Models / Llama 4 Scout

Meta

Llama 4 Scout

Llama 4 Scout is strongest at sticking to the facts; worth a look for simple, high-volume work where cost matters most. The cheapest model of similar intelligence is Gemma 3 4B, at $0.04 per million tokens against $0.15.

Results 16 Nov 2026 · 33 results · 5 sources

Test Llama 4 Scout on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$0.10 in · $0.30 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices
Speed
132 tokens a second; on its test prompt the answer starts after 0.6 s, thinking time included
Artificial Analysis, on its usual API
Intelligence Index
6.5
Artificial Analysis
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
Meta, based in the US
Weights published
Released
5 Apr 2025
1,310,720 tokens of context

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location, plus models with published weights. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 173rd of 185Claude Opus 5.5 – $0.15 blended, 13th percentilecheapest: Mistral Nemo 29th of 65Nemotron 3.5 Super VL
Models priced under $0.25 per million tokens 30th of 41Claude Haiku 5.5 – sets this group 8th of 19Nemotron 3.5 Super VL
Models with similar intelligence sets this group – $0.15 blended, 37th percentilecheapest: Gemma 3 4B 5th of 14gpt-oss-20b
Models writing 100–200 tokens a second 21st of 21Claude Sonnet 5.5 – $0.15 blended, 5th percentilecheapest: Qwen3.5-9B sets this group
Models from developers based in the US 84th of 92Claude Opus 5.5 – $0.15 blended, 15th percentilecheapest: Gemma 3 4B 18th of 33Nemotron 3.5 Super VL
Open-weights models 93rd of 104MiMo-V2.6-Pro – $0.15 blended, 21st percentilecheapest: Mistral Nemo 18th of 43Nemotron 3.5 Super VL

The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.

How good is it, and for what?

Each use case ranks the available models its benchmarks measured, then those priced under $0.25 per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.

Product listingsTurning a sparse product feed and photos into listings that can go live Not measured
  • CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is Not measured
  • DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled Not measured
  • SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending Not measured
  • ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 146th of 159 available · 29th of 37 at its price
BenchmarkLlama 4 ScoutRank among availableBest available
Berkeley Function Calling Leaderboard (BFCL) V4BFCL: overall accuracy · reported 28.1% 28th of 36 Claude Opus 4.5 77.5%
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 0.0% 67th of 107 Kimi K3.1 Pro 67.2%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 3.7% 101st of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 3.3% 100th of 104 Grok 4.6 50.7%
  • tau2-bench: has not measured this model.
  • OpenHands Index: has not measured this model.
  • Microsoft STATE-Bench: has not measured this model.
  • Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects Not measured
  • APEX-Agents: has not measured this model.
  • GDP.pdf: has not measured this model.
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge 165th of 187 available · 29th of 41 at its price
BenchmarkLlama 4 ScoutRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 6.5 173rd of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 3.8% 172nd of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 58.7% 135th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 150th of 169 available · 28th of 39 at its price
BenchmarkLlama 4 ScoutRank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,322 130th of 153 Gemini 4 Argon 1,525
UGI LeaderboardUGI: writing score · reported 26.7 110th of 124 Gemini 3.8 Flash 78.6
Sticking to the factsSummarising without inventing things, and factual answers 47th of 139 available · 13th of 30 at its price
BenchmarkLlama 4 ScoutRank among availableBest available
Vectara Hallucination LeaderboardVectara: hallucination rate · reported 7.7% 26th of 71 GPT-5.4 nano 3.1%
  • Arena (formerly LMArena): has not measured this model.
  • SimpleQA Verified (Epoch AI): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess) Not measured
  • BulletBench: has not measured this model.

Nearest alternatives

Against Llama 4 Scout at $0.15 blended, Intelligence Index 6.5. "Similar intelligence" means within 4 points or better.

Where to run it

2 hosts on OpenRouter at the standard service tier, with a median of $0.26 blended per million tokens; quantisation where the host states it: FP8. Cheapest first.

HostQuantisationInputOutputBlended
DeepInfraFP8$0.10$0.30$0.15
Googlenot stated$0.25$0.70$0.36

Other service tiers, not counted above: DeepInfra flex $0.08 in, $0.24 out; DeepInfra priority $0.15 in, $0.45 out. Flex and batch are cheaper but slower or queued; priority and fast cost more.

Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

Llama 4 ScoutClaude Haiku 5.5
most intelligent at under $0.25 per million tokens
Gemma 3 4B
cheapest with similar intelligence
gpt-oss-20b
fastest with similar intelligence
Claude Opus 5.5
most intelligent available today
Price per million tokens $0.15 $0.20$0.04$0.06$8.00
Tokens a second 132 240–27796
Intelligence Index 6.5 43.44.810.057.6
Spring Prompt overall – 40––82
Rank among available models, by use case
Product listings – 20th––13th
Decks from an analysis – 18th––7th
User surveys – 7th––4th
Marketing planning – 30th––9th
Agents and tool use 146th of 159 28th158th130th3rd
Professional work – –––3rd
Reasoning and knowledge 165th of 187 25th181st132nd1st
Writing 150th of 169 –157th155th5th
Sticking to the facts 47th of 139 –32nd–3rd
Speed under pressure – 21st–––

Shaded figures are better than Llama 4 Scout's. A dash means no result.

