Model comparison
Llama 4 Scout vs Mistral Small 3.1
Mistral Small 3.1 is the stronger model overall, scoring 31.7 to 27.7 on the Noometry Index. Llama 4 Scout costs 2.7× less per token, which makes it the better buy when Mistral Small 3.1's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
Meta
Mistral AISummary
- They share 27 benchmarks with published results for both. Llama 4 Scout scores higher in 3 categories and Mistral Small 3.1 in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Mistral Small 3.1 leads 38.3 to 20.2.
- The biggest single-benchmark swing is MMLU-Pro: 74.2% for Llama 4 Scout and 61% for Mistral Small 3.1.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.35 / $0.56 for Mistral Small 3.1.
Side by side
| Llama 4 Scout | Mistral Small 3.1 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 27.7 | 31.7 |
| Released | 2025-04-05 | 2025-03-17 |
| Weights | Open | Open |
| Context window | 128K | 128K |
| Max output | 4K | 102K |
| Input $ / M tokens | $0.10 | $0.35 |
| Output $ / M tokens | $0.30 | $0.56 |
| Results tracked | 43 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3.1 leads
Llama 4 Scout: 20.2 (#339), Mistral Small 3.1: 38.3 (#179)
| Benchmark | Llama 4 Scout | Mistral Small 3.1 |
|---|---|---|
| LMArena Coding | 1286 | 1309 |
| SWE-bench Verified (bash only) | 9.1% | — |
| SciCode | 17% | — |
| BigCodeBench Complete | 43.1% | — |
Agentic & Tool Use Not comparable
Llama 4 Scout: 24.6 (#119), Mistral Small 3.1: —
| Benchmark | Llama 4 Scout | Mistral Small 3.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |
Reasoning Mistral Small 3.1 leads
Llama 4 Scout: 9.1 (#345), Mistral Small 3.1: 19.7 (#254)
| Benchmark | Llama 4 Scout | Mistral Small 3.1 |
|---|---|---|
| LMArena Hard Prompts | 1266 | 1278 |
| Epoch Capabilities Index | 129.64 | 127.48 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 36.9% | — |
| ARC-AGI-1 | 0.5% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 1% |
| DTBench | 57.9% | — |
| LMCA | 12% | — |
| ForecastBench | 57.5 | — |
Math Llama 4 Scout leads
Llama 4 Scout: 19.6 (#286), Mistral Small 3.1: 14.7 (#301)
| Benchmark | Llama 4 Scout | Mistral Small 3.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.8% | 3.9% |
| Omni-MATH | 37.3% | 24.8% |
| LMArena Math | 1287 | 1262 |
| MATH Level 5 | 62.3% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
Knowledge Llama 4 Scout leads
Llama 4 Scout: 31.9 (#217), Mistral Small 3.1: 22.6 (#271)
| Benchmark | Llama 4 Scout | Mistral Small 3.1 |
|---|---|---|
| GPQA Diamond | 51.8% | 41.9% |
| MMLU-Pro | 74.2% | 61% |
| GPQA (HELM) | 50.7% | 39.2% |
| LMArena Expert | 1235 | 1257 |
| Vectara Hallucination Rate | 7.7% | — |
Multimodal Mistral Small 3.1 leads
Llama 4 Scout: 32.2 (#102), Mistral Small 3.1: 33.2 (#99)
| Benchmark | Llama 4 Scout | Mistral Small 3.1 |
|---|---|---|
| LMArena Vision | 1118 | 1136 |
| SpatialViz-Bench | 34.2% | — |
Multilingual Too close to call
Llama 4 Scout: 41.0 (#212), Mistral Small 3.1: 41.2 (#209)
| Benchmark | Llama 4 Scout | Mistral Small 3.1 |
|---|---|---|
| LMArena Non-English | 1252 | 1255 |
| LMArena Chinese | 1255 | 1253 |
| LMArena French | 1282 | 1273 |
| LMArena German | 1272 | 1266 |
| LMArena Japanese | 1206 | 1208 |
| LMArena Korean | 1207 | 1206 |
| LMArena Russian | 1263 | 1263 |
| LMArena Spanish | 1278 | 1283 |
Instruction Following Llama 4 Scout leads
Llama 4 Scout: 65.8 (#217), Mistral Small 3.1: 63.6 (#230)
| Benchmark | Llama 4 Scout | Mistral Small 3.1 |
|---|---|---|
| IFEval | 81.8% | 75% |
| LMArena Instruction Following | 1248 | 1264 |
Long Context Mistral Small 3.1 leads
Llama 4 Scout: 27.5 (#294), Mistral Small 3.1: 39.5 (#178)
| Benchmark | Llama 4 Scout | Mistral Small 3.1 |
|---|---|---|
| LMArena Longer Query | 1265 | 1299 |
| Fiction.LiveBench | 36% | — |
Writing & Preference Too close to call
Llama 4 Scout: 37.0 (#261), Mistral Small 3.1: 37.0 (#259)
| Benchmark | Llama 4 Scout | Mistral Small 3.1 |
|---|---|---|
| LMArena Text | 1279 | 1277 |
| LMArena Creative Writing | 1249 | 1253 |
| EQ-Bench Creative Writing | 783 | 761 |
| WildBench | 78% | 78.8% |
| LMArena Multi-Turn | 1280 | 1270 |
Frequently asked questions
Is Llama 4 Scout better than Mistral Small 3.1?
Mistral Small 3.1 is the stronger model overall, scoring 31.7 to 27.7 on the Noometry Index. Llama 4 Scout costs 2.7× less per token, which makes it the better buy when Mistral Small 3.1's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Scout or Mistral Small 3.1?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Mistral Small 3.1 lists at $0.35 and $0.56.
Is Llama 4 Scout or Mistral Small 3.1 better for coding?
Mistral Small 3.1 scores higher on coding benchmarks: 38.3 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do Llama 4 Scout and Mistral Small 3.1 share?
27 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Mistral Small 3.1 has 28.