Model comparison
Llama 3.1-70B vs Mistral Medium 3.5
Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 29.4 on the Noometry Index. Llama 3.1-70B costs 7.5× 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 3.1-70B scores higher in 1 category and Mistral Medium 3.5 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Medium 3.5 leads 36.4 to 12.7.
- Llama 3.1-70B is cheaper at $0.40 / $0.40 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 3.1-70B | Mistral Medium 3.5 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 29.4 | 39.6 |
| Released | 2024-07-23 | — |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 210K |
| Input $ / M tokens | $0.40 | $1.50 |
| Output $ / M tokens | $0.40 | $7.50 |
| Results tracked | 35 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Medium 3.5 leads
Llama 3.1-70B: 29.8 (#292), Mistral Medium 3.5: 35.7 (#208)
| Benchmark | Llama 3.1-70B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Coding | 1260 | 1461 |
| LMArena WebDev | — | 1263 |
| WeirdML | 9% | — |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 54.8% | — |
Agentic & Tool Use Not comparable
Llama 3.1-70B: 24.9 (#104), Mistral Medium 3.5: —
| Benchmark | Llama 3.1-70B | Mistral Medium 3.5 |
|---|---|---|
| TheAgentCompany | 6.9% | — |
| BALROG | 27.9% | — |
Reasoning Llama 3.1-70B leads
Llama 3.1-70B: 20.8 (#215), Mistral Medium 3.5: 16.6 (#290)
| Benchmark | Llama 3.1-70B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1436 |
| Epoch Capabilities Index | 125.91 | 141.42 |
| Kagi LLM Benchmark | — | 41.4% |
| NYT Connections (extended) | — | 12.9% |
| DTBench | 60% | — |
| LMCA | 14.8% | — |
Math Mistral Medium 3.5 leads
Llama 3.1-70B: 12.7 (#298), Mistral Medium 3.5: 36.4 (#113)
| Benchmark | Llama 3.1-70B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Math | 1252 | 1432 |
| OTIS Mock AIME 2024-2025 | 3.6% | — |
| Omni-MATH | 21% | — |
| MATH Level 5 | 36.7% | — |
Knowledge Mistral Medium 3.5 leads
Llama 3.1-70B: 24.1 (#264), Mistral Medium 3.5: 39.3 (#123)
| Benchmark | Llama 3.1-70B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Expert | 1209 | 1431 |
| GPQA Diamond | 44.2% | — |
| MMLU-Pro | 65.3% | — |
| GPQA (HELM) | 42.6% | — |
| MMLU | 80.1% | — |
Multimodal Not comparable
Llama 3.1-70B: —, Mistral Medium 3.5: 37.6 (#64)
| Benchmark | Llama 3.1-70B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Vision | — | 1222 |
Multilingual Mistral Medium 3.5 leads
Llama 3.1-70B: 38.9 (#220), Mistral Medium 3.5: 52.1 (#93)
| Benchmark | Llama 3.1-70B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Non-English | 1219 | 1405 |
| LMArena Chinese | 1215 | 1443 |
| LMArena French | 1260 | 1448 |
| LMArena German | 1222 | 1453 |
| LMArena Korean | 1140 | 1387 |
| LMArena Russian | 1234 | 1396 |
| LMArena Spanish | 1253 | 1406 |
| LMArena Japanese | 1132 | — |
Instruction Following Mistral Medium 3.5 leads
Llama 3.1-70B: 65.5 (#218), Mistral Medium 3.5: 74.7 (#87)
| Benchmark | Llama 3.1-70B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Instruction Following | 1231 | 1414 |
| IFEval | 82.1% | — |
Long Context Mistral Medium 3.5 leads
Llama 3.1-70B: 37.6 (#208), Mistral Medium 3.5: 43.2 (#101)
| Benchmark | Llama 3.1-70B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Longer Query | 1241 | 1414 |
Writing & Preference Mistral Medium 3.5 leads
Llama 3.1-70B: 35.6 (#262), Mistral Medium 3.5: 58.6 (#113)
| Benchmark | Llama 3.1-70B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Text | 1261 | 1421 |
| LMArena Creative Writing | 1232 | 1372 |
| LMArena Multi-Turn | 1256 | 1423 |
| EQ-Bench Creative Writing | 784 | — |
| WildBench | 75.8% | — |
| EQ-Bench 4 | — | 993 |
Frequently asked questions
Is Llama 3.1-70B better than Mistral Medium 3.5?
Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 29.4 on the Noometry Index. Llama 3.1-70B costs 7.5× 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 3.1-70B or Mistral Medium 3.5?
Llama 3.1-70B is cheaper. It lists at $0.40 per million input tokens and $0.40 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.
Is Llama 3.1-70B or Mistral Medium 3.5 better for coding?
Mistral Medium 3.5 scores higher on coding benchmarks: 35.7 versus 29.8 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 3.1-70B and Mistral Medium 3.5 share?
17 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Mistral Medium 3.5 has 22.