Model comparison
DeepSeek-V3.1-Terminus vs Muse Glimmer
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 41.7 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeek
MetaSummary
- They share 12 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 6 categories and Muse Glimmer in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.0 to 57.5.
Side by side
| DeepSeek-V3.1-Terminus | Muse Glimmer | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 43.1 | 41.7 |
| Released | 2025-09-22 | 2026-08-10 |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 147K | — |
| Input $ / M tokens | $0.27 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 16 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 42.0 (#113), Muse Glimmer: 40.4 (#142)
| Benchmark | DeepSeek-V3.1-Terminus | Muse Glimmer |
|---|---|---|
| SciCode | 40.6% | 44.9% |
| LMArena Coding | 1426 | 1416 |
| LMArena WebDev | — | 1355 |
| ALE-Bench | 745.17 | — |
Reasoning Too close to call
DeepSeek-V3.1-Terminus: 26.4 (#133), Muse Glimmer: 25.7 (#144)
| Benchmark | DeepSeek-V3.1-Terminus | Muse Glimmer |
|---|---|---|
| CritPt | 1.7% | 2.6% |
| LMArena Hard Prompts | 1426 | 1396 |
| Kagi LLM Benchmark | 57.4% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
Math Too close to call
DeepSeek-V3.1-Terminus: 38.5 (#137), Muse Glimmer: 38.8 (#125)
| Benchmark | DeepSeek-V3.1-Terminus | Muse Glimmer |
|---|---|---|
| LMArena Math | 1402 | 1417 |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Muse Glimmer: 38.5 (#143)
| Benchmark | DeepSeek-V3.1-Terminus | Muse Glimmer |
|---|---|---|
| LMArena Expert | — | 1386 |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.1 (#92), Muse Glimmer: 50.5 (#122)
| Benchmark | DeepSeek-V3.1-Terminus | Muse Glimmer |
|---|---|---|
| LMArena Non-English | 1407 | 1384 |
| LMArena Russian | 1436 | 1390 |
| LMArena Chinese | — | 1412 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.0 (#106), Muse Glimmer: 72.6 (#135)
| Benchmark | DeepSeek-V3.1-Terminus | Muse Glimmer |
|---|---|---|
| LMArena Instruction Following | 1404 | 1375 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.4 (#97), Muse Glimmer: 42.1 (#129)
| Benchmark | DeepSeek-V3.1-Terminus | Muse Glimmer |
|---|---|---|
| LMArena Longer Query | 1421 | 1382 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.0 (#92), Muse Glimmer: 57.5 (#126)
| Benchmark | DeepSeek-V3.1-Terminus | Muse Glimmer |
|---|---|---|
| LMArena Text | 1419 | 1389 |
| LMArena Creative Writing | 1403 | 1339 |
| LMArena Multi-Turn | 1411 | 1399 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Muse Glimmer?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 41.7 on the Noometry Index.
Is DeepSeek-V3.1-Terminus or Muse Glimmer better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 40.4 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1-Terminus and Muse Glimmer share?
12 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Muse Glimmer has 15.