Model comparison
Llama 4 Scout vs Mistral Small
Mistral Small is the stronger model overall, scoring 33.4 to 27.7 on the Noometry Index. Llama 4 Scout costs 1.7× less per token, which makes it the better buy when Mistral Small'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 2 categories and Mistral Small in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Small leads 52.5 to 37.0.
- The biggest single-benchmark swing is MATH Level 5: 62.3% for Llama 4 Scout and 46.8% for Mistral Small.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.15 / $0.60 for Mistral Small.
- Mistral Small accepts more context: 262K tokens versus 128K.
Side by side
| Llama 4 Scout | Mistral Small | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 27.7 | 33.4 |
| Released | 2025-04-05 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 256K |
| Input $ / M tokens | $0.10 | $0.15 |
| Output $ / M tokens | $0.30 | $0.60 |
| Results tracked | 43 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small leads
Llama 4 Scout: 20.2 (#339), Mistral Small: 34.0 (#247)
| Benchmark | Llama 4 Scout | Mistral Small |
|---|---|---|
| SciCode | 17% | 26.5% |
| LMArena Coding | 1286 | 1362 |
| BigCodeBench Complete | 43.1% | 46.6% |
| SWE-bench Verified (bash only) | 9.1% | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| ALE-Bench | — | 497.62 |
Agentic & Tool Use Mistral Small leads
Llama 4 Scout: 24.6 (#119), Mistral Small: 28.1 (#93)
| Benchmark | Llama 4 Scout | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | 37.1% |
Reasoning Mistral Small leads
Llama 4 Scout: 9.1 (#345), Mistral Small: 19.8 (#250)
| Benchmark | Llama 4 Scout | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 36.9% | 37.8% |
| CritPt | 0% | 0% |
| LMArena Hard Prompts | 1266 | 1335 |
| DTBench | 57.9% | 70.9% |
| LMCA | 12% | 20.6% |
| ARC-AGI-2 | 0% | — |
| ARC-AGI-1 | 0.5% | — |
| LiveBench Reasoning | — | 44.8% |
| LiveBench Data Analysis | — | 53.7% |
| Epoch Capabilities Index | 129.64 | — |
| ForecastBench | 57.5 | — |
| LiveBench | — | 44% |
Math Llama 4 Scout leads
Llama 4 Scout: 19.6 (#286), Mistral Small: 16.4 (#293)
| Benchmark | Llama 4 Scout | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.8% | 5.8% |
| LMArena Math | 1287 | 1341 |
| MATH Level 5 | 62.3% | 46.8% |
| Omni-MATH | 37.3% | — |
| LiveBench Math | — | 39.9% |
| FrontierMath (Feb 2025 set) | 0% | — |
Knowledge Too close to call
Llama 4 Scout: 31.9 (#217), Mistral Small: 31.0 (#222)
| Benchmark | Llama 4 Scout | Mistral Small |
|---|---|---|
| GPQA Diamond | 51.8% | 47.5% |
| Vectara Hallucination Rate | 7.7% | 5.1% |
| LMArena Expert | 1235 | 1291 |
| MMLU-Pro | 74.2% | — |
| GPQA (HELM) | 50.7% | — |
| MMLU | — | 68.7% |
Multimodal Mistral Small leads
Llama 4 Scout: 32.2 (#102), Mistral Small: 33.5 (#96)
| Benchmark | Llama 4 Scout | Mistral Small |
|---|---|---|
| LMArena Vision | 1118 | 1142 |
| SpatialViz-Bench | 34.2% | — |
Multilingual Mistral Small leads
Llama 4 Scout: 41.0 (#212), Mistral Small: 45.5 (#169)
| Benchmark | Llama 4 Scout | Mistral Small |
|---|---|---|
| LMArena Non-English | 1252 | 1315 |
| LMArena Chinese | 1255 | 1340 |
| LMArena French | 1282 | 1337 |
| LMArena German | 1272 | 1340 |
| LMArena Japanese | 1206 | 1275 |
| LMArena Korean | 1207 | 1259 |
| LMArena Russian | 1263 | 1324 |
| LMArena Spanish | 1278 | 1346 |
Instruction Following Too close to call
Llama 4 Scout: 65.8 (#217), Mistral Small: 66.4 (#209)
| Benchmark | Llama 4 Scout | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1248 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
| IFEval | 81.8% | — |
Long Context Mistral Small leads
Llama 4 Scout: 27.5 (#294), Mistral Small: 40.4 (#156)
| Benchmark | Llama 4 Scout | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1265 | 1327 |
| Fiction.LiveBench | 36% | — |
Writing & Preference Mistral Small leads
Llama 4 Scout: 37.0 (#261), Mistral Small: 52.5 (#171)
| Benchmark | Llama 4 Scout | Mistral Small |
|---|---|---|
| LMArena Text | 1279 | 1338 |
| LMArena Creative Writing | 1249 | 1305 |
| LMArena Multi-Turn | 1280 | 1344 |
| EQ-Bench Creative Writing | 783 | — |
| WildBench | 78% | — |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is Llama 4 Scout better than Mistral Small?
Mistral Small is the stronger model overall, scoring 33.4 to 27.7 on the Noometry Index. Llama 4 Scout costs 1.7× less per token, which makes it the better buy when Mistral Small's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Scout or Mistral Small?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Mistral Small lists at $0.15 and $0.60.
Is Llama 4 Scout or Mistral Small better for coding?
Mistral Small scores higher on coding benchmarks: 34.0 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Mistral Small does, with 262K tokens against 128K.
How many benchmarks do Llama 4 Scout and Mistral Small share?
29 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Mistral Small has 39.