3% |
| LMArena WebDev | 1473 | 1542 |
| SciCode | 47.5% | 58.8% |
| FrontierCode | 30.1% | — |
| WeirdML | 54.1% | — |
| LMArena Coding | — | 1498 |
| ALE-Bench | 886.23 | — |
Agentic & Tool Use Muse Spark 1.1 leads
Kimi K2.7 Code: 24.0 (#122), Muse Spark 1.1: 30.8 (#73)
| Benchmark | Kimi K2.7 Code | Muse Spark 1.1 |
|---|---|---|
| APEX-Agents | 37.6% | 31.8% |
| GBAEval | 0.9% | 7.9% |
| Vending-Bench 2 | 5,083 | 6,520 |
| τ²-bench Banking | — | 40.5% |
| GDP.pdf | — | 15% |
Reasoning Muse Spark 1.1 leads
Kimi K2.7 Code: 39.0 (#61), Muse Spark 1.1: 47.1 (#44)
| Benchmark | Kimi K2.7 Code | Muse Spark 1.1 |
|---|---|---|
| CritPt | 10% | 15.1% |
| Surface Evolver Bench | 48.8% | 52.5% |
| Epoch Capabilities Index | 149.97 | 154.21 |
| SimpleBench | 57.9% | — |
| NYT Connections (extended) | — | 84.9% |
| Chess Puzzles | 21% | — |
| LMArena Hard Prompts | — | 1486 |
| DTBench | — | 94.4% |
| LMCA | — | 49.9% |
Math Kimi K2.7 Code leads
Kimi K2.7 Code: 52.9 (#48), Muse Spark 1.1: 45.5 (#76)
| Benchmark | Kimi K2.7 Code | Muse Spark 1.1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 54% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| ProofBench | — | 39% |
| LMArena Math | — | 1483 |
Knowledge Too close to call
Kimi K2.7 Code: 53.5 (#57), Muse Spark 1.1: 53.1 (#59)
| Benchmark | Kimi K2.7 Code | Muse Spark 1.1 |
|---|---|---|
| SimpleQA Verified | 36.5% | 57.8% |
| GPQA Diamond | 87.9% | — |
| LMArena Expert | — | 1478 |
Multimodal Not comparable
Kimi K2.7 Code: —, Muse Spark 1.1: 42.6 (#29)
| Benchmark | Kimi K2.7 Code | Muse Spark 1.1 |
|---|---|---|
| LMArena Vision | — | 1293 |
| LMArena Document | — | 1465 |
Multilingual Not comparable
Kimi K2.7 Code: —, Muse Spark 1.1: 56.7 (#17)
| Benchmark | Kimi K2.7 Code | Muse Spark 1.1 |
|---|---|---|
| LMArena Non-English | — | 1472 |
| LMArena Chinese | — | 1518 |
| LMArena French | — | 1494 |
| LMArena German | — | 1466 |
| LMArena Japanese | — | 1451 |
| LMArena Korean | — | 1458 |
| LMArena Russian | — | 1483 |
| LMArena Spanish | — | 1464 |
Instruction Following Not comparable
Kimi K2.7 Code: —, Muse Spark 1.1: 76.5 (#39)
| Benchmark | Kimi K2.7 Code | Muse Spark 1.1 |
|---|---|---|
| LMArena Instruction Following | — | 1457 |
Long Context Not comparable
Kimi K2.7 Code: —, Muse Spark 1.1: 44.8 (#58)
| Benchmark | Kimi K2.7 Code | Muse Spark 1.1 |
|---|---|---|
| LMArena Longer Query | — | 1462 |
Writing & Preference Not comparable
Kimi K2.7 Code: —, Muse Spark 1.1: 73.4 (#11)
| Benchmark | Kimi K2.7 Code | Muse Spark 1.1 |
|---|---|---|
| LMArena Text | — | 1479 |
| LMArena Creative Writing | — | 1437 |
| EQ-Bench Creative Writing | — | 1927 |
| EQ-Bench 4 | — | 1260 |
| LMArena Multi-Turn | — | 1485 |
Frequently asked questions
Is Kimi K2.7 Code better than Muse Spark 1.1?
Muse Spark 1.1 is the stronger model overall, scoring 49.9 to 43.3 on the Noometry Index.
Which is cheaper, Kimi K2.7 Code or Muse Spark 1.1?
Kimi K2.7 Code is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; Muse Spark 1.1 lists at $1.25 and $4.25.
Is Kimi K2.7 Code or Muse Spark 1.1 better for coding?
Muse Spark 1.1 scores higher on coding benchmarks: 51.3 versus 42.9 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.1 does, with 1.05M tokens against 262K.
How many benchmarks do Kimi K2.7 Code and Muse Spark 1.1 share?
10 benchmarks have published results for both models. Kimi K2.7 Code has 19 scored results on Noometry and Muse Spark 1.1 has 37.