Model comparison
DeepSeek-R1 vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.6 to 42.3 on the Noometry Index.
Last verified . 21 shared benchmarks.
DeepSeek
MetaSummary
- They share 21 benchmarks with published results for both. DeepSeek-R1 scores higher in 2 categories and Muse Spark in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 44.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 66.4% for DeepSeek-R1 and 88.9% for Muse Spark.
Side by side
| DeepSeek-R1 | Muse Spark | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 42.3 | 50.6 |
| Released | 2025-01-20 | 2026-04-08 |
| Weights | Proprietary | Proprietary |
| Context window | 164K | — |
| Max output | 64K | — |
| Input $ / M tokens | $0.50 | — |
| Output $ / M tokens | $2.15 | — |
| Results tracked | 52 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek-R1: 46.3 (#68), Muse Spark: 46.2 (#69)
| Benchmark | DeepSeek-R1 | Muse Spark |
|---|---|---|
| SciCode | 35.7% | 51.5% |
| LMArena Coding | 1427 | 1481 |
| Aider Polyglot | 71.4% | — |
| WeirdML | 41.6% | — |
| LiveBench Coding | 66.7% | — |
| ALE-Bench | 804.12 | — |
| AlgoTune | 1.7 | — |
Agentic & Tool Use Not comparable
DeepSeek-R1: 30.7 (#75), Muse Spark: —
| Benchmark | DeepSeek-R1 | Muse Spark |
|---|---|---|
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |
Reasoning Muse Spark leads
DeepSeek-R1: 18.6 (#278), Muse Spark: 35.9 (#67)
| Benchmark | DeepSeek-R1 | Muse Spark |
|---|---|---|
| CritPt | 1.1% | 11.3% |
| LMArena Hard Prompts | 1416 | 1474 |
| Epoch Capabilities Index | 141.29 | 152.04 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 40.8% | — |
| Kagi LLM Benchmark | 69.4% | — |
| ARC-AGI-1 | 21.2% | — |
| LiveBench Reasoning | 83.2% | — |
| LiveBench Data Analysis | 69.8% | — |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |
Math Muse Spark leads
DeepSeek-R1: 43.8 (#79), Muse Spark: 47.8 (#66)
| Benchmark | DeepSeek-R1 | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.4% | 88.9% |
| LMArena Math | 1400 | 1455 |
| ProofBench | — | 17% |
| Omni-MATH | 42.4% | — |
| LiveBench Math | 80.7% | — |
| MATH Level 5 | 96.6% | — |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Muse Spark leads
DeepSeek-R1: 44.5 (#87), Muse Spark: 65.7 (#13)
| Benchmark | DeepSeek-R1 | Muse Spark |
|---|---|---|
| GPQA Diamond | 76.3% | 89.8% |
| LMArena Expert | 1394 | 1457 |
| Humanity's Last Exam | — | 40.6% |
| MMLU-Pro | 79.3% | — |
| Confabulations | 12.7% | — |
| Vectara Hallucination Rate | 11.3% | — |
| GPQA (HELM) | 66.6% | — |
Multimodal Not comparable
DeepSeek-R1: —, Muse Spark: 43.4 (#24)
| Benchmark | DeepSeek-R1 | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |
Multilingual Muse Spark leads
DeepSeek-R1: 52.4 (#85), Muse Spark: 56.1 (#24)
| Benchmark | DeepSeek-R1 | Muse Spark |
|---|---|---|
| LMArena Non-English | 1412 | 1464 |
| LMArena Chinese | 1442 | 1509 |
| LMArena French | 1417 | 1497 |
| LMArena German | 1404 | 1497 |
| LMArena Korean | 1360 | 1459 |
| LMArena Russian | 1423 | 1466 |
| LMArena Spanish | 1411 | 1472 |
| LMArena Japanese | 1391 | — |
Instruction Following Muse Spark leads
DeepSeek-R1: 72.0 (#143), Muse Spark: 75.9 (#51)
| Benchmark | DeepSeek-R1 | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1382 | 1442 |
| LiveBench Instruction Following | 80.5% | — |
| IFEval | 78.4% | — |
Long Context DeepSeek-R1 leads
DeepSeek-R1: 45.4 (#36), Muse Spark: 44.4 (#69)
| Benchmark | DeepSeek-R1 | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1391 | 1451 |
| Fiction.LiveBench | 75% | — |
Writing & Preference Muse Spark leads
DeepSeek-R1: 61.4 (#88), Muse Spark: 66.0 (#39)
| Benchmark | DeepSeek-R1 | Muse Spark |
|---|---|---|
| LMArena Text | 1428 | 1474 |
| LMArena Creative Writing | 1405 | 1459 |
| LMArena Multi-Turn | 1405 | 1477 |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1500 | — |
| WildBench | 82.8% | — |
| LiveBench Language | 48.5% | — |
Frequently asked questions
Is DeepSeek-R1 better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.6 to 42.3 on the Noometry Index.
Is DeepSeek-R1 or Muse Spark better for coding?
They score almost the same on coding (46.3 vs 46.2); test both on your own repository before choosing.
How many benchmarks do DeepSeek-R1 and Muse Spark share?
21 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Muse Spark has 27.