Model comparison
Llama 4 Scout vs Mixtral 8x22B
Llama 4 Scout and Mixtral 8x22B score almost the same on the Noometry Index (27.7 vs 27.1), so choose on price, context window or the category you care about most.
Last verified . 28 shared benchmarks.
Meta
Mistral AISummary
- They share 28 benchmarks with published results for both. Llama 4 Scout scores higher in 5 categories and Mixtral 8x22B in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 4 Scout leads 31.9 to 15.1.
- The biggest single-benchmark swing is MATH Level 5: 62.3% for Llama 4 Scout and 24.2% for Mixtral 8x22B.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- Llama 4 Scout accepts more context: 128K tokens versus 64K.
Side by side
| Llama 4 Scout | Mixtral 8x22B | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 27.7 | 27.1 |
| Released | 2025-04-05 | 2024-04-17 |
| Weights | Open | Open |
| Context window | 128K | 64K |
| Max output | 4K | 64K |
| Input $ / M tokens | $0.10 | $2 |
| Output $ / M tokens | $0.30 | $6 |
| Results tracked | 43 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mixtral 8x22B leads
Llama 4 Scout: 20.2 (#339), Mixtral 8x22B: 24.2 (#329)
| Benchmark | Llama 4 Scout | Mixtral 8x22B |
|---|---|---|
| LMArena Coding | 1286 | 1166 |
| BigCodeBench Complete | 43.1% | 50.2% |
| SWE-bench Verified (bash only) | 9.1% | — |
| SciCode | 17% | — |
| WeirdML | — | 3.2% |
| BigCodeBench Instruct | — | 40.6% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |
Agentic & Tool Use Llama 4 Scout leads
Llama 4 Scout: 24.6 (#119), Mixtral 8x22B: 23.1 (#127)
| Benchmark | Llama 4 Scout | Mixtral 8x22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |
| Cybench | — | 7.5% |
Reasoning Mixtral 8x22B leads
Llama 4 Scout: 9.1 (#345), Mixtral 8x22B: 19.9 (#248)
| Benchmark | Llama 4 Scout | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1266 | 1150 |
| DTBench | 57.9% | 55.1% |
| Epoch Capabilities Index | 129.64 | 122.03 |
| ForecastBench | 57.5 | 56.3 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 36.9% | — |
| ARC-AGI-1 | 0.5% | — |
| CritPt | 0% | — |
| LMCA | 12% | — |
Math Mixtral 8x22B leads
Llama 4 Scout: 19.6 (#286), Mixtral 8x22B: 22.9 (#275)
| Benchmark | Llama 4 Scout | Mixtral 8x22B |
|---|---|---|
| Omni-MATH | 37.3% | 16.3% |
| LMArena Math | 1287 | 1184 |
| MATH Level 5 | 62.3% | 24.2% |
| OTIS Mock AIME 2024-2025 | 7.8% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
Knowledge Llama 4 Scout leads
Llama 4 Scout: 31.9 (#217), Mixtral 8x22B: 15.1 (#293)
| Benchmark | Llama 4 Scout | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | 51.8% | 34.1% |
| MMLU-Pro | 74.2% | 46% |
| GPQA (HELM) | 50.7% | 33.4% |
| LMArena Expert | 1235 | 1113 |
| Vectara Hallucination Rate | 7.7% | — |
| MMLU | — | 77.8% |
Multimodal Not comparable
Llama 4 Scout: 32.2 (#102), Mixtral 8x22B: —
| Benchmark | Llama 4 Scout | Mixtral 8x22B |
|---|---|---|
| LMArena Vision | 1118 | — |
| SpatialViz-Bench | 34.2% | — |
Multilingual Llama 4 Scout leads
Llama 4 Scout: 41.0 (#212), Mixtral 8x22B: 32.8 (#255)
| Benchmark | Llama 4 Scout | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1252 | 1128 |
| LMArena Chinese | 1255 | 1116 |
| LMArena French | 1282 | 1166 |
| LMArena German | 1272 | 1141 |
| LMArena Japanese | 1206 | 1037 |
| LMArena Korean | 1207 | 1057 |
| LMArena Russian | 1263 | 1158 |
| LMArena Spanish | 1278 | 1151 |
Instruction Following Llama 4 Scout leads
Llama 4 Scout: 65.8 (#217), Mixtral 8x22B: 57.7 (#266)
| Benchmark | Llama 4 Scout | Mixtral 8x22B |
|---|---|---|
| IFEval | 81.8% | 72.4% |
| LMArena Instruction Following | 1248 | 1147 |
Long Context Mixtral 8x22B leads
Llama 4 Scout: 27.5 (#294), Mixtral 8x22B: 34.7 (#247)
| Benchmark | Llama 4 Scout | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1265 | 1144 |
| Fiction.LiveBench | 36% | — |
Writing & Preference Too close to call
Llama 4 Scout: 37.0 (#261), Mixtral 8x22B: 36.9 (#262)
| Benchmark | Llama 4 Scout | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1279 | 1162 |
| LMArena Creative Writing | 1249 | 1141 |
| WildBench | 78% | 71.1% |
| LMArena Multi-Turn | 1280 | 1130 |
| EQ-Bench Creative Writing | 783 | — |
Frequently asked questions
Is Llama 4 Scout better than Mixtral 8x22B?
Llama 4 Scout and Mixtral 8x22B score almost the same on the Noometry Index (27.7 vs 27.1), so choose on price, context window or the category you care about most.
Which is cheaper, Llama 4 Scout or Mixtral 8x22B?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Mixtral 8x22B lists at $2 and $6.
Is Llama 4 Scout or Mixtral 8x22B better for coding?
Mixtral 8x22B scores higher on coding benchmarks: 24.2 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Llama 4 Scout does, with 128K tokens against 64K.
How many benchmarks do Llama 4 Scout and Mixtral 8x22B share?
28 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Mixtral 8x22B has 34.