Model comparison
DeepSeek-V3.1-Terminus vs Wizardlm 13b
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 31.4 on the Noometry Index.
Last verified . 9 shared benchmarks.
DeepSeek
MicrosoftSummary
- They share 9 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and Wizardlm 13b in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.0 to 30.5.
Side by side
| DeepSeek-V3.1-Terminus | Wizardlm 13b | |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 43.1 | 31.4 |
| Released | 2025-09-22 | — |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 147K | — |
| Input $ / M tokens | $0.27 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 16 | 10 |
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), Wizardlm 13b: 30.1 (#298)
| Benchmark | DeepSeek-V3.1-Terminus | Wizardlm 13b |
|---|---|---|
| LMArena Coding | 1426 | 1035 |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 26.4 (#133), Wizardlm 13b: 19.4 (#259)
| Benchmark | DeepSeek-V3.1-Terminus | Wizardlm 13b |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1018 |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 38.5 (#137), Wizardlm 13b: 30.2 (#238)
| Benchmark | DeepSeek-V3.1-Terminus | Wizardlm 13b |
|---|---|---|
| LMArena Math | 1402 | 1017 |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.1 (#92), Wizardlm 13b: 27.1 (#277)
| Benchmark | DeepSeek-V3.1-Terminus | Wizardlm 13b |
|---|---|---|
| LMArena Non-English | 1407 | 1034 |
| LMArena Chinese | — | 1023 |
| LMArena Russian | 1436 | — |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.0 (#106), Wizardlm 13b: 53.5 (#285)
| Benchmark | DeepSeek-V3.1-Terminus | Wizardlm 13b |
|---|---|---|
| LMArena Instruction Following | 1404 | 1048 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.4 (#97), Wizardlm 13b: 32.0 (#273)
| Benchmark | DeepSeek-V3.1-Terminus | Wizardlm 13b |
|---|---|---|
| LMArena Longer Query | 1421 | 1054 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.0 (#92), Wizardlm 13b: 30.5 (#287)
| Benchmark | DeepSeek-V3.1-Terminus | Wizardlm 13b |
|---|---|---|
| LMArena Text | 1419 | 1077 |
| LMArena Creative Writing | 1403 | 1091 |
| LMArena Multi-Turn | 1411 | 1047 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Wizardlm 13b?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 31.4 on the Noometry Index.
Is DeepSeek-V3.1-Terminus or Wizardlm 13b better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 30.1 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1-Terminus and Wizardlm 13b share?
9 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Wizardlm 13b has 10.