Model comparison
Kimi K3 vs Muse Spark
Kimi K3 is the stronger model overall, scoring 59.5 to 50.6 on the Noometry Index.
Last verified . 22 shared benchmarks.
MetaSummary
- They share 22 benchmarks with published results for both. Kimi K3 scores higher in 7 categories and Muse Spark in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K3 leads 63.0 to 35.9.
- The biggest single-benchmark swing is ProofBench: 87% for Kimi K3 and 17% for Muse Spark.
- Kimi K3 has downloadable open weights; the other is API-only.
Side by side
| Kimi K3 | Muse Spark | |
|---|---|---|
| Provider | Moonshot AI | Meta |
| Noometry Index | 59.5 | 50.6 |
| Released | 2026-07-16 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | 1.05M | — |
| Max output | 1.05M | — |
| Input $ / M tokens | $3 | — |
| Output $ / M tokens | $15 | — |
| Results tracked | 53 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Kimi K3: 61.0 (#10), Muse Spark: 46.2 (#69)
| Benchmark | Kimi K3 | Muse Spark |
|---|---|---|
| SciCode | 59.5% | 51.5% |
| LMArena Coding | 1508 | 1481 |
| DeepSWE | 68.5% | — |
| FrontierCode | 44.2% | — |
| LMArena WebDev | 1654 | — |
| FrontierSWE | 25.9% | — |
| WeirdML | 82.6% | — |
| ALE-Bench | 1,524 | — |
Agentic & Tool Use Not comparable
Kimi K3: 41.8 (#20), Muse Spark: —
| Benchmark | Kimi K3 | Muse Spark |
|---|---|---|
| APEX-Agents | 50.6% | — |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 32% | — |
| GBAEval | 48.3% | — |
| GDP.pdf | 19% | — |
| Vending-Bench 2 | 5,165 | — |
Reasoning Kimi K3 leads
Kimi K3: 63.0 (#17), Muse Spark: 35.9 (#67)
| Benchmark | Kimi K3 | Muse Spark |
|---|---|---|
| CritPt | 23.4% | 11.3% |
| LMArena Hard Prompts | 1496 | 1474 |
| Epoch Capabilities Index | 157.45 | 152.04 |
| ARC-AGI-2 | 60.4% | — |
| SimpleBench | 60.7% | — |
| NYT Connections (extended) | 93.6% | — |
| ARC-AGI-1 | 94.5% | — |
| Chess Puzzles | 39% | — |
| Mystery Game Puzzles | 26% | — |
| DTBench | 91.2% | — |
| LMCA | 52.7% | — |
| Surface Evolver Bench | 95% | — |
| ForecastBench | 61.1 | — |
Math Kimi K3 leads
Kimi K3: 74.2 (#16), Muse Spark: 47.8 (#66)
| Benchmark | Kimi K3 | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 97.2% | 88.9% |
| ProofBench | 87% | 17% |
| LMArena Math | 1491 | 1455 |
| FrontierMath (Tiers 1-3) | 72.2% | — |
| FrontierMath Tier 4 | 39% | — |
| MathArena Final-Answer Competitions | 87.8% | — |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Muse Spark leads
Kimi K3: 63.2 (#21), Muse Spark: 65.7 (#13)
| Benchmark | Kimi K3 | Muse Spark |
|---|---|---|
| GPQA Diamond | 93.1% | 89.8% |
| LMArena Expert | 1521 | 1457 |
| Humanity's Last Exam | — | 40.6% |
| SimpleQA Verified | 50.6% | — |
Multimodal Muse Spark leads
Kimi K3: 37.8 (#70), Muse Spark: 43.4 (#24)
| Benchmark | Kimi K3 | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| Blueprint-Bench 2 | 29.5% | — |
| Furniture Assembly | 34.2% | — |
| LMArena Document | — | 1444 |
Multilingual Too close to call
Kimi K3: 56.3 (#21), Muse Spark: 56.1 (#24)
| Benchmark | Kimi K3 | Muse Spark |
|---|---|---|
| LMArena Non-English | 1466 | 1464 |
| LMArena Chinese | 1529 | 1509 |
| LMArena French | 1491 | 1497 |
| LMArena German | 1488 | 1497 |
| LMArena Korean | 1458 | 1459 |
| LMArena Russian | 1482 | 1466 |
| LMArena Spanish | 1472 | 1472 |
| LMArena Japanese | 1487 | — |
Instruction Following Kimi K3 leads
Kimi K3: 77.7 (#14), Muse Spark: 75.9 (#51)
| Benchmark | Kimi K3 | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1483 | 1442 |
Long Context Kimi K3 leads
Kimi K3: 45.8 (#29), Muse Spark: 44.4 (#69)
| Benchmark | Kimi K3 | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1494 | 1451 |
Writing & Preference Kimi K3 leads
Kimi K3: 76.6 (#4), Muse Spark: 66.0 (#39)
| Benchmark | Kimi K3 | Muse Spark |
|---|---|---|
| LMArena Text | 1476 | 1474 |
| LMArena Creative Writing | 1454 | 1459 |
| LMArena Multi-Turn | 1488 | 1477 |
| EQ-Bench Creative Writing | 2082 | — |
| EQ-Bench 4 | 1339 | — |
Frequently asked questions
Is Kimi K3 better than Muse Spark?
Kimi K3 is the stronger model overall, scoring 59.5 to 50.6 on the Noometry Index.
Is Kimi K3 or Muse Spark better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 46.2 in the Noometry coding category.
How many benchmarks do Kimi K3 and Muse Spark share?
22 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and Muse Spark has 27.