Model comparison
Mistral Small 3 vs Wizardlm 70b
Wizardlm 70b is the stronger model overall, scoring 33.0 to 31.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 12 benchmarks with published results for both. Mistral Small 3 scores higher in 4 categories and Wizardlm 70b in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Wizardlm 70b leads 32.2 to 16.3.
Side by side
| Mistral Small 3 | Wizardlm 70b | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 31.2 | 33.0 |
| Released | 2025-01-30 | — |
| Weights | Open | Open |
| Context window | 33K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 24 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3 leads
Mistral Small 3: 36.5 (#207), Wizardlm 70b: 31.4 (#285)
| Benchmark | Mistral Small 3 | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1246 | 1081 |
| BigCodeBench Instruct | 45.3% | — |
| BigCodeBench Complete | 50.4% | — |
Reasoning Wizardlm 70b leads
Mistral Small 3: 18.9 (#273), Wizardlm 70b: 20.7 (#234)
| Benchmark | Mistral Small 3 | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1233 | 1079 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 127.07 | — |
Math Wizardlm 70b leads
Mistral Small 3: 16.3 (#295), Wizardlm 70b: 32.2 (#218)
| Benchmark | Mistral Small 3 | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1240 | 1116 |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
Knowledge Not comparable
Mistral Small 3: 25.1 (#263), Wizardlm 70b: —
| Benchmark | Mistral Small 3 | Wizardlm 70b |
|---|---|---|
| GPQA Diamond | 47.3% | — |
| Confabulations | 25.2% | — |
| LMArena Expert | 1202 | — |
Multilingual Mistral Small 3 leads
Mistral Small 3: 37.3 (#236), Wizardlm 70b: 29.6 (#265)
| Benchmark | Mistral Small 3 | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1198 | 1078 |
| LMArena Chinese | 1204 | 1052 |
| LMArena German | 1211 | 1083 |
| LMArena Russian | 1216 | 1155 |
| LMArena French | 1203 | — |
| LMArena Japanese | 1111 | — |
| LMArena Korean | 1188 | — |
Instruction Following Mistral Small 3 leads
Mistral Small 3: 63.7 (#229), Wizardlm 70b: 56.3 (#273)
| Benchmark | Mistral Small 3 | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1214 | 1093 |
Long Context Mistral Small 3 leads
Mistral Small 3: 37.8 (#211), Wizardlm 70b: 33.3 (#263)
| Benchmark | Mistral Small 3 | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1246 | 1097 |
Writing & Preference Wizardlm 70b leads
Mistral Small 3: 32.2 (#280), Wizardlm 70b: 34.8 (#269)
| Benchmark | Mistral Small 3 | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1234 | 1120 |
| LMArena Creative Writing | 1195 | 1149 |
| LMArena Multi-Turn | 1217 | 1108 |
| EQ-Bench Creative Writing | 707 | — |
Frequently asked questions
Is Mistral Small 3 better than Wizardlm 70b?
Wizardlm 70b is the stronger model overall, scoring 33.0 to 31.2 on the Noometry Index.
Is Mistral Small 3 or Wizardlm 70b better for coding?
Mistral Small 3 scores higher on coding benchmarks: 36.5 versus 31.4 in the Noometry coding category.
How many benchmarks do Mistral Small 3 and Wizardlm 70b share?
12 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Wizardlm 70b has 12.