Llama 4 Scout llama-4-scout
meta-llama · llama
unranked — no quality signals yet
- params
- 109B (A17B)
- arch
- moe
- context
- 10000k
- license
- llama4 open weights gated
- released
- Apr 2025
- downloads/30d
- 722.0k
# why ranked
Overall: provisional — score 10.0 ● low — a single signal; treat with caution
provisional: too few independent signals for a numbered position — the score is shown, but this model sorts after every ranked model.
| signal | weight | input (0–100) |
|---|---|---|
| aa_intelligence | 0.50 | 10.0 |
| arena_elo | 0.30 | — |
| bench_composite | 0.20 | — |
missing signals are dropped and the remaining weights renormalized — never imputed.
Coding: provisional — score 3.4 ● low — a single signal; treat with caution
provisional: too few independent signals for a numbered position — the score is shown, but this model sorts after every ranked model.
| signal | weight | input (0–100) |
|---|---|---|
| aa_coding | 0.25 | 3.4 |
| aider_polyglot | 0.25 | — |
| arena_elo_code | 0.15 | — |
| swe_bench_verified | 0.35 | — |
missing signals are dropped and the remaining weights renormalized — never imputed.
# trend
# benchmarks
| benchmark | score | source | date |
|---|---|---|---|
| AA Coding Index | 8.2 | Artificial Analysis | — |
| AA Intelligence Index | 10.0 | Artificial Analysis | — |
| AA Math Index | 14.0 | Artificial Analysis | — |
| Chartqa | 0.9 / 1 | LLM Stats | — |
| Docvqa | 0.9 / 1 | LLM Stats | — |
# where to run
| provider | quant | ctx | $/M in | $/M out | $/M blend | tps | uptime |
|---|---|---|---|---|---|---|---|
| DeepInfra | fp8 | 320k | $0.10 | $0.30 | $0.15 | — | 99.7% |
| Groq | unknown | 128k | $0.11 | $0.34 | $0.17 | — | 100.0% |
| Novita | bf16 | 128k | $0.18 | $0.59 | $0.28 | — | 99.5% |
| unknown | 1280k | $0.25 | $0.70 | $0.36 | — | 99.8% |
blended = (3·input + output) / 4 per 1M tokens · cheapest first
source aliases
- aa
llama-4-scout- arena
Llama-4-Scout-17B-16E-Instruct- openrouter
meta-llama/llama-4-scout