Model comparison
Llama 4 Scout vs Magistral Medium
Magistral Medium is the stronger model overall, scoring 35.2 to 27.7 on the Noometry Index. Llama 4 Scout costs 18× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.
Last verified . 22 shared benchmarks.
Meta
Mistral AISummary
- They share 22 benchmarks with published results for both. Llama 4 Scout scores higher in 2 categories and Magistral Medium in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where Magistral Medium leads 39.1 to 20.2.
- The biggest single-benchmark swing is SciCode: 17% for Llama 4 Scout and 39.2% for Magistral Medium.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Magistral Medium accepts more context: 262K tokens versus 128K.
Side by side
| Llama 4 Scout | Magistral Medium | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 27.7 | 35.2 |
| Released | 2025-04-05 | 2025-03-17 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 16K |
| Input $ / M tokens | $0.10 | $2 |
| Output $ / M tokens | $0.30 | $5 |
| Results tracked | 43 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
Llama 4 Scout: 20.2 (#339), Magistral Medium: 39.1 (#161)
| Benchmark | Llama 4 Scout | Magistral Medium |
|---|---|---|
| SciCode | 17% | 39.2% |
| LMArena Coding | 1286 | 1319 |
| SWE-bench Verified (bash only) | 9.1% | — |
| BigCodeBench Complete | 43.1% | — |
Agentic & Tool Use Not comparable
Llama 4 Scout: 24.6 (#119), Magistral Medium: —
| Benchmark | Llama 4 Scout | Magistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |
Reasoning Too close to call
Llama 4 Scout: 9.1 (#345), Magistral Medium: 8.6 (#348)
| Benchmark | Llama 4 Scout | Magistral Medium |
|---|---|---|
| ARC-AGI-2 | 0% | 0% |
| Kagi LLM Benchmark | 36.9% | 16.2% |
| ARC-AGI-1 | 0.5% | 6.1% |
| CritPt | 0% | 0.3% |
| LMArena Hard Prompts | 1266 | 1267 |
| DTBench | 57.9% | — |
| LMCA | 12% | — |
| Epoch Capabilities Index | 129.64 | — |
| ForecastBench | 57.5 | — |
Math Magistral Medium leads
Llama 4 Scout: 19.6 (#286), Magistral Medium: 35.1 (#189)
| Benchmark | Llama 4 Scout | Magistral Medium |
|---|---|---|
| LMArena Math | 1287 | 1250 |
| OTIS Mock AIME 2024-2025 | 7.8% | — |
| Omni-MATH | 37.3% | — |
| MATH Level 5 | 62.3% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
Knowledge Magistral Medium leads
Llama 4 Scout: 31.9 (#217), Magistral Medium: 33.5 (#202)
| Benchmark | Llama 4 Scout | Magistral Medium |
|---|---|---|
| LMArena Expert | 1235 | 1223 |
| GPQA Diamond | 51.8% | — |
| MMLU-Pro | 74.2% | — |
| Vectara Hallucination Rate | 7.7% | — |
| GPQA (HELM) | 50.7% | — |
Multimodal Not comparable
Llama 4 Scout: 32.2 (#102), Magistral Medium: —
| Benchmark | Llama 4 Scout | Magistral Medium |
|---|---|---|
| LMArena Vision | 1118 | — |
| SpatialViz-Bench | 34.2% | — |
Multilingual Llama 4 Scout leads
Llama 4 Scout: 41.0 (#212), Magistral Medium: 39.6 (#224)
| Benchmark | Llama 4 Scout | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1252 | 1232 |
| LMArena Chinese | 1255 | 1227 |
| LMArena French | 1282 | 1267 |
| LMArena German | 1272 | 1248 |
| LMArena Japanese | 1206 | 1175 |
| LMArena Korean | 1207 | 1125 |
| LMArena Russian | 1263 | 1224 |
| LMArena Spanish | 1278 | 1271 |
Instruction Following Too close to call
Llama 4 Scout: 65.8 (#217), Magistral Medium: 66.0 (#211)
| Benchmark | Llama 4 Scout | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1248 | 1254 |
| IFEval | 81.8% | — |
Long Context Magistral Medium leads
Llama 4 Scout: 27.5 (#294), Magistral Medium: 39.3 (#183)
| Benchmark | Llama 4 Scout | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1265 | 1295 |
| Fiction.LiveBench | 36% | — |
Writing & Preference Magistral Medium leads
Llama 4 Scout: 37.0 (#261), Magistral Medium: 46.3 (#219)
| Benchmark | Llama 4 Scout | Magistral Medium |
|---|---|---|
| LMArena Text | 1279 | 1255 |
| LMArena Creative Writing | 1249 | 1245 |
| LMArena Multi-Turn | 1280 | 1275 |
| EQ-Bench Creative Writing | 783 | — |
| WildBench | 78% | — |
Frequently asked questions
Is Llama 4 Scout better than Magistral Medium?
Magistral Medium is the stronger model overall, scoring 35.2 to 27.7 on the Noometry Index. Llama 4 Scout costs 18× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Scout or Magistral Medium?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Magistral Medium lists at $2 and $5.
Is Llama 4 Scout or Magistral Medium better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Magistral Medium does, with 262K tokens against 128K.
How many benchmarks do Llama 4 Scout and Magistral Medium share?
22 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Magistral Medium has 22.