Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Muse Spark
Muse Spark has enough public results to be ranked (#41); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
DeepSeek
MetaSummary
- They share 1 benchmark with published results for both. DeepSeek-V2 (MoE-236B, May 2024) scores higher in 0 categories and Muse Spark in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where Muse Spark leads 45.6 to 39.8.
- DeepSeek-V2 (MoE-236B, May 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | Muse Spark | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 39.7 | 50.3 |
| Released | 2024-05-07 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
DeepSeek-V2 (MoE-236B, May 2024): 39.8 (#141), Muse Spark: 45.6 (#65)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Muse Spark |
|---|---|---|
| SciCode | — | 51.5% |
| BigCodeBench Instruct | 48.9% | — |
| LMArena Coding | — | 1482 |
| BigCodeBench Complete | 59.4% | — |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Muse Spark: 34.9 (#61)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Muse Spark |
|---|---|---|
| Epoch Capabilities Index | 124.78 | 152.09 |
| CritPt | — | 11.3% |
| LMArena Hard Prompts | — | 1475 |
| BIG-Bench Hard | 78.8% | — |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Muse Spark: 46.8 (#57)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 17% |
| LMArena Math | — | 1455 |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Muse Spark: 65.7 (#12)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Muse Spark |
|---|---|---|
| GPQA Diamond | — | 89.8% |
| Humanity's Last Exam | — | 40.6% |
| LMArena Expert | — | 1458 |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |
Multimodal Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Muse Spark: 42.7 (#23)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Muse Spark: 56.3 (#23)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | 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
DeepSeek-V2 (MoE-236B, May 2024): —, Muse Spark: 76.1 (#47)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Muse Spark |
|---|---|---|
| LMArena Instruction Following | — | 1443 |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Muse Spark: 44.4 (#65)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Muse Spark |
|---|---|---|
| LMArena Longer Query | — | 1451 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Muse Spark: 66.2 (#37)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Muse Spark |
|---|---|---|
| LMArena Text | — | 1474 |
| LMArena Creative Writing | — | 1460 |
| LMArena Multi-Turn | — | 1477 |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Muse Spark?
Muse Spark has enough public results to be ranked (#41); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or Muse Spark better for coding?
Muse Spark scores higher on coding benchmarks: 45.6 versus 39.8 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Muse Spark share?
1 benchmark has published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Muse Spark has 27.