Model comparison
DeepSeek-V2.5 (Sep 2024) vs Wizardlm 70b
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 33.0 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeek
MicrosoftSummary
- They share 12 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 7 categories and Wizardlm 70b in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V2.5 (Sep 2024) leads 49.8 to 34.8.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Wizardlm 70b | |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 37.6 | 33.0 |
| Released | 2024-09-06 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Wizardlm 70b: 31.4 (#285)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1309 | 1081 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Wizardlm 70b: 20.7 (#234)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1079 |
Math DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Wizardlm 70b: 32.2 (#218)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1288 | 1116 |
Knowledge Not comparable
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Wizardlm 70b: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Wizardlm 70b |
|---|---|---|
| LMArena Expert | 1266 | — |
Multilingual DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Wizardlm 70b: 29.6 (#265)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1273 | 1078 |
| LMArena Chinese | 1318 | 1052 |
| LMArena German | 1258 | 1083 |
| LMArena Russian | 1289 | 1155 |
| LMArena French | 1289 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Spanish | 1248 | — |
Instruction Following DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Wizardlm 70b: 56.3 (#273)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1280 | 1093 |
Long Context DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Wizardlm 70b: 33.3 (#263)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1301 | 1097 |
Writing & Preference DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Wizardlm 70b: 34.8 (#269)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1294 | 1120 |
| LMArena Creative Writing | 1285 | 1149 |
| LMArena Multi-Turn | 1297 | 1108 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Wizardlm 70b?
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 33.0 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Wizardlm 70b better for coding?
They score almost the same on coding (31.7 vs 31.4); test both on your own repository before choosing.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Wizardlm 70b share?
12 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Wizardlm 70b has 12.