Model comparison
Llama 3.1-8B vs Mistral Small 3.2
Mistral Small 3.2 is the stronger model overall, scoring 30.8 to 22.8 on the Noometry Index. Llama 3.1-8B costs 2.3× less per token, which makes it the better buy when Mistral Small 3.2's lead doesn't matter for your workload.
Last verified . 5 shared benchmarks.
Meta
Mistral AISummary
- They share 5 benchmarks with published results for both. Llama 3.1-8B scores higher in 0 categories and Mistral Small 3.2 in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Small 3.2 leads 26.8 to 8.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.7% for Llama 3.1-8B and 30.3% for Mistral Small 3.2.
- Llama 3.1-8B is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.0938 / $0.25 for Mistral Small 3.2.
- Mistral Small 3.2 accepts more context: 256K tokens versus 128K.
Side by side
| Llama 3.1-8B | Mistral Small 3.2 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 22.8 | 30.8 |
| Released | 2024-07-23 | 2025-06-20 |
| Weights | Open | Open |
| Context window | 128K | 256K |
| Max output | 4K | 16K |
| Input $ / M tokens | $0.05 | $0.0938 |
| Output $ / M tokens | $0.08 | $0.25 |
| Results tracked | 43 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.1-8B: 19.9 (#335), Mistral Small 3.2: —
| Benchmark | Llama 3.1-8B | Mistral Small 3.2 |
|---|---|---|
| SciCode | 13.2% | — |
| WeirdML | 1.7% | — |
| BigCodeBench Instruct | 32.8% | — |
| LMArena Coding | 1195 | — |
| BigCodeBench Complete | 40.5% | — |
| HumanEval+ | 62.8% | — |
| MBPP+ | 55.6% | — |
Agentic & Tool Use Not comparable
Llama 3.1-8B: 22.3 (#123), Mistral Small 3.2: —
| Benchmark | Llama 3.1-8B | Mistral Small 3.2 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25.8% | — |
| BALROG | 15.1% | — |
Reasoning Mistral Small 3.2 leads
Llama 3.1-8B: 14.5 (#316), Mistral Small 3.2: 17.5 (#282)
| Benchmark | Llama 3.1-8B | Mistral Small 3.2 |
|---|---|---|
| Chess Puzzles | 0% | 1% |
| Epoch Capabilities Index | 116.48 | 131.73 |
| Kagi LLM Benchmark | — | 40.4% |
| CritPt | 0% | — |
| LMArena Hard Prompts | 1175 | — |
| DTBench | 50.9% | — |
| LMCA | 5.4% | — |
| PIQA | 81.2% | — |
Math Mistral Small 3.2 leads
Llama 3.1-8B: 9.5 (#311), Mistral Small 3.2: 24.9 (#251)
| Benchmark | Llama 3.1-8B | Mistral Small 3.2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.7% | 30.3% |
| Omni-MATH | 13.7% | — |
| LMArena Math | 1179 | — |
| MATH Level 5 | 22.9% | — |
| GSM8K | 82.4% | — |
Knowledge Mistral Small 3.2 leads
Llama 3.1-8B: 8.0 (#302), Mistral Small 3.2: 26.8 (#249)
| Benchmark | Llama 3.1-8B | Mistral Small 3.2 |
|---|---|---|
| GPQA Diamond | 27% | 49.1% |
| MMLU-Pro | 40.6% | — |
| GPQA (HELM) | 24.7% | — |
| LMArena Expert | 1144 | — |
| BoolQ | 82.8% | — |
| MMLU | 56.1% | — |
Multilingual Not comparable
Llama 3.1-8B: 34.2 (#244), Mistral Small 3.2: —
| Benchmark | Llama 3.1-8B | Mistral Small 3.2 |
|---|---|---|
| LMArena Non-English | 1148 | — |
| LMArena Chinese | 1151 | — |
| LMArena French | 1176 | — |
| LMArena German | 1144 | — |
| LMArena Japanese | 1061 | — |
| LMArena Korean | 1053 | — |
| LMArena Russian | 1158 | — |
| LMArena Spanish | 1169 | — |
Instruction Following Not comparable
Llama 3.1-8B: 59.1 (#253), Mistral Small 3.2: —
| Benchmark | Llama 3.1-8B | Mistral Small 3.2 |
|---|---|---|
| IFEval | 74.3% | — |
| LMArena Instruction Following | 1159 | — |
Long Context Not comparable
Llama 3.1-8B: 35.8 (#233), Mistral Small 3.2: —
| Benchmark | Llama 3.1-8B | Mistral Small 3.2 |
|---|---|---|
| LMArena Longer Query | 1182 | — |
Writing & Preference Mistral Small 3.2 leads
Llama 3.1-8B: 29.9 (#285), Mistral Small 3.2: 45.1 (#219)
| Benchmark | Llama 3.1-8B | Mistral Small 3.2 |
|---|---|---|
| EQ-Bench Creative Writing | 713 | 1255 |
| LMArena Text | 1187 | — |
| LMArena Creative Writing | 1154 | — |
| WildBench | 68.7% | — |
| LMArena Multi-Turn | 1172 | — |
Frequently asked questions
Is Llama 3.1-8B better than Mistral Small 3.2?
Mistral Small 3.2 is the stronger model overall, scoring 30.8 to 22.8 on the Noometry Index. Llama 3.1-8B costs 2.3× less per token, which makes it the better buy when Mistral Small 3.2's lead doesn't matter for your workload.
Which is cheaper, Llama 3.1-8B or Mistral Small 3.2?
Llama 3.1-8B is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Mistral Small 3.2 lists at $0.0938 and $0.25.
Which has the bigger context window?
Mistral Small 3.2 does, with 256K tokens against 128K.
How many benchmarks do Llama 3.1-8B and Mistral Small 3.2 share?
5 benchmarks have published results for both models. Llama 3.1-8B has 43 scored results on Noometry and Mistral Small 3.2 has 6.