Skip to content
Model Pareto

Llama 4 Scout

MetaOpen weightsartificialanalysis.ai ↗
Compare with nearest rivalsCompare with…
Input
$0.19/M tok
Output
$0.68/M tok
Blended
$0.313/M tok · 3:1
Speed
107tok/s
Context
10Mtokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: Llama 4 Scout. Price = AA median host price.

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs, compared with the API price above.

Hardware
4× H100 80GB
FP8 weights
Throughput
~9,075 tok/s
many requests batched
Price
$0.14–1.31 /M tok
busy → light use
On your own machine
Mac Studio M5 Max 128GB (int4, ~51 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • FP8 weights (108.6B params, 17B active per token) + 40% KV-cache headroom ≈ 152 GB
  • 4× H100 80GB at $2.69–$6.88/GPU-hour on-demand (2026-09-24)
  • ~9,075 output tok/s aggregate at batch 265 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~110,009 tok/s
  • Low = 75% utilization at the low GPU price; high = 20% at the high price

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Coding

SWE-bench Pro (Public)Estimated
~#18 of 19 (estimated)~46.1%
  1. #1Claude Opus 5.589.9%
  2. #2Claude Sonnet 5.581.3%
  3. #17Muse Glimmer51.2%
  4. ~#18Llama 4 ScoutEstimated46.1%
  5. #18Nex-N2.5-Mini43.8%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#29 of 31 (estimated)~37.0%
  1. #1DeepSeek V4.1 Flash74.2%
  2. #2Grok 4.772.6%
  3. #28Qwen3.8 27B42.2%
  4. ~#29Llama 4 ScoutEstimated37.0%
  5. #29Nex-N2.5-Mini36.1%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~last of 15 (estimated)below measured range (<41.1)
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
  3. #14GPT-6 Luna41.1
  4. ~#15Llama 4 ScoutEstimated<41.1
No published score — estimated from related benchmarks

Writing & chat

MMMLUEstimated
~last of 5 (estimated)below measured range (<81.3%)
  1. #1Gemini 3.1 Pro92.6%
  2. #2Gemma 4 31B88.4%
  3. #4gpt-oss-120b81.3%
  4. ~#5Llama 4 ScoutEstimated<81.3%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#44 of 54 (estimated)~1328 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #43gpt-oss-120b1338
  4. ~#44Llama 4 ScoutEstimated1328
  5. #44INTELLECT-3Few votes1327
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#45 of 54 (estimated)~1351 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #44gpt-oss-120b1352
  4. ~#45Llama 4 ScoutEstimated1351
  5. #45Llama 3.1 Nemotron Ultra 253B v1Few votes1348
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#24 of 26 (estimated)~1343 Elo
  1. #1GPT-6 Astra2173
  2. #2Claude Fable 5.12162
  3. #23Gemma 4 31B1368
  4. ~#24Llama 4 ScoutEstimated1343
  5. #24gpt-oss-120b961
No published score — estimated from related benchmarks

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2Llama 4 ScoutEstimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
CharXiv ReasoningEstimated
~last of 9 (estimated)below measured range (<74.5%)
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #8Gemini 3.5 Flash-Lite74.5%
  4. ~#9Llama 4 ScoutEstimated<74.5%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~last of 8 (estimated)below measured range (<75.8%)
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #7Muse Glimmer75.8%
  4. ~#8Llama 4 ScoutEstimated<75.8%
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#41 of 43 (estimated)~0.7%
  1. #1GPT-6 Astra31.0%
  2. #2Muse Spark 1.326.6%
  3. #40Ministral 3 8B0.8%
  4. ~#41Llama 4 ScoutEstimated0.7%
  5. #41Ministral 3 3B0.0%
No published score — estimated from related benchmarks
ChartographyEstimated
~last of 23 (estimated)below measured range (<9.0%)
  1. #1GPT-6 Astra71.0%
  2. #2Claude Opus 5.566.3%
  3. #22Mistral Large 39.0%
  4. ~#23Llama 4 ScoutEstimated<9.0%
No published score — estimated from related benchmarks

Hard reasoning

AA Intelligence IndexEstimated
~#70 of 75 (estimated)~6.7
  1. #1Claude Opus 5.557.6
  2. #2Claude Sonnet 5.556.0
  3. #69Devstral Small 27.5
  4. ~#70Llama 4 ScoutEstimated6.7
  5. #70Celeris-16.3
No published score — estimated from related benchmarks

Agents

OSWorld-VerifiedEstimated
~#11 of 12 (estimated)~57.6%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #10Muse Glimmer65.9%
  4. ~#11Llama 4 ScoutEstimated57.6%
  5. #11Claude Haiku 4.550.7%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. #4GPT-5.547.5%
  4. ~#5Llama 4 ScoutEstimated<47.5%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#17 of 18 (estimated)~43.9%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #16Nemotron 3 Ultra44.4%
  4. ~#17Llama 4 ScoutEstimated43.9%
  5. #17Mistral Small 421.3%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#76 of 87 (estimated)~340 Elo
  1. #1Claude Opus 5.51846
  2. #2Claude Fable 5.11735
  3. #75Mistral Small 4349
  4. ~#76Llama 4 ScoutEstimated340
  5. #76gpt-oss-20b327
No published score — estimated from related benchmarks