Model comparison
Llama 4 Scout vs Mistral Small 3
Mistral Small 3 is the stronger model overall, scoring 31.2 to 27.7 on the Noometry Index.
Last verified . 21 shared benchmarks.
Meta
Mistral AISummary
- They share 21 benchmarks with published results for both. Llama 4 Scout scores higher in 5 categories and Mistral Small 3 in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Mistral Small 3 leads 36.5 to 20.2.
- The biggest single-benchmark swing is BigCodeBench Complete: 43.1% for Llama 4 Scout and 50.4% for Mistral Small 3.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.10 / $0.30 for Llama 4 Scout.
- Llama 4 Scout accepts more context: 128K tokens versus 33K.
Side by side
| Llama 4 Scout | Mistral Small 3 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 27.7 | 31.2 |
| Released | 2025-04-05 | 2025-01-30 |
| Weights | Open | Open |
| Context window | 128K | 33K |
| Max output | 4K | 16K |
| Input $ / M tokens | $0.10 | $0.05 |
| Output $ / M tokens | $0.30 | $0.08 |
| Results tracked | 43 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3 leads
Llama 4 Scout: 20.2 (#339), Mistral Small 3: 36.5 (#207)
| Benchmark | Llama 4 Scout | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1286 | 1246 |
| BigCodeBench Complete | 43.1% | 50.4% |
| SWE-bench Verified (bash only) | 9.1% | — |
| SciCode | 17% | — |
| BigCodeBench Instruct | — | 45.3% |
Agentic & Tool Use Not comparable
Llama 4 Scout: 24.6 (#119), Mistral Small 3: —
| Benchmark | Llama 4 Scout | Mistral Small 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |
Reasoning Mistral Small 3 leads
Llama 4 Scout: 9.1 (#345), Mistral Small 3: 18.9 (#273)
| Benchmark | Llama 4 Scout | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1266 | 1233 |
| Epoch Capabilities Index | 129.64 | 127.07 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 36.9% | — |
| ARC-AGI-1 | 0.5% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 0% |
| DTBench | 57.9% | — |
| LMCA | 12% | — |
| ForecastBench | 57.5 | — |
Math Llama 4 Scout leads
Llama 4 Scout: 19.6 (#286), Mistral Small 3: 16.3 (#295)
| Benchmark | Llama 4 Scout | Mistral Small 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.8% | 6.7% |
| LMArena Math | 1287 | 1240 |
| Omni-MATH | 37.3% | — |
| MATH Level 5 | 62.3% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
Knowledge Llama 4 Scout leads
Llama 4 Scout: 31.9 (#217), Mistral Small 3: 25.1 (#263)
| Benchmark | Llama 4 Scout | Mistral Small 3 |
|---|---|---|
| GPQA Diamond | 51.8% | 47.3% |
| LMArena Expert | 1235 | 1202 |
| MMLU-Pro | 74.2% | — |
| Confabulations | — | 25.2% |
| Vectara Hallucination Rate | 7.7% | — |
| GPQA (HELM) | 50.7% | — |
Multimodal Not comparable
Llama 4 Scout: 32.2 (#102), Mistral Small 3: —
| Benchmark | Llama 4 Scout | Mistral Small 3 |
|---|---|---|
| LMArena Vision | 1118 | — |
| SpatialViz-Bench | 34.2% | — |
Multilingual Llama 4 Scout leads
Llama 4 Scout: 41.0 (#212), Mistral Small 3: 37.3 (#236)
| Benchmark | Llama 4 Scout | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1252 | 1198 |
| LMArena Chinese | 1255 | 1204 |
| LMArena French | 1282 | 1203 |
| LMArena German | 1272 | 1211 |
| LMArena Japanese | 1206 | 1111 |
| LMArena Korean | 1207 | 1188 |
| LMArena Russian | 1263 | 1216 |
| LMArena Spanish | 1278 | — |
Instruction Following Llama 4 Scout leads
Llama 4 Scout: 65.8 (#217), Mistral Small 3: 63.7 (#229)
| Benchmark | Llama 4 Scout | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1214 |
| IFEval | 81.8% | — |
Long Context Mistral Small 3 leads
Llama 4 Scout: 27.5 (#294), Mistral Small 3: 37.8 (#211)
| Benchmark | Llama 4 Scout | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1265 | 1246 |
| Fiction.LiveBench | 36% | — |
Writing & Preference Llama 4 Scout leads
Llama 4 Scout: 37.0 (#261), Mistral Small 3: 32.2 (#280)
| Benchmark | Llama 4 Scout | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1279 | 1234 |
| LMArena Creative Writing | 1249 | 1195 |
| EQ-Bench Creative Writing | 783 | 707 |
| LMArena Multi-Turn | 1280 | 1217 |
| WildBench | 78% | — |
Frequently asked questions
Is Llama 4 Scout better than Mistral Small 3?
Mistral Small 3 is the stronger model overall, scoring 31.2 to 27.7 on the Noometry Index.
Which is cheaper, Llama 4 Scout or Mistral Small 3?
Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Llama 4 Scout lists at $0.10 and $0.30.
Is Llama 4 Scout or Mistral Small 3 better for coding?
Mistral Small 3 scores higher on coding benchmarks: 36.5 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Llama 4 Scout does, with 128K tokens against 33K.
How many benchmarks do Llama 4 Scout and Mistral Small 3 share?
21 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Mistral Small 3 has 24.