Model card
Llama-4-Scout.
Metaopen-source109B total / 17B active (16 experts) paramsMixture-of-Experts Transformer
Meta Llama 4 Scout. 16-expert MoE. Released April 2025. Context: 10M tokens.
§ 01 · Benchmarks
Every benchmark Llama-4-Scout has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | MBPP | Computer Code · Code Generation | pass@1 | 67.8% | #16 | — | source ↗ |
| 02 | LiveCodeBench | Computer Code · Code Generation | pass@1 | 32.8% | #27 | — | source ↗ |
| 03 | PLCC | Natural Language Processing · Polish Cultural Competency | grammar | 51.0% | #108 | — | source ↗ |
| 04 | PLCC | Natural Language Processing · Polish Cultural Competency | vocabulary | 42.0% | #113 | — | source ↗ |
| 05 | PLCC | Natural Language Processing · Polish Cultural Competency | geography | 51.0% | #130 | — | source ↗ |
| 06 | PLCC | Natural Language Processing · Polish Cultural Competency | average | 41.5% | #135 | — | source ↗ |
| 07 | PLCC | Natural Language Processing · Polish Cultural Competency | culture-and-tradition | 35.0% | #137 | — | source ↗ |
| 08 | PLCC | Natural Language Processing · Polish Cultural Competency | history | 47.0% | #144 | — | source ↗ |
| 09 | PLCC | Natural Language Processing · Polish Cultural Competency | art-and-entertainment | 23.0% | #144 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area
Where Llama-4-Scout actually performs.
§ 04 · Related models
Other Meta models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
sdadas/PLCC
7
results
meta-model-card
2
results
9 of 9 rows marked verified.