Where it has been measured

2nd cheapest of the 21 models writing 100–200 tokens a second. 30th most intelligent of the 41 models priced under $0.25 per million tokens. Among models available today, in the bottom quarter for agents and tool use, reasoning and knowledge, and writing.

Every result

33 published results from 5 sources, each in the source's own units, with the configuration that produced it.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 6 results
MeasureValueRankConfigurationDated
Arena Text: business, management and financeArena rating, higher is better 1,316
1,307–1,325
251 of 406 Llama 4 Scout 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,289
1,279–1,299
249 of 411 Llama 4 Scout 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,308
1,293–1,324
253 of 363 Llama 4 Scout 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,299
1,292–1,306
263 of 413 Llama 4 Scout 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,322
1,317–1,326
257 of 413 Llama 4 Scout 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,305
1,297–1,313
250 of 412 Llama 4 Scout 2 Oct 2026

Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Artificial Analysis · reported by Artificial Analysis · 14 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 8.2 178 of 187 Llama 4 Scout 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 6.5 391 of 413 Llama 4 Scout 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 58.7% 298 of 360 Llama 4 Scout 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 3.8% 389 of 419 Llama 4 Scout 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 39.5% 209 of 288 Llama 4 Scout 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 27.7% 347 of 407 Llama 4 Scout 20 Oct 2026
Artificial Analysis: Output speedtokens per second, higher is better 132 49 of 137 Llama 4 Scout 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 21.3% 202 of 205 Llama 4 Scout 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 3.7% 174 of 188 Llama 4 Scout 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 0.0% 152 of 204 Llama 4 Scout 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 1.5% 266 of 282 Llama 4 Scout 20 Oct 2026
Artificial Analysis: Time to first answer tokenseconds, lower is better 0.61 12 of 137 Llama 4 Scout 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 3.3% 170 of 175 Llama 4 Scout 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 15.5% 268 of 286 Llama 4 Scout 20 Oct 2026

Not shown: Not your codebase or tools.

Berkeley Function Calling Leaderboard (BFCL) V4 · reported by Berkeley Function Calling Leaderboard (BFCL) V4 · 8 results
MeasureValueRankConfigurationDated
BFCL: irrelevance detection% correct, higher is better 44.9% 101 of 109 Llama 4 Scout (bfcl fc) 16 Dec 2025
BFCL: memory% correct, higher is better 8.2% 79 of 109 Llama 4 Scout (bfcl fc) 16 Dec 2025
BFCL: multi-turn tasks% correct, higher is better 9.0% 71 of 109 Llama 4 Scout (bfcl fc) 16 Dec 2025
BFCL: overall accuracy% correct, higher is better 28.1% 72 of 109 Llama 4 Scout (bfcl fc) 16 Dec 2025
BFCL: relevance detection% correct, higher is better 100.0% 1 of 109 Llama 4 Scout (bfcl fc) 16 Dec 2025
BFCL: single-turn calls (curated)% correct, higher is better 89.4% 8 of 109 Llama 4 Scout (bfcl fc) 16 Dec 2025
BFCL: single-turn calls (user-contributed)% correct, higher is better 74.7% 41 of 109 Llama 4 Scout (bfcl fc) 16 Dec 2025
BFCL: web search% correct, higher is better 14.5% 49 of 109 Llama 4 Scout (bfcl fc) 16 Dec 2025

Not shown: Not general refusal or safety behaviour.

UGI Leaderboard · reported by UGI Leaderboard · 3 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 19.0% 171 of 379 Llama 4 Scout 26 Oct 2025
UGI: style adherencescore from 0 to 1, higher is better 0.36 136 of 379 Llama 4 Scout 26 Oct 2025
UGI: writing scorescore out of 100, higher is better 26.7 302 of 379 Llama 4 Scout 26 Oct 2025

Not shown: Not other format limits such as character counts or bullet counts.

Vectara Hallucination Leaderboard · reported by Vectara Hallucination Leaderboard · 2 results
MeasureValueRankConfigurationDated
Vectara: answer rate% of documents, higher is better 99.0% 68 of 108 Llama 4 Scout 22 Sep 2026
Vectara: hallucination rate% of summaries, lower is better 7.7% 38 of 108 Llama 4 Scout 22 Sep 2026

Not shown: Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.

Will Llama 4 Scout work for your product?

Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.

New here? Your email starts a free trial. No credit card needed.