Model comparison
Llama 3.2 3B vs Mistral Medium
Mistral Medium is the stronger model overall, scoring 36.3 to 28.9 on the Noometry Index. Llama 3.2 3B costs 25× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
Meta
Mistral AISummary
- They share 14 benchmarks with published results for both. Llama 3.2 3B scores higher in 2 categories and Mistral Medium in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium leads 60.0 to 24.7.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 21.9% for Llama 3.2 3B and 37.7% for Mistral Medium.
- Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Mistral Medium accepts more context: 262K tokens versus 131K.
Side by side
| Llama 3.2 3B | Mistral Medium | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 28.9 | 36.3 |
| Released | 2024-09-24 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 118K | 262K |
| Input $ / M tokens | $0.05 | $1.50 |
| Output $ / M tokens | $0.33 | $7.50 |
| Results tracked | 18 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Medium leads
Llama 3.2 3B: 27.6 (#319), Mistral Medium: 34.2 (#243)
| Benchmark | Llama 3.2 3B | Mistral Medium |
|---|---|---|
| LMArena Coding | 1098 | 1434 |
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| WeirdML | — | 43.7% |
| BigCodeBench Instruct | 23.4% | — |
| BigCodeBench Complete | 28.3% | — |
| ALE-Bench | — | 763.98 |
Agentic & Tool Use Mistral Medium leads
Llama 3.2 3B: 20.1 (#143), Mistral Medium: 28.3 (#90)
| Benchmark | Llama 3.2 3B | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | 37.7% |
| BALROG | 10.1% | — |
Reasoning Mistral Medium leads
Llama 3.2 3B: 21.0 (#228), Mistral Medium: 24.0 (#167)
| Benchmark | Llama 3.2 3B | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1095 | 1426 |
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
Math Llama 3.2 3B leads
Llama 3.2 3B: 32.4 (#214), Mistral Medium: 28.1 (#245)
| Benchmark | Llama 3.2 3B | Mistral Medium |
|---|---|---|
| LMArena Math | 1126 | 1408 |
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| ProofBench | — | 9% |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Llama 3.2 3B leads
Llama 3.2 3B: 29.7 (#235), Mistral Medium: 25.0 (#265)
| Benchmark | Llama 3.2 3B | Mistral Medium |
|---|---|---|
| LMArena Expert | 1090 | 1408 |
| GPQA Diamond | — | 59.5% |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |
Multimodal Not comparable
Llama 3.2 3B: —, Mistral Medium: 35.3 (#88)
| Benchmark | Llama 3.2 3B | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Mistral Medium leads
Llama 3.2 3B: 26.2 (#281), Mistral Medium: 52.1 (#91)
| Benchmark | Llama 3.2 3B | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1019 | 1408 |
| LMArena Chinese | 1017 | 1447 |
| LMArena German | 1056 | 1432 |
| LMArena Russian | 949 | 1411 |
| LMArena French | — | 1459 |
| LMArena Japanese | — | 1378 |
| LMArena Korean | — | 1380 |
| LMArena Spanish | — | 1433 |
Instruction Following Mistral Medium leads
Llama 3.2 3B: 56.0 (#275), Mistral Medium: 73.7 (#116)
| Benchmark | Llama 3.2 3B | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1089 | 1398 |
Long Context Mistral Medium leads
Llama 3.2 3B: 33.4 (#261), Mistral Medium: 42.9 (#114)
| Benchmark | Llama 3.2 3B | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1100 | 1406 |
Writing & Preference Mistral Medium leads
Llama 3.2 3B: 24.7 (#307), Mistral Medium: 60.0 (#103)
| Benchmark | Llama 3.2 3B | Mistral Medium |
|---|---|---|
| LMArena Text | 1110 | 1424 |
| LMArena Creative Writing | 1094 | 1391 |
| LMArena Multi-Turn | 1105 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| EQ-Bench Creative Writing | 595 | — |
Frequently asked questions
Is Llama 3.2 3B better than Mistral Medium?
Mistral Medium is the stronger model overall, scoring 36.3 to 28.9 on the Noometry Index. Llama 3.2 3B costs 25× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Which is cheaper, Llama 3.2 3B or Mistral Medium?
Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Llama 3.2 3B or Mistral Medium better for coding?
Mistral Medium scores higher on coding benchmarks: 34.2 versus 27.6 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium does, with 262K tokens against 131K.
How many benchmarks do Llama 3.2 3B and Mistral Medium share?
14 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Mistral Medium has 36.