Model comparison
Llama 3.1-8B vs Mistral Medium 3.5
Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 23.0 on the Noometry Index. Llama 3.1-8B costs 52× less per token, which makes it the better buy when Mistral Medium 3.5's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Meta
Mistral AISummary
- They share 17 benchmarks with published results for both. Llama 3.1-8B scores higher in 0 categories and Mistral Medium 3.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Medium 3.5 leads 40.0 to 8.0.
- Llama 3.1-8B is cheaper at $0.05 / $0.08 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
- Mistral Medium 3.5 accepts more context: 262K tokens versus 128K.
Side by side
| Llama 3.1-8B | Mistral Medium 3.5 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 23.0 | 40.2 |
| Released | 2024-07-23 | — |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 210K |
| Input $ / M tokens | $0.05 | $1.50 |
| Output $ / M tokens | $0.08 | $7.50 |
| Results tracked | 43 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Medium 3.5 leads
Llama 3.1-8B: 20.2 (#340), Mistral Medium 3.5: 36.0 (#213)
| Benchmark | Llama 3.1-8B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Coding | 1195 | 1461 |
| LMArena WebDev | — | 1264 |
| SciCode | 13.2% | — |
| WeirdML | 1.7% | — |
| BigCodeBench Instruct | 32.8% | — |
| BigCodeBench Complete | 40.5% | — |
| HumanEval+ | 62.8% | — |
| MBPP+ | 55.6% | — |
Agentic & Tool Use Not comparable
Llama 3.1-8B: 22.5 (#131), Mistral Medium 3.5: —
| Benchmark | Llama 3.1-8B | Mistral Medium 3.5 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25.8% | — |
| BALROG | 15.1% | — |
Reasoning Mistral Medium 3.5 leads
Llama 3.1-8B: 14.9 (#321), Mistral Medium 3.5: 17.3 (#295)
| Benchmark | Llama 3.1-8B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Hard Prompts | 1175 | 1436 |
| Epoch Capabilities Index | 116.57 | 141.35 |
| Kagi LLM Benchmark | — | 41.4% |
| NYT Connections (extended) | — | 12.9% |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 5.4% | — |
| PIQA | 81.2% | — |
Math Mistral Medium 3.5 leads
Llama 3.1-8B: 10.2 (#317), Mistral Medium 3.5: 39.1 (#113)
| Benchmark | Llama 3.1-8B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Math | 1179 | 1431 |
| OTIS Mock AIME 2024-2025 | 1.7% | — |
| Omni-MATH | 13.7% | — |
| MATH Level 5 | 22.9% | — |
| GSM8K | 82.4% | — |
Knowledge Mistral Medium 3.5 leads
Llama 3.1-8B: 8.0 (#307), Mistral Medium 3.5: 40.0 (#126)
| Benchmark | Llama 3.1-8B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Expert | 1144 | 1432 |
| GPQA Diamond | 27% | — |
| MMLU-Pro | 40.6% | — |
| GPQA (HELM) | 24.7% | — |
| BoolQ | 82.8% | — |
| MMLU | 56.1% | — |
Multimodal Not comparable
Llama 3.1-8B: —, Mistral Medium 3.5: 38.3 (#65)
| Benchmark | Llama 3.1-8B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Vision | — | 1223 |
Multilingual Mistral Medium 3.5 leads
Llama 3.1-8B: 34.0 (#249), Mistral Medium 3.5: 51.9 (#100)
| Benchmark | Llama 3.1-8B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Non-English | 1148 | 1404 |
| LMArena Chinese | 1151 | 1442 |
| LMArena French | 1177 | 1448 |
| LMArena German | 1144 | 1451 |
| LMArena Korean | 1053 | 1385 |
| LMArena Russian | 1158 | 1395 |
| LMArena Spanish | 1169 | 1409 |
| LMArena Japanese | 1061 | — |
Instruction Following Mistral Medium 3.5 leads
Llama 3.1-8B: 58.9 (#258), Mistral Medium 3.5: 74.6 (#90)
| Benchmark | Llama 3.1-8B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Instruction Following | 1159 | 1415 |
| IFEval | 74.3% | — |
Long Context Mistral Medium 3.5 leads
Llama 3.1-8B: 35.8 (#238), Mistral Medium 3.5: 43.2 (#103)
| Benchmark | Llama 3.1-8B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Longer Query | 1182 | 1415 |
Writing & Preference Mistral Medium 3.5 leads
Llama 3.1-8B: 29.7 (#290), Mistral Medium 3.5: 58.5 (#117)
| Benchmark | Llama 3.1-8B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Text | 1187 | 1421 |
| LMArena Creative Writing | 1154 | 1374 |
| LMArena Multi-Turn | 1172 | 1423 |
| EQ-Bench Creative Writing | 713 | — |
| WildBench | 68.7% | — |
| EQ-Bench 4 | — | 993 |
Frequently asked questions
Is Llama 3.1-8B better than Mistral Medium 3.5?
Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 23.0 on the Noometry Index. Llama 3.1-8B costs 52× less per token, which makes it the better buy when Mistral Medium 3.5's lead doesn't matter for your workload.
Which is cheaper, Llama 3.1-8B or Mistral Medium 3.5?
Llama 3.1-8B is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.
Is Llama 3.1-8B or Mistral Medium 3.5 better for coding?
Mistral Medium 3.5 scores higher on coding benchmarks: 36.0 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium 3.5 does, with 262K tokens against 128K.
How many benchmarks do Llama 3.1-8B and Mistral Medium 3.5 share?
17 benchmarks have published results for both models. Llama 3.1-8B has 43 scored results on Noometry and Mistral Medium 3.5 has 22.