Model comparison
Llama 4 Scout vs Mistral
Mistral is the stronger model overall, scoring 29.4 to 27.4 on the Noometry Index.
Last verified . 22 shared benchmarks.
Meta
Mistral AISummary
- They share 22 benchmarks with published results for both. Llama 4 Scout scores higher in 3 categories and Mistral in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 4 Scout leads 31.8 to 16.3.
- The biggest single-benchmark swing is MMLU-Pro: 74.2% for Llama 4 Scout and 27.7% for Mistral.
- Llama 4 Scout has downloadable open weights; the other is API-only.
Side by side
| Llama 4 Scout | Mistral | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 27.4 | 29.4 |
| Released | 2025-04-05 | — |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 43 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
Llama 4 Scout: 19.9 (#334), Mistral: 33.2 (#249)
| Benchmark | Llama 4 Scout | Mistral |
|---|---|---|
| LMArena Coding | 1286 | 1162 |
| SWE-bench Verified (bash only) | 9.1% | — |
| SciCode | 17% | — |
| BigCodeBench Complete | 43.1% | — |
Agentic & Tool Use Not comparable
Llama 4 Scout: 24.4 (#109), Mistral: —
| Benchmark | Llama 4 Scout | Mistral |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |
Reasoning Mistral leads
Llama 4 Scout: 9.2 (#339), Mistral: 21.3 (#199)
| Benchmark | Llama 4 Scout | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1266 | 1149 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 36.9% | — |
| ARC-AGI-1 | 0.5% | — |
| CritPt | 0% | — |
| DTBench | 57.9% | — |
| LMCA | 12% | — |
| Epoch Capabilities Index | 129.64 | — |
| ForecastBench | 57.5 | — |
Math Mistral leads
Llama 4 Scout: 18.4 (#280), Mistral: 20.5 (#275)
| Benchmark | Llama 4 Scout | Mistral |
|---|---|---|
| Omni-MATH | 37.3% | 7.2% |
| LMArena Math | 1286 | 1180 |
| OTIS Mock AIME 2024-2025 | 7.8% | — |
| MATH Level 5 | 62.3% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
Knowledge Llama 4 Scout leads
Llama 4 Scout: 31.8 (#208), Mistral: 16.3 (#283)
| Benchmark | Llama 4 Scout | Mistral |
|---|---|---|
| MMLU-Pro | 74.2% | 27.7% |
| GPQA (HELM) | 50.7% | 30.3% |
| LMArena Expert | 1236 | 1125 |
| GPQA Diamond | 51.8% | — |
| Vectara Hallucination Rate | 7.7% | — |
Multimodal Not comparable
Llama 4 Scout: 31.6 (#98), Mistral: —
| Benchmark | Llama 4 Scout | Mistral |
|---|---|---|
| LMArena Vision | 1118 | — |
| SpatialViz-Bench | 34.2% | — |
Multilingual Llama 4 Scout leads
Llama 4 Scout: 41.3 (#207), Mistral: 33.0 (#249)
| Benchmark | Llama 4 Scout | Mistral |
|---|---|---|
| LMArena Non-English | 1253 | 1129 |
| LMArena Chinese | 1256 | 1109 |
| LMArena French | 1283 | 1179 |
| LMArena German | 1274 | 1155 |
| LMArena Japanese | 1209 | 1012 |
| LMArena Korean | 1207 | 1032 |
| LMArena Russian | 1263 | 1168 |
| LMArena Spanish | 1277 | 1143 |
Instruction Following Llama 4 Scout leads
Llama 4 Scout: 66.0 (#212), Mistral: 52.9 (#283)
| Benchmark | Llama 4 Scout | Mistral |
|---|---|---|
| IFEval | 81.8% | 56.8% |
| LMArena Instruction Following | 1248 | 1152 |
Long Context Mistral leads
Llama 4 Scout: 27.5 (#289), Mistral: 35.0 (#240)
| Benchmark | Llama 4 Scout | Mistral |
|---|---|---|
| LMArena Longer Query | 1265 | 1154 |
| Fiction.LiveBench | 36% | — |
Writing & Preference Too close to call
Llama 4 Scout: 37.1 (#256), Mistral: 37.2 (#255)
| Benchmark | Llama 4 Scout | Mistral |
|---|---|---|
| LMArena Text | 1279 | 1165 |
| LMArena Creative Writing | 1249 | 1158 |
| WildBench | 78% | 66% |
| LMArena Multi-Turn | 1281 | 1147 |
| EQ-Bench Creative Writing | 783 | — |
Frequently asked questions
Is Llama 4 Scout better than Mistral?
Mistral is the stronger model overall, scoring 29.4 to 27.4 on the Noometry Index.
Is Llama 4 Scout or Mistral better for coding?
Mistral scores higher on coding benchmarks: 33.2 versus 19.9 in the Noometry coding category.
How many benchmarks do Llama 4 Scout and Mistral share?
22 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Mistral has 22.