Model comparison
Mistral vs Wizardlm 13b
Wizardlm 13b is the stronger model overall, scoring 30.8 to 29.4 on the Noometry Index.
Last verified . 10 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 10 benchmarks with published results for both. Mistral scores higher in 5 categories and Wizardlm 13b in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Wizardlm 13b leads 27.8 to 20.5.
- Wizardlm 13b has downloadable open weights; the other is API-only.
Side by side
| Mistral | Wizardlm 13b | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 29.4 | 30.8 |
| Released | — | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
Mistral: 33.2 (#249), Wizardlm 13b: 29.6 (#293)
| Benchmark | Mistral | Wizardlm 13b |
|---|---|---|
| LMArena Coding | 1162 | 1035 |
Reasoning Mistral leads
Mistral: 21.3 (#199), Wizardlm 13b: 18.5 (#265)
| Benchmark | Mistral | Wizardlm 13b |
|---|---|---|
| LMArena Hard Prompts | 1149 | 1018 |
Math Wizardlm 13b leads
Mistral: 20.5 (#275), Wizardlm 13b: 27.8 (#235)
| Benchmark | Mistral | Wizardlm 13b |
|---|---|---|
| LMArena Math | 1180 | 1017 |
| Omni-MATH | 7.2% | — |
Knowledge Not comparable
Mistral: 16.3 (#283), Wizardlm 13b: —
| Benchmark | Mistral | Wizardlm 13b |
|---|---|---|
| MMLU-Pro | 27.7% | — |
| GPQA (HELM) | 30.3% | — |
| LMArena Expert | 1125 | — |
Multilingual Mistral leads
Mistral: 33.0 (#249), Wizardlm 13b: 27.3 (#272)
| Benchmark | Mistral | Wizardlm 13b |
|---|---|---|
| LMArena Non-English | 1129 | 1034 |
| LMArena Chinese | 1109 | 1023 |
| LMArena French | 1179 | — |
| LMArena German | 1155 | — |
| LMArena Japanese | 1012 | — |
| LMArena Korean | 1032 | — |
| LMArena Russian | 1168 | — |
| LMArena Spanish | 1143 | — |
Instruction Following Too close to call
Mistral: 52.9 (#283), Wizardlm 13b: 53.7 (#280)
| Benchmark | Mistral | Wizardlm 13b |
|---|---|---|
| LMArena Instruction Following | 1152 | 1049 |
| IFEval | 56.8% | — |
Long Context Mistral leads
Mistral: 35.0 (#240), Wizardlm 13b: 32.0 (#268)
| Benchmark | Mistral | Wizardlm 13b |
|---|---|---|
| LMArena Longer Query | 1154 | 1054 |
Writing & Preference Mistral leads
Mistral: 37.2 (#255), Wizardlm 13b: 30.7 (#282)
| Benchmark | Mistral | Wizardlm 13b |
|---|---|---|
| LMArena Text | 1165 | 1077 |
| LMArena Creative Writing | 1158 | 1090 |
| LMArena Multi-Turn | 1147 | 1047 |
| WildBench | 66% | — |
Frequently asked questions
Is Mistral better than Wizardlm 13b?
Wizardlm 13b is the stronger model overall, scoring 30.8 to 29.4 on the Noometry Index.
Is Mistral or Wizardlm 13b better for coding?
Mistral scores higher on coding benchmarks: 33.2 versus 29.6 in the Noometry coding category.
How many benchmarks do Mistral and Wizardlm 13b share?
10 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and Wizardlm 13b has 10.