Model comparison
Mistral 7B vs Wizardlm 70b
Wizardlm 70b is the stronger model overall, scoring 32.4 to 22.9 on the Noometry Index.
Last verified . 12 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 12 benchmarks with published results for both. Mistral 7B scores higher in 0 categories and Wizardlm 70b in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Wizardlm 70b leads 29.7 to 7.6.
Side by side
| Mistral 7B | Wizardlm 70b | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 22.9 | 32.4 |
| Released | 2023-09-27 | — |
| Weights | Open | Open |
| Context window | 8K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.25 | — |
| Results tracked | 37 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Wizardlm 70b leads
Mistral 7B: 25.9 (#321), Wizardlm 70b: 30.9 (#280)
| Benchmark | Mistral 7B | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1082 | 1081 |
| BigCodeBench Instruct | 19.5% | — |
| BigCodeBench Complete | 27.3% | — |
| HumanEval+ | 36% | — |
| MBPP+ | 42.1% | — |
Reasoning Wizardlm 70b leads
Mistral 7B: 12.6 (#331), Wizardlm 70b: 19.8 (#231)
| Benchmark | Mistral 7B | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1067 | 1079 |
| Chess Puzzles | 0% | — |
| DTBench | 42.5% | — |
| Adversarial NLI | 47.1% | — |
| BIG-Bench Hard | 56.1% | — |
| Epoch Capabilities Index | 111.97 | — |
| HellaSwag | 81% | — |
| PIQA | 83% | — |
| WinoGrande | 75.3% | — |
Math Wizardlm 70b leads
Mistral 7B: 7.6 (#319), Wizardlm 70b: 29.7 (#216)
| Benchmark | Mistral 7B | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1085 | 1116 |
| OTIS Mock AIME 2024-2025 | 0.3% | — |
| MATH Level 5 | 3.7% | — |
| GSM8K | 54.4% | — |
Knowledge Not comparable
Mistral 7B: 7.3 (#306), Wizardlm 70b: —
| Benchmark | Mistral 7B | Wizardlm 70b |
|---|---|---|
| GPQA Diamond | 15.2% | — |
| LMArena Expert | 1036 | — |
| ARC (AI2) Challenge | 78.6% | — |
| BoolQ | 87.4% | — |
| MMLU | 62.5% | — |
| OpenBookQA | 79.8% | — |
| TriviaQA | 75.2% | — |
Multilingual Wizardlm 70b leads
Mistral 7B: 26.0 (#278), Wizardlm 70b: 29.8 (#260)
| Benchmark | Mistral 7B | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1012 | 1078 |
| LMArena Chinese | 1009 | 1052 |
| LMArena German | 987 | 1083 |
| LMArena Russian | 1018 | 1155 |
| LMArena French | 1036 | — |
| LMArena Japanese | 878 | — |
| LMArena Spanish | 1026 | — |
Instruction Following Wizardlm 70b leads
Mistral 7B: 54.5 (#275), Wizardlm 70b: 56.5 (#268)
| Benchmark | Mistral 7B | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1060 | 1093 |
Long Context Wizardlm 70b leads
Mistral 7B: 32.2 (#266), Wizardlm 70b: 33.3 (#258)
| Benchmark | Mistral 7B | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1060 | 1097 |
Writing & Preference Wizardlm 70b leads
Mistral 7B: 30.9 (#281), Wizardlm 70b: 34.9 (#264)
| Benchmark | Mistral 7B | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1090 | 1120 |
| LMArena Creative Writing | 1068 | 1149 |
| LMArena Multi-Turn | 1062 | 1108 |
Frequently asked questions
Is Mistral 7B better than Wizardlm 70b?
Wizardlm 70b is the stronger model overall, scoring 32.4 to 22.9 on the Noometry Index.
Is Mistral 7B or Wizardlm 70b better for coding?
Wizardlm 70b scores higher on coding benchmarks: 30.9 versus 25.9 in the Noometry coding category.
How many benchmarks do Mistral 7B and Wizardlm 70b share?
12 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Wizardlm 70b has 12.