Model comparison
DeepSeek V4 Pro vs Muse Glimmer
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 41.7 on the Noometry Index.
Last verified . 15 shared benchmarks.
DeepSeek
MetaSummary
- They share 15 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 8 categories and Muse Glimmer in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.5 to 25.7.
- The biggest single-benchmark swing is CritPt: 18% for DeepSeek V4 Pro and 2.6% for Muse Glimmer.
Side by side
| DeepSeek V4 Pro | Muse Glimmer | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 54.3 | 41.7 |
| Released | 2026-04-24 | 2026-08-10 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.66 | — |
| Output $ / M tokens | $1.98 | — |
| Results tracked | 48 | 15 |
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 Glimmer: 40.4 (#142)
| Benchmark | DeepSeek V4 Pro | Muse Glimmer |
|---|---|---|
| LMArena WebDev | 1582 | 1355 |
| SciCode | 51% | 44.9% |
| LMArena Coding | 1470 | 1416 |
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| WeirdML | 66.2% | — |
| ALE-Bench | 1,403 | — |
Agentic & Tool Use Not comparable
DeepSeek V4 Pro: 32.8 (#58), Muse Glimmer: —
| Benchmark | DeepSeek V4 Pro | Muse Glimmer |
|---|---|---|
| APEX-Agents | 47.3% | — |
| Vending-Bench 2 | 3,285 | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.5 (#24), Muse Glimmer: 25.7 (#144)
| Benchmark | DeepSeek V4 Pro | Muse Glimmer |
|---|---|---|
| CritPt | 18% | 2.6% |
| LMArena Hard Prompts | 1461 | 1396 |
| ARC-AGI-2 | 61.3% | — |
| Kagi LLM Benchmark | 53.5% | — |
| NYT Connections (extended) | 91.3% | — |
| ARC-AGI-1 | 90.5% | — |
| Chess Puzzles | 47% | — |
| Mystery Game Puzzles | 43% | — |
| DTBench | 93.9% | — |
| LMCA | 45.5% | — |
| Surface Evolver Bench | 40% | — |
| Epoch Capabilities Index | 155.31 | — |
| ForecastBench | 56.1 | — |
Math DeepSeek V4 Pro leads
DeepSeek V4 Pro: 64.8 (#30), Muse Glimmer: 38.8 (#125)
| Benchmark | DeepSeek V4 Pro | Muse Glimmer |
|---|---|---|
| LMArena Math | 1455 | 1417 |
| FrontierMath (Tiers 1-3) | 64.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.6% | — |
| OTIS Mock AIME 2024-2025 | 98.6% | — |
| ProofBench | 50% | — |
Knowledge DeepSeek V4 Pro leads
DeepSeek V4 Pro: 59.5 (#31), Muse Glimmer: 38.5 (#143)
| Benchmark | DeepSeek V4 Pro | Muse Glimmer |
|---|---|---|
| LMArena Expert | 1464 | 1386 |
| GPQA Diamond | 91.7% | — |
| SimpleQA Verified | 52.9% | — |
| Vectara Hallucination Rate | 8.6% | — |
Multilingual DeepSeek V4 Pro leads
DeepSeek V4 Pro: 54.4 (#45), Muse Glimmer: 50.5 (#122)
| Benchmark | DeepSeek V4 Pro | Muse Glimmer |
|---|---|---|
| LMArena Non-English | 1439 | 1384 |
| LMArena Chinese | 1486 | 1412 |
| LMArena Russian | 1453 | 1390 |
| LMArena French | 1472 | — |
| LMArena German | 1458 | — |
| LMArena Japanese | 1445 | — |
| LMArena Korean | 1447 | — |
| LMArena Spanish | 1458 | — |
Instruction Following DeepSeek V4 Pro leads
DeepSeek V4 Pro: 76.1 (#47), Muse Glimmer: 72.6 (#135)
| Benchmark | DeepSeek V4 Pro | Muse Glimmer |
|---|---|---|
| LMArena Instruction Following | 1448 | 1375 |
Long Context DeepSeek V4 Pro leads
DeepSeek V4 Pro: 45.0 (#51), Muse Glimmer: 42.1 (#129)
| Benchmark | DeepSeek V4 Pro | Muse Glimmer |
|---|---|---|
| LMArena Longer Query | 1458 | 1382 |
| CL-bench Life | 13.5% | — |
Writing & Preference DeepSeek V4 Pro leads
DeepSeek V4 Pro: 65.5 (#46), Muse Glimmer: 57.5 (#126)
| Benchmark | DeepSeek V4 Pro | Muse Glimmer |
|---|---|---|
| LMArena Text | 1451 | 1389 |
| LMArena Creative Writing | 1446 | 1339 |
| LMArena Multi-Turn | 1467 | 1399 |
| EQ-Bench Creative Writing | 1553 | — |
| EQ-Bench 4 | 1166 | — |
Frequently asked questions
Is DeepSeek V4 Pro better than Muse Glimmer?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 41.7 on the Noometry Index.
Is DeepSeek V4 Pro or Muse Glimmer better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 40.4 in the Noometry coding category.
How many benchmarks do DeepSeek V4 Pro and Muse Glimmer share?
15 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Muse Glimmer has 15.