Model comparison
Llama 4 Scout vs Mistral Large
Mistral Large is the stronger model overall, scoring 31.9 to 27.7 on the Noometry Index. Llama 4 Scout costs 20× less per token, which makes it the better buy when Mistral Large's lead doesn't matter for your workload.
Last verified . 36 shared benchmarks.
Meta
Mistral AISummary
- They share 36 benchmarks with published results for both. Llama 4 Scout scores higher in 3 categories and Mistral Large in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Mistral Large leads 34.3 to 20.2.
- The biggest single-benchmark swing is SciCode: 17% for Llama 4 Scout and 36.2% for Mistral Large.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $2 / $6 for Mistral Large.
- Mistral Large accepts more context: 131K tokens versus 128K.
Side by side
| Llama 4 Scout | Mistral Large | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 27.7 | 31.9 |
| Released | 2025-04-05 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 4K | 16K |
| Input $ / M tokens | $0.10 | $2 |
| Output $ / M tokens | $0.30 | $6 |
| Results tracked | 43 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large leads
Llama 4 Scout: 20.2 (#339), Mistral Large: 34.3 (#240)
| Benchmark | Llama 4 Scout | Mistral Large |
|---|---|---|
| SciCode | 17% | 36.2% |
| LMArena Coding | 1286 | 1277 |
| BigCodeBench Complete | 43.1% | 38.3% |
| SWE-bench Verified (bash only) | 9.1% | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| ALE-Bench | — | 264.7 |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Mistral Large leads
Llama 4 Scout: 24.6 (#119), Mistral Large: 28.6 (#89)
| Benchmark | Llama 4 Scout | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | 38.4% |
Reasoning Mistral Large leads
Llama 4 Scout: 9.1 (#345), Mistral Large: 15.8 (#310)
| Benchmark | Llama 4 Scout | Mistral Large |
|---|---|---|
| CritPt | 0% | 0% |
| LMArena Hard Prompts | 1266 | 1257 |
| DTBench | 57.9% | 65.1% |
| LMCA | 12% | 16.7% |
| Epoch Capabilities Index | 129.64 | 128.52 |
| ForecastBench | 57.5 | 57.1 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | — | 22.5% |
| Kagi LLM Benchmark | 36.9% | — |
| ARC-AGI-1 | 0.5% | — |
| LiveBench Reasoning | — | 43.5% |
| LiveBench Data Analysis | — | 50.1% |
| LiveBench | — | 48.4% |
Math Llama 4 Scout leads
Llama 4 Scout: 19.6 (#286), Mistral Large: 18.2 (#291)
| Benchmark | Llama 4 Scout | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.8% | 8.5% |
| Omni-MATH | 37.3% | 28.1% |
| LMArena Math | 1287 | 1262 |
| MATH Level 5 | 62.3% | 50.3% |
| FrontierMath (Feb 2025 set) | 0% | 0.3% |
| LiveBench Math | — | 42.5% |
Knowledge Llama 4 Scout leads
Llama 4 Scout: 31.9 (#217), Mistral Large: 30.1 (#230)
| Benchmark | Llama 4 Scout | Mistral Large |
|---|---|---|
| GPQA Diamond | 51.8% | 51.3% |
| MMLU-Pro | 74.2% | 59.9% |
| Vectara Hallucination Rate | 7.7% | 4.5% |
| GPQA (HELM) | 50.7% | 43.5% |
| LMArena Expert | 1235 | 1232 |
| Confabulations | — | 21.4% |
| MMLU | — | 80% |
Multimodal Not comparable
Llama 4 Scout: 32.2 (#102), Mistral Large: —
| Benchmark | Llama 4 Scout | Mistral Large |
|---|---|---|
| LMArena Vision | 1118 | — |
| SpatialViz-Bench | 34.2% | — |
Multilingual Llama 4 Scout leads
Llama 4 Scout: 41.0 (#212), Mistral Large: 40.0 (#219)
| Benchmark | Llama 4 Scout | Mistral Large |
|---|---|---|
| LMArena Non-English | 1252 | 1237 |
| LMArena Chinese | 1255 | 1240 |
| LMArena French | 1282 | 1325 |
| LMArena German | 1272 | 1254 |
| LMArena Japanese | 1206 | 1188 |
| LMArena Korean | 1207 | 1202 |
| LMArena Russian | 1263 | 1257 |
| LMArena Spanish | 1278 | 1268 |
Instruction Following Mistral Large leads
Llama 4 Scout: 65.8 (#217), Mistral Large: 67.9 (#191)
| Benchmark | Llama 4 Scout | Mistral Large |
|---|---|---|
| IFEval | 81.8% | 87.7% |
| LMArena Instruction Following | 1248 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
Long Context Mistral Large leads
Llama 4 Scout: 27.5 (#294), Mistral Large: 38.3 (#199)
| Benchmark | Llama 4 Scout | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1265 | 1261 |
| Fiction.LiveBench | 36% | — |
Writing & Preference Mistral Large leads
Llama 4 Scout: 37.0 (#261), Mistral Large: 40.7 (#242)
| Benchmark | Llama 4 Scout | Mistral Large |
|---|---|---|
| LMArena Text | 1279 | 1266 |
| LMArena Creative Writing | 1249 | 1243 |
| EQ-Bench Creative Writing | 783 | 985 |
| WildBench | 78% | 80.1% |
| LMArena Multi-Turn | 1280 | 1260 |
| Short-Story Creative Writing | — | 69% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is Llama 4 Scout better than Mistral Large?
Mistral Large is the stronger model overall, scoring 31.9 to 27.7 on the Noometry Index. Llama 4 Scout costs 20× less per token, which makes it the better buy when Mistral Large's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Scout or Mistral Large?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Mistral Large lists at $2 and $6.
Is Llama 4 Scout or Mistral Large better for coding?
Mistral Large scores higher on coding benchmarks: 34.3 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Mistral Large does, with 131K tokens against 128K.
How many benchmarks do Llama 4 Scout and Mistral Large share?
36 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Mistral Large has 51.