Model comparison
Llama 3.1-70B vs Magistral Medium
Magistral Medium is the stronger model overall, scoring 35.2 to 29.6 on the Noometry Index. Llama 3.1-70B costs 6.9× less per token, which makes it the better buy when Magistral Medium'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 Magistral Medium in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Magistral Medium leads 35.1 to 13.5.
- Llama 3.1-70B is cheaper at $0.40 / $0.40 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Magistral Medium accepts more context: 262K tokens versus 128K.
Side by side
| Llama 3.1-70B | Magistral Medium | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 29.6 | 35.2 |
| Released | 2024-07-23 | 2025-03-17 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 16K |
| Input $ / M tokens | $0.40 | $2 |
| Output $ / M tokens | $0.40 | $5 |
| Results tracked | 35 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
Llama 3.1-70B: 30.3 (#296), Magistral Medium: 39.1 (#161)
| Benchmark | Llama 3.1-70B | Magistral Medium |
|---|---|---|
| LMArena Coding | 1260 | 1319 |
| SciCode | — | 39.2% |
| WeirdML | 9% | — |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 54.8% | — |
Agentic & Tool Use Not comparable
Llama 3.1-70B: 25.1 (#112), Magistral Medium: —
| Benchmark | Llama 3.1-70B | Magistral Medium |
|---|---|---|
| TheAgentCompany | 6.9% | — |
| BALROG | 27.9% | — |
Reasoning Llama 3.1-70B leads
Llama 3.1-70B: 21.6 (#220), Magistral Medium: 8.6 (#348)
| Benchmark | Llama 3.1-70B | Magistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1267 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 16.2% |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |
| DTBench | 60% | — |
| LMCA | 14.8% | — |
| Epoch Capabilities Index | 125.92 | — |
Math Magistral Medium leads
Llama 3.1-70B: 13.5 (#304), Magistral Medium: 35.1 (#189)
| Benchmark | Llama 3.1-70B | Magistral Medium |
|---|---|---|
| LMArena Math | 1252 | 1250 |
| OTIS Mock AIME 2024-2025 | 3.6% | — |
| Omni-MATH | 21% | — |
| MATH Level 5 | 36.7% | — |
Knowledge Magistral Medium leads
Llama 3.1-70B: 24.2 (#269), Magistral Medium: 33.5 (#202)
| Benchmark | Llama 3.1-70B | Magistral Medium |
|---|---|---|
| LMArena Expert | 1209 | 1223 |
| GPQA Diamond | 44.2% | — |
| MMLU-Pro | 65.3% | — |
| GPQA (HELM) | 42.6% | — |
| MMLU | 80.1% | — |
Multilingual Too close to call
Llama 3.1-70B: 38.8 (#225), Magistral Medium: 39.6 (#224)
| Benchmark | Llama 3.1-70B | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1219 | 1232 |
| LMArena Chinese | 1215 | 1227 |
| LMArena French | 1261 | 1267 |
| LMArena German | 1222 | 1248 |
| LMArena Japanese | 1132 | 1175 |
| LMArena Korean | 1140 | 1125 |
| LMArena Russian | 1234 | 1224 |
| LMArena Spanish | 1253 | 1271 |
Instruction Following Too close to call
Llama 3.1-70B: 65.3 (#223), Magistral Medium: 66.0 (#211)
| Benchmark | Llama 3.1-70B | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1231 | 1254 |
| IFEval | 82.1% | — |
Long Context Magistral Medium leads
Llama 3.1-70B: 37.6 (#214), Magistral Medium: 39.3 (#183)
| Benchmark | Llama 3.1-70B | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1241 | 1295 |
Writing & Preference Magistral Medium leads
Llama 3.1-70B: 35.4 (#267), Magistral Medium: 46.3 (#219)
| Benchmark | Llama 3.1-70B | Magistral Medium |
|---|---|---|
| LMArena Text | 1261 | 1255 |
| LMArena Creative Writing | 1232 | 1245 |
| LMArena Multi-Turn | 1256 | 1275 |
| EQ-Bench Creative Writing | 784 | — |
| WildBench | 75.8% | — |
Frequently asked questions
Is Llama 3.1-70B better than Magistral Medium?
Magistral Medium is the stronger model overall, scoring 35.2 to 29.6 on the Noometry Index. Llama 3.1-70B costs 6.9× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.
Which is cheaper, Llama 3.1-70B or Magistral Medium?
Llama 3.1-70B is cheaper. It lists at $0.40 per million input tokens and $0.40 per million output tokens; Magistral Medium lists at $2 and $5.
Is Llama 3.1-70B or Magistral Medium better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 30.3 in the Noometry coding category.
Which has the bigger context window?
Magistral Medium does, with 262K tokens against 128K.
How many benchmarks do Llama 3.1-70B and Magistral Medium share?
17 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Magistral Medium has 22.