Llama 4 Maverick (FP8): benchmark scores, price and ranking

Llama 4 Maverick (FP8) from Meta AI ranks #570 of 743 LLMs on the LLMs Tiger aggregate benchmark score (45.6), based on 3 benchmark results captured up to 2026-10-13.

Organisation: Meta AI
Type: Open-weight / local model
Open weights: Yes
Released: 2025-04-05 (source: curated)
Cheapest API price: $0.188 in / $0.652 out per million tokens (via openrouter, observed 2026-10-13T20:47Z)
Aggregate rank: #570 of 743 (score 45.6)

Relative to other models, Llama 4 Maverick (FP8) is strongest on GPQA Diamond (#149 of 275) and weakest on ALE-Bench (#78 of 79).

Across the 3 benchmarks where at least ten models are scored, Llama 4 Maverick (FP8) is in the top 10% on 0 and in the top half on 0.

Its cheapest listed input price, $0.188 per million tokens, is lower than that of 70% of the 427 models with a listed price.

Llama 4 Maverick (FP8) benchmark results

Llama 4 Maverick (FP8) benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
GPQA Diamond	67.0%	#149 of 275	Epoch AI Benchmarking Hub	2026-10-13
OTIS Mock AIME	20.6%	#130 of 189	Epoch AI Benchmarking Hub	2026-10-13
ALE-Bench	173	#78 of 79	Epoch AI Benchmarking Hub	2026-10-13

About Llama 4 Maverick (FP8)

Llama 4 Maverick (FP8) is an open-weight model that can run on your own hardware from Meta AI. It was released on 2025-04-05, according to the developer's announcement. The cheapest API listing we track charges $0.188 per million input tokens and $0.652 per million output tokens, through openrouter. We hold 3 benchmark results for it across 2 areas, and none is in the top tenth of its board.

Where Llama 4 Maverick (FP8) stands

On our aggregate score, Llama 4 Maverick (FP8) is #570 of 743 ranked models, in the lower half. Its score is 45.6; the scale is centred on 50, so it sits 4.4 points below the typical model. That beats 23% of the ranked field. Among the 28 ranked Meta AI models it is #14. The next one up is Llama-3.2-90B-Vision-Instruct at 45.9. The next one down is Llama 3.1-8B at 45.3.

Llama 4 Maverick (FP8), benchmark by benchmark

Llama 4 Maverick (FP8) lands below the middle on GPQA Diamond: 67.0%, #149 of 275, with 54% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is DeepSeek-V3 (Mar 2025) at 67.6%. It covers expert-level science questions. The board median is 71.7%, so Llama 4 Maverick (FP8) is 4.7 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Llama 4 Maverick (FP8) lands below the middle on OTIS Mock AIME: 20.6%, #130 of 189, with 68% of the field scoring higher. Claude Fable 5.1 (max) leads at 100.0%; the closest result above is DeepSeek-R1-Distill-Qwen-1.5B at 21.4%. It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so Llama 4 Maverick (FP8) is 37.2 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

ALE-Bench is a weak spot. Llama 4 Maverick (FP8) scores 173, #78 of 79, behind 97% of the models measured. The leader, GPT-6 Astra (max), reaches 2,951. It covers AtCoder heuristic-optimisation contests (performance rating). The board median is 764, so Llama 4 Maverick (FP8) is 591 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Strengths and weaknesses

Reasoning, maths and science: uneven, ahead of 39% of the field on average across 2 benchmarks. Its best board here is GPQA Diamond (#149 of 275) and its weakest is OTIS Mock AIME (#130 of 189).

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so Llama 4 Maverick (FP8) 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 GPT-5.4 nano (xhigh) ($0.200) and Step 3.7 Flash ($0.200).

Release history

The Meta AI model released before it was Llama 4 Maverick on 2025-04-05, which scores 42.0. The next one was Llama 4 Scout on 2025-04-05, at 47.4.

Reading these numbers

The 3 scores on this page come from 1 source: Epoch AI Benchmarking Hub (3). No official leaderboard supplied any of them, so treat them as third-party measurements. With 3 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#567 open-mistral-nemo-2407 (45.6)
#568 MiniMax-M2.7 (45.6)
#569 ollama/mistral-nemo:12b-instruct-2407-q4_K_M (45.6)
#571 mistral-large-2411 (45.6)
#572 gemini-2.5-flash (45.6)
#573 qwen3-14b (45.6)