Model comparison
Llama 3.2 1B vs Mistral Medium
Mistral Medium is the stronger model overall, scoring 36.0 to 19.9 on the Noometry Index. Llama 3.2 1B costs 43× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Meta
Mistral AISummary
- They share 16 benchmarks with published results for both. Llama 3.2 1B scores higher in 0 categories and Mistral Medium in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium leads 60.2 to 21.4.
- The biggest single-benchmark swing is GPQA Diamond: 23.9% for Llama 3.2 1B and 59.5% for Mistral Medium.
- Llama 3.2 1B is cheaper at $0.027 / $0.20 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Mistral Medium accepts more context: 262K tokens versus 60K.
Side by side
| Llama 3.2 1B | Mistral Medium | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 19.9 | 36.0 |
| Released | 2024-09-24 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 60K | 262K |
| Max output | 54K | 262K |
| Input $ / M tokens | $0.027 | $1.50 |
| Output $ / M tokens | $0.20 | $7.50 |
| Results tracked | 22 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Medium leads
Llama 3.2 1B: 20.6 (#333), Mistral Medium: 33.8 (#241)
| Benchmark | Llama 3.2 1B | Mistral Medium |
|---|---|---|
| LMArena Coding | 1071 | 1434 |
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| WeirdML | — | 43.7% |
| BigCodeBench Instruct | 8.2% | — |
| BigCodeBench Complete | 11.3% | — |
| ALE-Bench | — | 763.98 |
Agentic & Tool Use Mistral Medium leads
Llama 3.2 1B: 14.5 (#142), Mistral Medium: 28.1 (#84)
| Benchmark | Llama 3.2 1B | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | 10.8% | 37.7% |
| BALROG | 6.6% | — |
Reasoning Mistral Medium leads
Llama 3.2 1B: 15.6 (#304), Mistral Medium: 23.3 (#165)
| Benchmark | Llama 3.2 1B | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1044 | 1426 |
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| Chess Puzzles | 0% | — |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 101.95 | — |
Math Mistral Medium leads
Llama 3.2 1B: 9.7 (#308), Mistral Medium: 27.2 (#238)
| Benchmark | Llama 3.2 1B | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 32.2% |
| LMArena Math | 1086 | 1409 |
| ProofBench | — | 9% |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Mistral Medium leads
Llama 3.2 1B: 7.2 (#307), Mistral Medium: 24.9 (#260)
| Benchmark | Llama 3.2 1B | Mistral Medium |
|---|---|---|
| GPQA Diamond | 23.9% | 59.5% |
| LMArena Expert | 1007 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |
Multimodal Not comparable
Llama 3.2 1B: —, Mistral Medium: 34.6 (#82)
| Benchmark | Llama 3.2 1B | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Mistral Medium leads
Llama 3.2 1B: 23.9 (#287), Mistral Medium: 52.3 (#86)
| Benchmark | Llama 3.2 1B | Mistral Medium |
|---|---|---|
| LMArena Non-English | 973 | 1408 |
| LMArena Chinese | 958 | 1448 |
| LMArena German | 1014 | 1433 |
| LMArena Russian | 941 | 1411 |
| LMArena French | — | 1460 |
| LMArena Japanese | — | 1378 |
| LMArena Korean | — | 1382 |
| LMArena Spanish | — | 1433 |
Instruction Following Mistral Medium leads
Llama 3.2 1B: 52.6 (#285), Mistral Medium: 73.9 (#111)
| Benchmark | Llama 3.2 1B | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1031 | 1398 |
Long Context Mistral Medium leads
Llama 3.2 1B: 31.9 (#269), Mistral Medium: 42.9 (#108)
| Benchmark | Llama 3.2 1B | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1050 | 1406 |
Writing & Preference Mistral Medium leads
Llama 3.2 1B: 21.4 (#305), Mistral Medium: 60.2 (#97)
| Benchmark | Llama 3.2 1B | Mistral Medium |
|---|---|---|
| LMArena Text | 1055 | 1424 |
| LMArena Creative Writing | 1033 | 1391 |
| LMArena Multi-Turn | 1030 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| EQ-Bench Creative Writing | 200 | — |
Frequently asked questions
Is Llama 3.2 1B better than Mistral Medium?
Mistral Medium is the stronger model overall, scoring 36.0 to 19.9 on the Noometry Index. Llama 3.2 1B costs 43× 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 1B or Mistral Medium?
Llama 3.2 1B is cheaper. It lists at $0.027 per million input tokens and $0.20 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Llama 3.2 1B or Mistral Medium better for coding?
Mistral Medium scores higher on coding benchmarks: 33.8 versus 20.6 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium does, with 262K tokens against 60K.
How many benchmarks do Llama 3.2 1B and Mistral Medium share?
16 benchmarks have published results for both models. Llama 3.2 1B has 22 scored results on Noometry and Mistral Medium has 36.