Model comparison
Llama 3-70B vs Magistral Medium
Magistral Medium is the stronger model overall, scoring 35.2 to 28.8 on the Noometry Index.
Last verified . 18 shared benchmarks.
Meta
Mistral AISummary
- They share 18 benchmarks with published results for both. Llama 3-70B scores higher in 1 category and Magistral Medium in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Magistral Medium leads 35.1 to 12.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 35.1% for Llama 3-70B and 16.2% for Magistral Medium.
Side by side
| Llama 3-70B | Magistral Medium | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 28.8 | 35.2 |
| Released | 2024-04-18 | 2025-03-17 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 16K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $5 |
| Results tracked | 31 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
Llama 3-70B: 35.8 (#218), Magistral Medium: 39.1 (#161)
| Benchmark | Llama 3-70B | Magistral Medium |
|---|---|---|
| LMArena Coding | 1206 | 1319 |
| SciCode | — | 39.2% |
| BigCodeBench Instruct | 43.6% | — |
| BigCodeBench Complete | 54.5% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |
Agentic & Tool Use Not comparable
Llama 3-70B: 21.1 (#139), Magistral Medium: —
| Benchmark | Llama 3-70B | Magistral Medium |
|---|---|---|
| Cybench | 5% | — |
Reasoning Llama 3-70B leads
Llama 3-70B: 18.0 (#288), Magistral Medium: 8.6 (#348)
| Benchmark | Llama 3-70B | Magistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 35.1% | 16.2% |
| LMArena Hard Prompts | 1195 | 1267 |
| ARC-AGI-2 | — | 0% |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |
| DTBench | 54.2% | — |
| Epoch Capabilities Index | 122.93 | — |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |
Math Magistral Medium leads
Llama 3-70B: 12.8 (#305), Magistral Medium: 35.1 (#189)
| Benchmark | Llama 3-70B | Magistral Medium |
|---|---|---|
| LMArena Math | 1218 | 1250 |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| MATH Level 5 | 22.6% | — |
Knowledge Magistral Medium leads
Llama 3-70B: 20.8 (#277), Magistral Medium: 33.5 (#202)
| Benchmark | Llama 3-70B | Magistral Medium |
|---|---|---|
| LMArena Expert | 1149 | 1223 |
| GPQA Diamond | 40.6% | — |
| MMLU | 79.3% | — |
Multilingual Magistral Medium leads
Llama 3-70B: 33.6 (#251), Magistral Medium: 39.6 (#224)
| Benchmark | Llama 3-70B | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1142 | 1232 |
| LMArena Chinese | 1114 | 1227 |
| LMArena French | 1232 | 1267 |
| LMArena German | 1169 | 1248 |
| LMArena Japanese | 1017 | 1175 |
| LMArena Korean | 1017 | 1125 |
| LMArena Russian | 1159 | 1224 |
| LMArena Spanish | 1241 | 1271 |
Instruction Following Magistral Medium leads
Llama 3-70B: 62.5 (#238), Magistral Medium: 66.0 (#211)
| Benchmark | Llama 3-70B | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1194 | 1254 |
Long Context Magistral Medium leads
Llama 3-70B: 35.6 (#240), Magistral Medium: 39.3 (#183)
| Benchmark | Llama 3-70B | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1174 | 1295 |
Writing & Preference Magistral Medium leads
Llama 3-70B: 42.8 (#231), Magistral Medium: 46.3 (#219)
| Benchmark | Llama 3-70B | Magistral Medium |
|---|---|---|
| LMArena Text | 1221 | 1255 |
| LMArena Creative Writing | 1210 | 1245 |
| LMArena Multi-Turn | 1223 | 1275 |
Frequently asked questions
Is Llama 3-70B better than Magistral Medium?
Magistral Medium is the stronger model overall, scoring 35.2 to 28.8 on the Noometry Index.
Is Llama 3-70B or Magistral Medium better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 35.8 in the Noometry coding category.
How many benchmarks do Llama 3-70B and Magistral Medium share?
18 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Magistral Medium has 22.