Model comparison
Llama 4 Scout vs Mistral Medium 3.5
Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 27.7 on the Noometry Index. Llama 4 Scout costs 20× less per token, which makes it the better buy when Mistral Medium 3.5's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Meta
Mistral AISummary
- They share 19 benchmarks with published results for both. Llama 4 Scout scores higher in 0 categories and Mistral Medium 3.5 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium 3.5 leads 58.5 to 37.0.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
- Mistral Medium 3.5 accepts more context: 262K tokens versus 128K.
Side by side
| Llama 4 Scout | Mistral Medium 3.5 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 27.7 | 40.2 |
| Released | 2025-04-05 | — |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 210K |
| Input $ / M tokens | $0.10 | $1.50 |
| Output $ / M tokens | $0.30 | $7.50 |
| Results tracked | 43 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Medium 3.5 leads
Llama 4 Scout: 20.2 (#339), Mistral Medium 3.5: 36.0 (#213)
| Benchmark | Llama 4 Scout | Mistral Medium 3.5 |
|---|---|---|
| LMArena Coding | 1286 | 1461 |
| SWE-bench Verified (bash only) | 9.1% | — |
| LMArena WebDev | — | 1264 |
| SciCode | 17% | — |
| BigCodeBench Complete | 43.1% | — |
Agentic & Tool Use Not comparable
Llama 4 Scout: 24.6 (#119), Mistral Medium 3.5: —
| Benchmark | Llama 4 Scout | Mistral Medium 3.5 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |
Reasoning Mistral Medium 3.5 leads
Llama 4 Scout: 9.1 (#345), Mistral Medium 3.5: 17.3 (#295)
| Benchmark | Llama 4 Scout | Mistral Medium 3.5 |
|---|---|---|
| Kagi LLM Benchmark | 36.9% | 41.4% |
| LMArena Hard Prompts | 1266 | 1436 |
| Epoch Capabilities Index | 129.64 | 141.35 |
| ARC-AGI-2 | 0% | — |
| NYT Connections (extended) | — | 12.9% |
| ARC-AGI-1 | 0.5% | — |
| CritPt | 0% | — |
| DTBench | 57.9% | — |
| LMCA | 12% | — |
| ForecastBench | 57.5 | — |
Math Mistral Medium 3.5 leads
Llama 4 Scout: 19.6 (#286), Mistral Medium 3.5: 39.1 (#113)
| Benchmark | Llama 4 Scout | Mistral Medium 3.5 |
|---|---|---|
| LMArena Math | 1287 | 1431 |
| OTIS Mock AIME 2024-2025 | 7.8% | — |
| Omni-MATH | 37.3% | — |
| MATH Level 5 | 62.3% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
Knowledge Mistral Medium 3.5 leads
Llama 4 Scout: 31.9 (#217), Mistral Medium 3.5: 40.0 (#126)
| Benchmark | Llama 4 Scout | Mistral Medium 3.5 |
|---|---|---|
| LMArena Expert | 1235 | 1432 |
| GPQA Diamond | 51.8% | — |
| MMLU-Pro | 74.2% | — |
| Vectara Hallucination Rate | 7.7% | — |
| GPQA (HELM) | 50.7% | — |
Multimodal Mistral Medium 3.5 leads
Llama 4 Scout: 32.2 (#102), Mistral Medium 3.5: 38.3 (#65)
| Benchmark | Llama 4 Scout | Mistral Medium 3.5 |
|---|---|---|
| LMArena Vision | 1118 | 1223 |
| SpatialViz-Bench | 34.2% | — |
Multilingual Mistral Medium 3.5 leads
Llama 4 Scout: 41.0 (#212), Mistral Medium 3.5: 51.9 (#100)
| Benchmark | Llama 4 Scout | Mistral Medium 3.5 |
|---|---|---|
| LMArena Non-English | 1252 | 1404 |
| LMArena Chinese | 1255 | 1442 |
| LMArena French | 1282 | 1448 |
| LMArena German | 1272 | 1451 |
| LMArena Korean | 1207 | 1385 |
| LMArena Russian | 1263 | 1395 |
| LMArena Spanish | 1278 | 1409 |
| LMArena Japanese | 1206 | — |
Instruction Following Mistral Medium 3.5 leads
Llama 4 Scout: 65.8 (#217), Mistral Medium 3.5: 74.6 (#90)
| Benchmark | Llama 4 Scout | Mistral Medium 3.5 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1415 |
| IFEval | 81.8% | — |
Long Context Mistral Medium 3.5 leads
Llama 4 Scout: 27.5 (#294), Mistral Medium 3.5: 43.2 (#103)
| Benchmark | Llama 4 Scout | Mistral Medium 3.5 |
|---|---|---|
| LMArena Longer Query | 1265 | 1415 |
| Fiction.LiveBench | 36% | — |
Writing & Preference Mistral Medium 3.5 leads
Llama 4 Scout: 37.0 (#261), Mistral Medium 3.5: 58.5 (#117)
| Benchmark | Llama 4 Scout | Mistral Medium 3.5 |
|---|---|---|
| LMArena Text | 1279 | 1421 |
| LMArena Creative Writing | 1249 | 1374 |
| LMArena Multi-Turn | 1280 | 1423 |
| EQ-Bench Creative Writing | 783 | — |
| WildBench | 78% | — |
| EQ-Bench 4 | — | 993 |
Frequently asked questions
Is Llama 4 Scout better than Mistral Medium 3.5?
Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 27.7 on the Noometry Index. Llama 4 Scout costs 20× less per token, which makes it the better buy when Mistral Medium 3.5's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Scout or Mistral Medium 3.5?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.
Is Llama 4 Scout or Mistral Medium 3.5 better for coding?
Mistral Medium 3.5 scores higher on coding benchmarks: 36.0 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium 3.5 does, with 262K tokens against 128K.
How many benchmarks do Llama 4 Scout and Mistral Medium 3.5 share?
19 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Mistral Medium 3.5 has 22.