Llama 4 Scout
Llama 4 Scout is behind the leaders in multimodal tasks. Too few results yet to rate reasoning, coding, agentic tasks, safety, long context, math, multilingual tasks, instruction following, or factuality.
Capability profile
Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.
Too few results yet to rate Reasoning, Coding, Agentic, Safety, Long Context, Math, Multilingual, Instruction Following or Factuality.
Price
$0.19input$0.68outputper million tokens
From Artificial Analysis · 5 providers tracked · All prices
Evidence
46results on43benchmarks
- 15 independently verified
- 19 aggregator
- 12 vendor-reported
From 14 sources · latest Oct 8, 2026 · How verification works
API features
Tool callingStructured outputs
As listed by OpenRouter
Research
7 papers reference Llama 4 ScoutLlama 4 Scout benchmark results
46 results on 43 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
42.2% behind the leader3 of 6 ranked benchmarks measured
- 69.40Oct 7, 2026
- 70.70Oct 7, 2026
- MMMU-Pro52.95Oct 8, 2026aa_mmmu_pro
Show 1 more multimodal resultHide 1 multimodal result
- MMMU-Pro52.20May 1, 2026image_reasoning_mmmu_pro
0 of 6 ranked benchmarks measured
- 0.00May 10, 2026
- 0.00Oct 8, 2026
- GPQA Diamond58.69Oct 8, 2026gpqa
Show 2 more reasoning resultsHide 2 reasoning results
- GPQA Diamond57.20Oct 7, 2026GPQA
- Humanity's Last Exam3.78Oct 8, 2026aa_hle
0 of 10 ranked benchmarks measured
- 9.06Sep 1, 2026
- SciCode21.30Oct 8, 2026aa_scicode
- Terminal-Bench 2.13.75Oct 8, 2026terminalbenchV21
Show 1 more coding resultHide 1 coding result
- Terminal-Bench Hard1.52Oct 8, 2026aa_terminalbench_hard
0 of 7 ranked benchmarks measured
- 0.00Oct 8, 2026
- Terminal-Bench 4.00.00Oct 8, 2026
- τ-Bench V3 · Banking3.30Oct 8, 2026tauBanking
0 of 3 ranked benchmarks measured
- 27.70Oct 8, 2026
0 of 3 ranked benchmarks measured
- IFBench39.52Oct 8, 2026aa_ifbench
0 of 4 ranked benchmarks measured
- 7.70May 2, 2026
- AA-Omniscience · Accuracy15.17Oct 8, 2026omniscienceAccuracy
- AA-Omniscience · Non-hallucination20.65Oct 8, 2026omniscienceNonHallucination
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- AA Intelligence8.00Jun 26, 2026Artificial Analysis Intelligence Index
- 52.27May 19, 2026
- 95.56May 10, 2026
- 97.00May 10, 2026
- 60.00May 10, 2026
- 87.50May 10, 2026
Show 19 more resultsHide 19 results
- 0.55Sep 9, 2026
- AA Intelligence8.08Oct 8, 2026aa_intelligence_index
- -52.15Oct 8, 2026
- 96.51May 10, 2026
- 0.50May 10, 2026
- Artificial Analysis Coding Index8.17Sep 9, 2026aa_coding_index
- 88.80Oct 7, 2026
- 94.40Oct 7, 2026
- 70.70May 1, 2026
- 69.40Jun 19, 2026
- 32.80Aug 23, 2026
- 67.80Oct 7, 2026
- 90.60Oct 7, 2026
- 74.30Oct 7, 2026
- 9.06May 1, 2026
- vectara_answer_rate99.00May 2, 2026Answer Rate
- vectara_avg_summary_length137.30May 2, 2026Average Summary Length (Words)
- vectara_factual_consistency92.30May 2, 2026Factual Consistency Rate
- τ²-Bench Telecom (AA run)15.50Oct 8, 2026aa_tau2
Llama 4 Scout: common questions
Who makes Llama 4 Scout?
Llama 4 Scout is made by Meta.
When was Llama 4 Scout released?
Llama 4 Scout was released on Apr 5, 2025, according to Artificial Analysis.
What is Llama 4 Scout good at?
Llama 4 Scout is behind the leaders in multimodal tasks. Too few results yet to rate reasoning, coding, agentic tasks, safety, long context, math, multilingual tasks, instruction following, or factuality.
How much does Llama 4 Scout cost?
Llama 4 Scout costs $0.19 per million input tokens and $0.68 per million output tokens, according to Artificial Analysis. We track its price at 5 providers. At a mix of three input tokens to one output token, it is cheaper than 71% of the 331 priced models we track.
How many benchmarks has Llama 4 Scout been tested on?
We track 46 results for Llama 4 Scout on 43 benchmarks from 14 sources, 15 of them independently verified. The latest was recorded on Oct 8, 2026.
Which API features does Llama 4 Scout support?
OpenRouter lists tool calling and structured outputs for Llama 4 Scout.
About this record
Where Llama 4 Scout's numbers come from, and every name it appears under.
- Tracked since
- May 1, 2026
- Newest source mention
- Aug 31, 2026
Where the results come from
Verification: 46 scores · 15 independently verified · 19 aggregator-attributed · 12 vendor-reported. How these tiers are assigned
From 14 sources on 6 sites. Artificial Analysis supplies 20 of them; the 15 independently verified results come from 5 sites. Bars are coloured by trust tier.
- artificialanalysis.ai20
- api.llm-stats.com9
- raw.githubusercontent.com7
- storage.googleapis.com6
- arcprize.org2
- swebench.com2