Model comparison
DeepSeek-V2.5 (Sep 2024) vs Muse Spark 1.3
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 37.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
MetaSummary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and Muse Spark 1.3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 73.1 to 35.9.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Muse Spark 1.3 | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 37.6 | 54.8 |
| Released | 2024-09-06 | 2026-09-02 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 131K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $4.25 |
| Results tracked | 22 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Muse Spark 1.3: 56.6 (#21)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark 1.3 |
|---|---|---|
| LMArena Coding | 1309 | 1514 |
| Aider Polyglot | 17.8% | — |
| CursorBench | — | 41.6% |
| LMArena WebDev | — | 1657 |
| SciCode | — | 59.7% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2.5 (Sep 2024): —, Muse Spark 1.3: 38.6 (#30)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark 1.3 |
|---|---|---|
| APEX-Agents | — | 57.8% |
| GDP.pdf | — | 27.6% |
Reasoning Muse Spark 1.3 leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Muse Spark 1.3: 54.0 (#27)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark 1.3 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1503 |
| NYT Connections (extended) | — | 85.1% |
| CritPt | — | 26% |
| Chess Puzzles | — | 38% |
| Mystery Game Puzzles | — | 25% |
| DTBench | — | 96.5% |
| LMCA | — | 53.9% |
| Bench to the Future 3 | — | 0.14 |
| Epoch Capabilities Index | — | 156.75 |
Math Muse Spark 1.3 leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Muse Spark 1.3: 73.1 (#21)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark 1.3 |
|---|---|---|
| LMArena Math | 1288 | 1494 |
| FrontierMath (Tiers 1-3) | — | 74.4% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 99.2% |
| ProofBench | — | 58% |
Knowledge Muse Spark 1.3 leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Muse Spark 1.3: 42.6 (#95)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1266 | 1516 |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, Muse Spark 1.3: 43.7 (#22)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | — | 1309 |
| LMArena Document | — | 1471 |
Multilingual Muse Spark 1.3 leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Muse Spark 1.3: 57.4 (#8)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1273 | 1481 |
| LMArena Chinese | 1318 | 1529 |
| LMArena French | 1289 | 1524 |
| LMArena German | 1258 | 1515 |
| LMArena Japanese | 1228 | 1474 |
| LMArena Korean | 1209 | 1501 |
| LMArena Russian | 1289 | 1490 |
| LMArena Spanish | 1248 | 1490 |
Instruction Following Muse Spark 1.3 leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Muse Spark 1.3: 77.5 (#22)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1477 |
Long Context Muse Spark 1.3 leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Muse Spark 1.3: 45.6 (#32)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1301 | 1488 |
Writing & Preference Muse Spark 1.3 leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Muse Spark 1.3: 73.6 (#9)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1294 | 1490 |
| LMArena Creative Writing | 1285 | 1455 |
| LMArena Multi-Turn | 1297 | 1482 |
| EQ-Bench Creative Writing | — | 1906 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Muse Spark 1.3?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Muse Spark 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Muse Spark 1.3 share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Muse Spark 1.3 has 37.