Llama-4-Scout-17B-16E-Instruct: benchmark scores, price and ranking
Llama-4-Scout-17B-16E-Instruct from Meta AI ranks #733 of 743 LLMs on the LLMs Tiger aggregate benchmark score (40.1), based on 7 benchmark results captured up to 2026-10-13.
- Organisation
- Meta AI
- Type
- Open-weight / local model
- Open weights
- Yes
- Released
- 2025-04-05 (source: epoch)
- Cheapest API price
- $0.050 in / $0.100 out per million tokens (via lambda_ai, observed 2026-10-13T20:47Z)
- Aggregate rank
- #733 of 743 (score 40.1)
Relative to other models, Llama-4-Scout-17B-16E-Instruct is strongest on GPQA Diamond (#182 of 275) and weakest on SciCode (#104 of 106).
Across the 7 benchmarks where at least ten models are scored, Llama-4-Scout-17B-16E-Instruct is in the top 10% on 0 and in the top half on 0.
Its cheapest listed input price, $0.050 per million tokens, is lower than that of 90% of the 427 models with a listed price.
Llama-4-Scout-17B-16E-Instruct benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| GPQA Diamond | 51.8% | #182 of 275 | Epoch AI Benchmarking Hub | 2026-10-13 |
| DTBench | 57.9% | #109 of 146 | Epoch AI Benchmarking Hub | 2026-10-13 |
| OTIS Mock AIME | 7.8% | #142 of 189 | Epoch AI Benchmarking Hub | 2026-10-13 |
| LMCA | 12.0% | #92 of 108 | Epoch AI Benchmarking Hub | 2026-10-13 |
| CritPt | 0.0% | #103 of 115 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Fiction.liveBench | 36.0% | #43 of 47 | Epoch AI Benchmarking Hub | 2026-10-13 |
| SciCode | 17.0% | #104 of 106 | Epoch AI Benchmarking Hub | 2026-10-13 |
About Llama-4-Scout-17B-16E-Instruct
Llama-4-Scout-17B-16E-Instruct is an open-weight model that can run on your own hardware from Meta AI. It was released on 2025-04-05, according to Epoch AI. The cheapest API listing we track charges $0.050 per million input tokens and $0.100 per million output tokens, through lambda_ai. We hold 7 benchmark results for it across 4 areas, and none is in the top tenth of its board.
Where Llama-4-Scout-17B-16E-Instruct stands
On our aggregate score, Llama-4-Scout-17B-16E-Instruct is #733 of 743 ranked models, in the lower half. Its score is 40.1; the scale is centred on 50, so it sits 9.9 points below the typical model. That beats 1% of the ranked field. Among the 28 ranked Meta AI models it is #26. The next one up is Llama-3.3-70B-Instruct at 40.7. The next one down is Meta-Llama-3-8B-Instruct at 39.4.
Llama-4-Scout-17B-16E-Instruct, benchmark by benchmark
Llama-4-Scout-17B-16E-Instruct lands below the middle on GPQA Diamond: 51.8%, #182 of 275, with 66% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is qwen3-4b at 52.3%. It covers expert-level science questions. The board median is 71.7%, so Llama-4-Scout-17B-16E-Instruct is 19.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Llama-4-Scout-17B-16E-Instruct lands below the middle on DTBench: 57.9%, #109 of 146, with 74% of the field scoring higher. Claude Opus 5.5 (max) leads at 98.9%; the closest result above is mistral-small-2503 at 58.6%. It covers dynamic tool-use benchmark. The board median is 68.8%, so Llama-4-Scout-17B-16E-Instruct is 10.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Llama-4-Scout-17B-16E-Instruct lands below the middle on OTIS Mock AIME: 7.8%, #142 of 189, with 75% of the field scoring higher. Claude Fable 5.1 (max) leads at 100.0%; the closest result above is qwen2.5-72b-instruct at 8.1%. It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so Llama-4-Scout-17B-16E-Instruct is 50.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
LMCA is a weak spot. Llama-4-Scout-17B-16E-Instruct scores 12.0%, #92 of 108, behind 84% of the models measured. The leader, Claude Opus 5.5 (max), reaches 68.2%. It covers language-model capability assessment. The board median is 29.2%, so Llama-4-Scout-17B-16E-Instruct is 17.3 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
CritPt is a weak spot. Llama-4-Scout-17B-16E-Instruct scores 0.0%, #103 of 115, behind 89% of the models measured. The leader, GPT-5.6 Sol (max), reaches 32.3%. It covers unpublished research-level physics problems. The board median is 2.9%, so Llama-4-Scout-17B-16E-Instruct is 2.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Fiction.liveBench is a weak spot. Llama-4-Scout-17B-16E-Instruct scores 36.0%, #43 of 47, behind 89% of the models measured. The leader, grok-4-0709, reaches 94.4%. It covers long-context story comprehension (16k). The board median is 61.1%, so Llama-4-Scout-17B-16E-Instruct is 25.1 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
SciCode is a weak spot. Llama-4-Scout-17B-16E-Instruct scores 17.0%, #104 of 106, behind 97% of the models measured. The leader, Claude Opus 5.5 (max), reaches 66.9%. It covers scientific research code. The board median is 44.3%, so Llama-4-Scout-17B-16E-Instruct is 27.3 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
Reasoning, maths and science: weak, ahead of 23% of the field on average across 3 benchmarks. Its best board here is GPQA Diamond (#182 of 275) and its weakest is CritPt (#103 of 115). General knowledge and chat: weak, ahead of 12% of the field on average across 2 benchmarks. Its best board here is LMCA (#92 of 108) and its weakest is Fiction.liveBench (#43 of 47).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so Llama-4-Scout-17B-16E-Instruct costs less than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on gemma-3-27b-it ($0.080) and GPT-4.1 nano ($0.100).
Release history
The Meta AI model released before it was Llama 4 Scout on 2025-04-05, which scores 47.4. The next one was Llama-4-Maverick-17B-128E-Instruct on 2025-04-06, at 46.9.
Reading these numbers
The 7 scores on this page come from 1 source: Epoch AI Benchmarking Hub (7). No official leaderboard supplied any of them, so treat them as third-party measurements. With 7 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #730 open-mistral-7b (41.0)
- #731 Llama-3.3-70B-Instruct (40.7)
- #732 claude-2.1 (40.6)
- #734 gemma-3-4b-it (39.9)
- #735 qwen2.5-7b-instruct (39.9)
- #736 claude-3-haiku-20240307 (39.9)
More from Meta AI
- Muse Spark 1.3 (max) (#18, 55.1)
- Muse Spark (#29, 53.7)
- Muse Spark 1.1 (xhigh) (#66, 52.4)
- Muse Spark 1.2 (xhigh) (#113, 51.5)
- Llama 3.1-405B (#142, 51.2)
- Muse Wonder (max) (#209, 50.1)
Compare it on the live leaderboard → · How the aggregate score works