Llama-4-Maverick-17B-128E-Instruct: benchmark scores, price and ranking

Llama-4-Maverick-17B-128E-Instruct from Meta AI ranks #481 of 743 LLMs on the LLMs Tiger aggregate benchmark score (46.9), based on 2 benchmark results captured up to 2026-10-13.

Organisation: Meta AI
Type: Open-weight / local model
Open weights: Yes
Released: 2025-04-06 (source: epoch)
Cheapest API price: $0.630 in / $1.80 out per million tokens (via sambanova, observed 2026-10-13T20:47Z)
Aggregate rank: #481 of 743 (score 46.9)

Across the 2 benchmarks where at least ten models are scored, Llama-4-Maverick-17B-128E-Instruct is in the top 10% on 0 and in the top half on 0.

Its cheapest listed input price, $0.630 per million tokens, is lower than that of 44% of the 427 models with a listed price.

Llama-4-Maverick-17B-128E-Instruct benchmark results

Llama-4-Maverick-17B-128E-Instruct benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
Fiction.liveBench	46.2%	#38 of 47	Epoch AI Benchmarking Hub	2026-10-13
CritPt	0.0%	#102 of 115	Epoch AI Benchmarking Hub	2026-10-13

About Llama-4-Maverick-17B-128E-Instruct

Llama-4-Maverick-17B-128E-Instruct is an open-weight model that can run on your own hardware from Meta AI. It was released on 2025-04-06, according to Epoch AI. The cheapest API listing we track charges $0.630 per million input tokens and $1.80 per million output tokens, through sambanova. We hold 2 benchmark results for it across 2 areas, and none is in the top tenth of its board.

Where Llama-4-Maverick-17B-128E-Instruct stands

On our aggregate score, Llama-4-Maverick-17B-128E-Instruct is #481 of 743 ranked models, in the lower half. Its score is 46.9; the scale is centred on 50, so it sits 3.1 points below the typical model. That beats 35% of the ranked field. Among the 28 ranked Meta AI models it is #12. The next one up is Llama-3.2-3B-Instruct at 47.2. The next one down is Llama-3.2-90B-Vision-Instruct at 45.9.

Llama-4-Maverick-17B-128E-Instruct, benchmark by benchmark

Fiction.liveBench is a weak spot. Llama-4-Maverick-17B-128E-Instruct scores 46.2%, #38 of 47, behind 79% 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-Maverick-17B-128E-Instruct is 14.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

CritPt is a weak spot. Llama-4-Maverick-17B-128E-Instruct scores 0.0%, #102 of 115, behind 88% 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-Maverick-17B-128E-Instruct is 2.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Strengths and weaknesses

Llama-4-Maverick-17B-128E-Instruct has too few results on boards with ten or more models to say where it is strong or weak. Treat any single score as a data point, not a verdict.

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so Llama-4-Maverick-17B-128E-Instruct costs more 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 kimi-k2.6-thinking ($0.650) and qwen3-coder-plus ($0.650).

Release history

The Meta AI model released before it was Llama-4-Scout-17B-16E-Instruct on 2025-04-05, which scores 40.1. The next one was Muse Spark on 2026-04-08, at 53.7.

Reading these numbers

The 2 scores on this page come from 1 source: Epoch AI Benchmarking Hub (2). No official leaderboard supplied any of them, so treat them as third-party measurements. With 2 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#478 GPT-5 mini (high) (46.9)
#479 GPT-4 (1106) (46.9)
#480 glm-4-9b (46.9)
#482 qwen3-30b-a3b-instruct-2507 (46.8)
#483 Command A+ (46.8)
#484 MiniMax-M2.5 (46.8)