Model comparison
Llama 3.1-8B vs Mistral Medium 3.1
Mistral Medium 3.1 is the stronger model overall, scoring 31.9 to 23.0 on the Noometry Index. Llama 3.1-8B costs 14× less per token, which makes it the better buy when Mistral Medium 3.1's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
Meta
Mistral AISummary
- They share 1 benchmark with published results for both. Llama 3.1-8B scores higher in 1 category and Mistral Medium 3.1 in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium 3.1 leads 55.5 to 29.7.
- Llama 3.1-8B is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.40 / $2 for Mistral Medium 3.1.
- Mistral Medium 3.1 accepts more context: 131K tokens versus 128K.
- Llama 3.1-8B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.1-8B | Mistral Medium 3.1 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 23.0 | 31.9 |
| Released | 2024-07-23 | — |
| Weights | Open | Proprietary |
| Context window | 128K | 131K |
| Max output | 4K | 105K |
| Input $ / M tokens | $0.05 | $0.40 |
| Output $ / M tokens | $0.08 | $2 |
| Results tracked | 43 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.1-8B: 20.2 (#340), Mistral Medium 3.1: —
| Benchmark | Llama 3.1-8B | Mistral Medium 3.1 |
|---|---|---|
| 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: 22.5 (#131), Mistral Medium 3.1: —
| Benchmark | Llama 3.1-8B | Mistral Medium 3.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25.8% | — |
| BALROG | 15.1% | — |
Reasoning Llama 3.1-8B leads
Llama 3.1-8B: 14.9 (#321), Mistral Medium 3.1: 10.6 (#341)
| Benchmark | Llama 3.1-8B | Mistral Medium 3.1 |
|---|---|---|
| NYT Connections (extended) | — | 6.5% |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| Thematic Generalization | — | 20.3% |
| LMArena Hard Prompts | 1175 | — |
| DTBench | 50.9% | — |
| LMCA | 5.4% | — |
| Epoch Capabilities Index | 116.57 | — |
| PIQA | 81.2% | — |
Math Not comparable
Llama 3.1-8B: 10.2 (#317), Mistral Medium 3.1: —
| Benchmark | Llama 3.1-8B | Mistral Medium 3.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.7% | — |
| Omni-MATH | 13.7% | — |
| LMArena Math | 1179 | — |
| MATH Level 5 | 22.9% | — |
| GSM8K | 82.4% | — |
Knowledge Not comparable
Llama 3.1-8B: 8.0 (#307), Mistral Medium 3.1: —
| Benchmark | Llama 3.1-8B | Mistral Medium 3.1 |
|---|---|---|
| GPQA Diamond | 27% | — |
| MMLU-Pro | 40.6% | — |
| GPQA (HELM) | 24.7% | — |
| LMArena Expert | 1144 | — |
| BoolQ | 82.8% | — |
| MMLU | 56.1% | — |
Multilingual Not comparable
Llama 3.1-8B: 34.0 (#249), Mistral Medium 3.1: —
| Benchmark | Llama 3.1-8B | Mistral Medium 3.1 |
|---|---|---|
| LMArena Non-English | 1148 | — |
| LMArena Chinese | 1151 | — |
| LMArena French | 1177 | — |
| LMArena German | 1144 | — |
| LMArena Japanese | 1061 | — |
| LMArena Korean | 1053 | — |
| LMArena Russian | 1158 | — |
| LMArena Spanish | 1169 | — |
Instruction Following Not comparable
Llama 3.1-8B: 58.9 (#258), Mistral Medium 3.1: —
| Benchmark | Llama 3.1-8B | Mistral Medium 3.1 |
|---|---|---|
| IFEval | 74.3% | — |
| LMArena Instruction Following | 1159 | — |
Long Context Not comparable
Llama 3.1-8B: 35.8 (#238), Mistral Medium 3.1: —
| Benchmark | Llama 3.1-8B | Mistral Medium 3.1 |
|---|---|---|
| LMArena Longer Query | 1182 | — |
Writing & Preference Mistral Medium 3.1 leads
Llama 3.1-8B: 29.7 (#290), Mistral Medium 3.1: 55.5 (#145)
| Benchmark | Llama 3.1-8B | Mistral Medium 3.1 |
|---|---|---|
| EQ-Bench Creative Writing | 713 | 1476 |
| 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 Medium 3.1?
Mistral Medium 3.1 is the stronger model overall, scoring 31.9 to 23.0 on the Noometry Index. Llama 3.1-8B costs 14× less per token, which makes it the better buy when Mistral Medium 3.1's lead doesn't matter for your workload.
Which is cheaper, Llama 3.1-8B or Mistral Medium 3.1?
Llama 3.1-8B is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Mistral Medium 3.1 lists at $0.40 and $2.
Which has the bigger context window?
Mistral Medium 3.1 does, with 131K tokens against 128K.
How many benchmarks do Llama 3.1-8B and Mistral Medium 3.1 share?
1 benchmark has published results for both models. Llama 3.1-8B has 43 scored results on Noometry and Mistral Medium 3.1 has 3.