Model comparison
DeepSeek-V3.1 vs Wizardlm 70b
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 33.0 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeek
MicrosoftSummary
- They share 12 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 7 categories and Wizardlm 70b in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.3 to 34.8.
Side by side
| DeepSeek-V3.1 | Wizardlm 70b | |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 42.8 | 33.0 |
| Released | 2025-08-21 | — |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.95 | — |
| Results tracked | 27 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1 leads
DeepSeek-V3.1: 40.3 (#144), Wizardlm 70b: 31.4 (#285)
| Benchmark | DeepSeek-V3.1 | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1417 | 1081 |
| WeirdML | 38.4% | — |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.9 (#110), Wizardlm 70b: 20.7 (#234)
| Benchmark | DeepSeek-V3.1 | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1079 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
Math DeepSeek-V3.1 leads
DeepSeek-V3.1: 38.9 (#122), Wizardlm 70b: 32.2 (#218)
| Benchmark | DeepSeek-V3.1 | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1420 | 1116 |
Knowledge Not comparable
DeepSeek-V3.1: 43.7 (#90), Wizardlm 70b: —
| Benchmark | DeepSeek-V3.1 | Wizardlm 70b |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | — |
| LMArena Expert | 1405 | — |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.6 (#106), Wizardlm 70b: 29.6 (#265)
| Benchmark | DeepSeek-V3.1 | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1400 | 1078 |
| LMArena Chinese | 1469 | 1052 |
| LMArena German | 1411 | 1083 |
| LMArena Russian | 1405 | 1155 |
| LMArena French | 1447 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1337 | — |
| LMArena Spanish | 1431 | — |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 73.9 (#110), Wizardlm 70b: 56.3 (#273)
| Benchmark | DeepSeek-V3.1 | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1400 | 1093 |
Long Context DeepSeek-V3.1 leads
DeepSeek-V3.1: 36.3 (#232), Wizardlm 70b: 33.3 (#263)
| Benchmark | DeepSeek-V3.1 | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1422 | 1097 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.3 (#98), Wizardlm 70b: 34.8 (#269)
| Benchmark | DeepSeek-V3.1 | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1420 | 1120 |
| LMArena Creative Writing | 1401 | 1149 |
| LMArena Multi-Turn | 1408 | 1108 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than Wizardlm 70b?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 33.0 on the Noometry Index.
Is DeepSeek-V3.1 or Wizardlm 70b better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 31.4 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1 and Wizardlm 70b share?
12 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Wizardlm 70b has 12.