Model comparison
Llama 4 Scout vs Mistral Medium
Mistral Medium is the stronger model overall, scoring 36.0 to 27.4 on the Noometry Index. Llama 4 Scout costs 20× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Last verified . 29 shared benchmarks.
Meta
Mistral AISummary
- They share 29 benchmarks with published results for both. Llama 4 Scout scores higher in 1 category and Mistral Medium in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium leads 60.2 to 37.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.8% for Llama 4 Scout and 32.2% for Mistral Medium.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Mistral Medium accepts more context: 262K tokens versus 128K.
Side by side
| Llama 4 Scout | Mistral Medium | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 27.4 | 36.0 |
| Released | 2025-04-05 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 262K |
| Input $ / M tokens | $0.10 | $1.50 |
| Output $ / M tokens | $0.30 | $7.50 |
| Results tracked | 43 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Medium leads
Llama 4 Scout: 19.9 (#334), Mistral Medium: 33.8 (#241)
| Benchmark | Llama 4 Scout | Mistral Medium |
|---|---|---|
| SciCode | 17% | 40.2% |
| LMArena Coding | 1286 | 1434 |
| FrontierCode | — | 8% |
| SWE-bench Verified (bash only) | 9.1% | — |
| WeirdML | — | 43.7% |
| BigCodeBench Complete | 43.1% | — |
| ALE-Bench | — | 763.98 |
Agentic & Tool Use Mistral Medium leads
Llama 4 Scout: 24.4 (#109), Mistral Medium: 28.1 (#84)
| Benchmark | Llama 4 Scout | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | 37.7% |
Reasoning Mistral Medium leads
Llama 4 Scout: 9.2 (#339), Mistral Medium: 23.3 (#165)
| Benchmark | Llama 4 Scout | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 36.9% | 50% |
| CritPt | 0% | 0% |
| LMArena Hard Prompts | 1266 | 1426 |
| DTBench | 57.9% | 75.5% |
| LMCA | 12% | 26.1% |
| ARC-AGI-2 | 0% | — |
| ARC-AGI-1 | 0.5% | — |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 129.64 | — |
| ForecastBench | 57.5 | — |
Math Mistral Medium leads
Llama 4 Scout: 18.4 (#280), Mistral Medium: 27.2 (#238)
| Benchmark | Llama 4 Scout | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.8% | 32.2% |
| LMArena Math | 1286 | 1409 |
| MATH Level 5 | 62.3% | 81.6% |
| FrontierMath (Feb 2025 set) | 0% | 0.3% |
| ProofBench | — | 9% |
| Omni-MATH | 37.3% | — |
Knowledge Llama 4 Scout leads
Llama 4 Scout: 31.8 (#208), Mistral Medium: 24.9 (#260)
| Benchmark | Llama 4 Scout | Mistral Medium |
|---|---|---|
| GPQA Diamond | 51.8% | 59.5% |
| Vectara Hallucination Rate | 7.7% | 22.7% |
| LMArena Expert | 1236 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| MMLU-Pro | 74.2% | — |
| GPQA (HELM) | 50.7% | — |
Multimodal Mistral Medium leads
Llama 4 Scout: 31.6 (#98), Mistral Medium: 34.6 (#82)
| Benchmark | Llama 4 Scout | Mistral Medium |
|---|---|---|
| LMArena Vision | 1118 | 1172 |
| SpatialViz-Bench | 34.2% | — |
Multilingual Mistral Medium leads
Llama 4 Scout: 41.3 (#207), Mistral Medium: 52.3 (#86)
| Benchmark | Llama 4 Scout | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1253 | 1408 |
| LMArena Chinese | 1256 | 1448 |
| LMArena French | 1283 | 1460 |
| LMArena German | 1274 | 1433 |
| LMArena Japanese | 1209 | 1378 |
| LMArena Korean | 1207 | 1382 |
| LMArena Russian | 1263 | 1411 |
| LMArena Spanish | 1277 | 1433 |
Instruction Following Mistral Medium leads
Llama 4 Scout: 66.0 (#212), Mistral Medium: 73.9 (#111)
| Benchmark | Llama 4 Scout | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1248 | 1398 |
| IFEval | 81.8% | — |
Long Context Mistral Medium leads
Llama 4 Scout: 27.5 (#289), Mistral Medium: 42.9 (#108)
| Benchmark | Llama 4 Scout | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1265 | 1406 |
| Fiction.LiveBench | 36% | — |
Writing & Preference Mistral Medium leads
Llama 4 Scout: 37.1 (#256), Mistral Medium: 60.2 (#97)
| Benchmark | Llama 4 Scout | Mistral Medium |
|---|---|---|
| LMArena Text | 1279 | 1424 |
| LMArena Creative Writing | 1249 | 1391 |
| LMArena Multi-Turn | 1281 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| EQ-Bench Creative Writing | 783 | — |
| WildBench | 78% | — |
Frequently asked questions
Is Llama 4 Scout better than Mistral Medium?
Mistral Medium is the stronger model overall, scoring 36.0 to 27.4 on the Noometry Index. Llama 4 Scout costs 20× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Scout or Mistral Medium?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Llama 4 Scout or Mistral Medium better for coding?
Mistral Medium scores higher on coding benchmarks: 33.8 versus 19.9 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium does, with 262K tokens against 128K.
How many benchmarks do Llama 4 Scout and Mistral Medium share?
29 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Mistral Medium has 36.