Model comparison
DeepSeek-V3.1-Terminus vs Muse Spark 1.2
Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 42.6 on the Noometry Index. DeepSeek-V3.1-Terminus costs 4.2× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.
Last verified . 13 shared benchmarks.
DeepSeek
MetaSummary
- They share 13 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 0 categories and Muse Spark 1.2 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 50.4 to 25.7.
- The biggest single-benchmark swing is LMCA: 28.6% for DeepSeek-V3.1-Terminus and 48.4% for Muse Spark 1.2.
- DeepSeek-V3.1-Terminus is cheaper at $0.30 / $1 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.2.
- Muse Spark 1.2 accepts more context: 1.05M tokens versus 164K.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1-Terminus | Muse Spark 1.2 | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 42.6 | 49.8 |
| Released | 2025-09-22 | 2026-08-05 |
| Weights | Open | Proprietary |
| Context window | 164K | 1.05M |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.30 | $1.25 |
| Output $ / M tokens | $1 | $4.25 |
| Results tracked | 16 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.2 leads
DeepSeek-V3.1-Terminus: 41.5 (#114), Muse Spark 1.2: 48.6 (#49)
| Benchmark | DeepSeek-V3.1-Terminus | Muse Spark 1.2 |
|---|---|---|
| SciCode | 40.6% | 56.4% |
| LMArena Coding | 1426 | 1497 |
| DeepSWE | — | 54.9% |
| LMArena WebDev | — | 1532 |
| FrontierSWE | — | 12% |
| WeirdML | — | 60.3% |
| ALE-Bench | 745.17 | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, Muse Spark 1.2: 29.5 (#77)
| Benchmark | DeepSeek-V3.1-Terminus | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | — | 36.4% |
| GDP.pdf | — | 16% |
Reasoning Muse Spark 1.2 leads
DeepSeek-V3.1-Terminus: 25.7 (#126), Muse Spark 1.2: 50.4 (#32)
| Benchmark | DeepSeek-V3.1-Terminus | Muse Spark 1.2 |
|---|---|---|
| CritPt | 1.7% | 17.7% |
| LMArena Hard Prompts | 1427 | 1490 |
| DTBench | 81.3% | 94.7% |
| LMCA | 28.6% | 48.4% |
| SimpleBench | — | 74.5% |
| Kagi LLM Benchmark | 57.4% | — |
| NYT Connections (extended) | — | 79.2% |
| Epoch Capabilities Index | — | 155.18 |
Math Muse Spark 1.2 leads
DeepSeek-V3.1-Terminus: 35.7 (#138), Muse Spark 1.2: 43.8 (#68)
| Benchmark | DeepSeek-V3.1-Terminus | Muse Spark 1.2 |
|---|---|---|
| ProofBench | — | 43% |
| LMArena Math | 1402 | — |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Muse Spark 1.2: 53.9 (#49)
| Benchmark | DeepSeek-V3.1-Terminus | Muse Spark 1.2 |
|---|---|---|
| SimpleQA Verified | — | 60.3% |
| LMArena Expert | — | 1485 |
Multimodal Not comparable
DeepSeek-V3.1-Terminus: —, Muse Spark 1.2: 42.6 (#24)
| Benchmark | DeepSeek-V3.1-Terminus | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | — | 1304 |
Multilingual Muse Spark 1.2 leads
DeepSeek-V3.1-Terminus: 52.3 (#87), Muse Spark 1.2: 57.4 (#10)
| Benchmark | DeepSeek-V3.1-Terminus | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1407 | 1479 |
| LMArena Russian | 1434 | 1494 |
| LMArena Chinese | — | 1519 |
Instruction Following Muse Spark 1.2 leads
DeepSeek-V3.1-Terminus: 74.4 (#96), Muse Spark 1.2: 77.1 (#30)
| Benchmark | DeepSeek-V3.1-Terminus | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1406 | 1466 |
Long Context Muse Spark 1.2 leads
DeepSeek-V3.1-Terminus: 43.5 (#88), Muse Spark 1.2: 45.4 (#35)
| Benchmark | DeepSeek-V3.1-Terminus | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1426 | 1483 |
Writing & Preference Muse Spark 1.2 leads
DeepSeek-V3.1-Terminus: 61.3 (#87), Muse Spark 1.2: 72.6 (#14)
| Benchmark | DeepSeek-V3.1-Terminus | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1420 | 1486 |
| LMArena Creative Writing | 1404 | 1444 |
| LMArena Multi-Turn | 1411 | 1504 |
| EQ-Bench Creative Writing | — | 1840 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Muse Spark 1.2?
Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 42.6 on the Noometry Index. DeepSeek-V3.1-Terminus costs 4.2× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.1-Terminus or Muse Spark 1.2?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.30 per million input tokens and $1 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.
Is DeepSeek-V3.1-Terminus or Muse Spark 1.2 better for coding?
Muse Spark 1.2 scores higher on coding benchmarks: 48.6 versus 41.5 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.2 does, with 1.05M tokens against 164K.
How many benchmarks do DeepSeek-V3.1-Terminus and Muse Spark 1.2 share?
13 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Muse Spark 1.2 has 28.