Model comparison
DeepSeek LLM 67B vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.6 to 24.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
DeepSeek
MetaSummary
- They share 13 benchmarks with published results for both. DeepSeek LLM 67B 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 7.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 88.9% for Muse Spark.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | Muse Spark | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 24.9 | 50.6 |
| Released | 2023-11-29 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
DeepSeek LLM 67B: 31.9 (#278), Muse Spark: 46.2 (#69)
| Benchmark | DeepSeek LLM 67B | Muse Spark |
|---|---|---|
| LMArena Coding | 1096 | 1481 |
| SciCode | — | 51.5% |
Reasoning Muse Spark leads
DeepSeek LLM 67B: 16.5 (#304), Muse Spark: 35.9 (#67)
| Benchmark | DeepSeek LLM 67B | Muse Spark |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1474 |
| Epoch Capabilities Index | 110.5 | 152.04 |
| CritPt | — | 11.3% |
| Chess Puzzles | 0% | — |
Math Muse Spark leads
DeepSeek LLM 67B: 8.7 (#324), Muse Spark: 47.8 (#66)
| Benchmark | DeepSeek LLM 67B | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 88.9% |
| LMArena Math | 1108 | 1455 |
| ProofBench | — | 17% |
| MATH Level 5 | 6.4% | — |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Muse Spark leads
DeepSeek LLM 67B: 7.0 (#313), Muse Spark: 65.7 (#13)
| Benchmark | DeepSeek LLM 67B | Muse Spark |
|---|---|---|
| GPQA Diamond | 24.6% | 89.8% |
| Humanity's Last Exam | — | 40.6% |
| LMArena Expert | — | 1457 |
Multimodal Not comparable
DeepSeek LLM 67B: —, Muse Spark: 43.4 (#24)
| Benchmark | DeepSeek LLM 67B | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |
Multilingual Muse Spark leads
DeepSeek LLM 67B: 29.4 (#267), Muse Spark: 56.1 (#24)
| Benchmark | DeepSeek LLM 67B | Muse Spark |
|---|---|---|
| LMArena Non-English | 1073 | 1464 |
| LMArena Chinese | 1132 | 1509 |
| LMArena French | — | 1497 |
| LMArena German | — | 1497 |
| LMArena Korean | — | 1459 |
| LMArena Russian | — | 1466 |
| LMArena Spanish | — | 1472 |
Instruction Following Muse Spark leads
DeepSeek LLM 67B: 55.4 (#277), Muse Spark: 75.9 (#51)
| Benchmark | DeepSeek LLM 67B | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1079 | 1442 |
Long Context Muse Spark leads
DeepSeek LLM 67B: 33.1 (#265), Muse Spark: 44.4 (#69)
| Benchmark | DeepSeek LLM 67B | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1092 | 1451 |
Writing & Preference Muse Spark leads
DeepSeek LLM 67B: 31.6 (#282), Muse Spark: 66.0 (#39)
| Benchmark | DeepSeek LLM 67B | Muse Spark |
|---|---|---|
| LMArena Text | 1105 | 1474 |
| LMArena Creative Writing | 1067 | 1459 |
| LMArena Multi-Turn | 1082 | 1477 |
Frequently asked questions
Is DeepSeek LLM 67B better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.6 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Muse Spark better for coding?
Muse Spark scores higher on coding benchmarks: 46.2 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Muse Spark share?
13 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Muse Spark has 27.