Model comparison
DeepSeek V4 Pro vs Muse Spark 1.1
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 49.9 on the Noometry Index.
Last verified . 31 shared benchmarks.
DeepSeek
MetaSummary
- They share 31 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 6 categories and Muse Spark 1.1 in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4 Pro leads 64.8 to 45.5.
- The biggest single-benchmark swing is APEX-Agents: 47.3% for DeepSeek V4 Pro and 31.8% for Muse Spark 1.1.
- DeepSeek V4 Pro is cheaper at $0.66 / $1.98 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.1.
- Muse Spark 1.1 accepts more context: 1.05M tokens versus 1M.
- DeepSeek V4 Pro has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4 Pro | Muse Spark 1.1 | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 54.3 | 49.9 |
| Released | 2026-04-24 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 393K | 131K |
| Input $ / M tokens | $0.66 | $1.25 |
| Output $ / M tokens | $1.98 | $4.25 |
| Results tracked | 48 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Pro leads
DeepSeek V4 Pro: 52.4 (#34), Muse Spark 1.1: 51.3 (#40)
| Benchmark | DeepSeek V4 Pro | Muse Spark 1.1 |
|---|---|---|
| LMArena WebDev | 1582 | 1542 |
| SciCode | 51% | 58.8% |
| LMArena Coding | 1470 | 1498 |
| SWE-bench Verified | 77.6% | — |
| DeepSWE | — | 53.3% |
| FrontierCode | 28.6% | — |
| WeirdML | 66.2% | — |
| ALE-Bench | 1,403 | — |
Agentic & Tool Use DeepSeek V4 Pro leads
DeepSeek V4 Pro: 32.8 (#58), Muse Spark 1.1: 30.8 (#73)
| Benchmark | DeepSeek V4 Pro | Muse Spark 1.1 |
|---|---|---|
| APEX-Agents | 47.3% | 31.8% |
| Vending-Bench 2 | 3,285 | 6,520 |
| τ²-bench Banking | — | 40.5% |
| GBAEval | — | 7.9% |
| GDP.pdf | — | 15% |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.5 (#24), Muse Spark 1.1: 47.1 (#44)
| Benchmark | DeepSeek V4 Pro | Muse Spark 1.1 |
|---|---|---|
| NYT Connections (extended) | 91.3% | 84.9% |
| CritPt | 18% | 15.1% |
| LMArena Hard Prompts | 1461 | 1486 |
| DTBench | 93.9% | 94.4% |
| LMCA | 45.5% | 49.9% |
| Surface Evolver Bench | 40% | 52.5% |
| Epoch Capabilities Index | 155.31 | 154.21 |
| ARC-AGI-2 | 61.3% | — |
| Kagi LLM Benchmark | 53.5% | — |
| ARC-AGI-1 | 90.5% | — |
| Chess Puzzles | 47% | — |
| Mystery Game Puzzles | 43% | — |
| ForecastBench | 56.1 | — |
Math DeepSeek V4 Pro leads
DeepSeek V4 Pro: 64.8 (#30), Muse Spark 1.1: 45.5 (#76)
| Benchmark | DeepSeek V4 Pro | Muse Spark 1.1 |
|---|---|---|
| ProofBench | 50% | 39% |
| LMArena Math | 1455 | 1483 |
| FrontierMath (Tiers 1-3) | 64.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.6% | — |
| OTIS Mock AIME 2024-2025 | 98.6% | — |
Knowledge DeepSeek V4 Pro leads
DeepSeek V4 Pro: 59.5 (#31), Muse Spark 1.1: 53.1 (#59)
| Benchmark | DeepSeek V4 Pro | Muse Spark 1.1 |
|---|---|---|
| SimpleQA Verified | 52.9% | 57.8% |
| LMArena Expert | 1464 | 1478 |
| GPQA Diamond | 91.7% | — |
| Vectara Hallucination Rate | 8.6% | — |
Multimodal Not comparable
DeepSeek V4 Pro: —, Muse Spark 1.1: 42.6 (#29)
| Benchmark | DeepSeek V4 Pro | Muse Spark 1.1 |
|---|---|---|
| LMArena Vision | — | 1293 |
| LMArena Document | — | 1465 |
Multilingual Muse Spark 1.1 leads
DeepSeek V4 Pro: 54.4 (#45), Muse Spark 1.1: 56.7 (#17)
| Benchmark | DeepSeek V4 Pro | Muse Spark 1.1 |
|---|---|---|
| LMArena Non-English | 1439 | 1472 |
| LMArena Chinese | 1486 | 1518 |
| LMArena French | 1472 | 1494 |
| LMArena German | 1458 | 1466 |
| LMArena Japanese | 1445 | 1451 |
| LMArena Korean | 1447 | 1458 |
| LMArena Russian | 1453 | 1483 |
| LMArena Spanish | 1458 | 1464 |
Instruction Following Too close to call
DeepSeek V4 Pro: 76.1 (#47), Muse Spark 1.1: 76.5 (#39)
| Benchmark | DeepSeek V4 Pro | Muse Spark 1.1 |
|---|---|---|
| LMArena Instruction Following | 1448 | 1457 |
Long Context Too close to call
DeepSeek V4 Pro: 45.0 (#51), Muse Spark 1.1: 44.8 (#58)
| Benchmark | DeepSeek V4 Pro | Muse Spark 1.1 |
|---|---|---|
| LMArena Longer Query | 1458 | 1462 |
| CL-bench Life | 13.5% | — |
Writing & Preference Muse Spark 1.1 leads
DeepSeek V4 Pro: 65.5 (#46), Muse Spark 1.1: 73.4 (#11)
| Benchmark | DeepSeek V4 Pro | Muse Spark 1.1 |
|---|---|---|
| LMArena Text | 1451 | 1479 |
| LMArena Creative Writing | 1446 | 1437 |
| EQ-Bench Creative Writing | 1553 | 1927 |
| EQ-Bench 4 | 1166 | 1260 |
| LMArena Multi-Turn | 1467 | 1485 |
Frequently asked questions
Is DeepSeek V4 Pro better than Muse Spark 1.1?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 49.9 on the Noometry Index.
Which is cheaper, DeepSeek V4 Pro or Muse Spark 1.1?
DeepSeek V4 Pro is cheaper. It lists at $0.66 per million input tokens and $1.98 per million output tokens; Muse Spark 1.1 lists at $1.25 and $4.25.
Is DeepSeek V4 Pro or Muse Spark 1.1 better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 51.3 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.1 does, with 1.05M tokens against 1M.
How many benchmarks do DeepSeek V4 Pro and Muse Spark 1.1 share?
31 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Muse Spark 1.1 has 37.