Model comparison
Llama 3.2 3B vs Mistral
Llama 3.2 3B and Mistral score almost the same on the Noometry Index (28.9 vs 29.9), so choose on price, context window or the category you care about most.
Last verified . 13 shared benchmarks.
Meta
Mistral AISummary
- They share 13 benchmarks with published results for both. Llama 3.2 3B scores higher in 3 categories and Mistral in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 3.2 3B leads 29.7 to 16.6.
- Llama 3.2 3B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.2 3B | Mistral | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 28.9 | 29.9 |
| Released | 2024-09-24 | — |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 118K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.33 | — |
| Results tracked | 18 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
Llama 3.2 3B: 27.6 (#319), Mistral: 33.8 (#250)
| Benchmark | Llama 3.2 3B | Mistral |
|---|---|---|
| LMArena Coding | 1098 | 1162 |
| BigCodeBench Instruct | 23.4% | — |
| BigCodeBench Complete | 28.3% | — |
Agentic & Tool Use Not comparable
Llama 3.2 3B: 20.1 (#143), Mistral: —
| Benchmark | Llama 3.2 3B | Mistral |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | — |
| BALROG | 10.1% | — |
Reasoning Mistral leads
Llama 3.2 3B: 21.0 (#228), Mistral: 22.2 (#200)
| Benchmark | Llama 3.2 3B | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1095 | 1149 |
Math Llama 3.2 3B leads
Llama 3.2 3B: 32.4 (#214), Mistral: 22.3 (#278)
| Benchmark | Llama 3.2 3B | Mistral |
|---|---|---|
| LMArena Math | 1126 | 1180 |
| Omni-MATH | — | 7.2% |
Knowledge Llama 3.2 3B leads
Llama 3.2 3B: 29.7 (#235), Mistral: 16.6 (#288)
| Benchmark | Llama 3.2 3B | Mistral |
|---|---|---|
| LMArena Expert | 1090 | 1125 |
| MMLU-Pro | — | 27.7% |
| GPQA (HELM) | — | 30.3% |
Multilingual Mistral leads
Llama 3.2 3B: 26.2 (#281), Mistral: 32.8 (#254)
| Benchmark | Llama 3.2 3B | Mistral |
|---|---|---|
| LMArena Non-English | 1019 | 1129 |
| LMArena Chinese | 1017 | 1109 |
| LMArena German | 1056 | 1155 |
| LMArena Russian | 949 | 1168 |
| LMArena French | — | 1180 |
| LMArena Japanese | — | 1013 |
| LMArena Korean | — | 1032 |
| LMArena Spanish | — | 1143 |
Instruction Following Llama 3.2 3B leads
Llama 3.2 3B: 56.0 (#275), Mistral: 52.6 (#288)
| Benchmark | Llama 3.2 3B | Mistral |
|---|---|---|
| LMArena Instruction Following | 1089 | 1152 |
| IFEval | — | 56.8% |
Long Context Mistral leads
Llama 3.2 3B: 33.4 (#261), Mistral: 35.0 (#245)
| Benchmark | Llama 3.2 3B | Mistral |
|---|---|---|
| LMArena Longer Query | 1100 | 1153 |
Writing & Preference Mistral leads
Llama 3.2 3B: 24.7 (#307), Mistral: 37.0 (#260)
| Benchmark | Llama 3.2 3B | Mistral |
|---|---|---|
| LMArena Text | 1110 | 1165 |
| LMArena Creative Writing | 1094 | 1158 |
| LMArena Multi-Turn | 1105 | 1147 |
| EQ-Bench Creative Writing | 595 | — |
| WildBench | — | 66% |
Frequently asked questions
Is Llama 3.2 3B better than Mistral?
Llama 3.2 3B and Mistral score almost the same on the Noometry Index (28.9 vs 29.9), so choose on price, context window or the category you care about most.
Is Llama 3.2 3B or Mistral better for coding?
Mistral scores higher on coding benchmarks: 33.8 versus 27.6 in the Noometry coding category.
How many benchmarks do Llama 3.2 3B and Mistral share?
13 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Mistral has 22.