Llama-3.2-1B-Instruct: benchmark scores, price and ranking

Llama-3.2-1B-Instruct from Meta AI ranks #729 of 743 LLMs on the LLMs Tiger aggregate benchmark score (41.1), based on 4 benchmark results captured up to 2026-10-13.

Organisation: Meta AI
Type: Open-weight / local model
Open weights: Yes
Released: 2024-09-24 (source: epoch)
Cheapest API price: $0.020 in / $0.020 out per million tokens (via novita, observed 2026-10-13T20:47Z)
Aggregate rank: #729 of 743 (score 41.1)

Relative to other models, Llama-3.2-1B-Instruct is strongest on Chess Puzzles (#115 of 122) and weakest on OTIS Mock AIME (#186 of 189).

Across the 4 benchmarks where at least ten models are scored, Llama-3.2-1B-Instruct is in the top 10% on 0 and in the top half on 0.

Its cheapest listed input price, $0.020 per million tokens, is lower than that of 97% of the 427 models with a listed price.

Llama-3.2-1B-Instruct benchmark results

Llama-3.2-1B-Instruct benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
Chess Puzzles	0.0%	#115 of 122	Epoch AI Benchmarking Hub	2026-10-13
BALROG	6.6%	#33 of 34	Epoch AI Benchmarking Hub	2026-10-13
GPQA Diamond	18.7%	#270 of 275	HuggingFace GPQA Diamond leaderboard	2026-10-13
OTIS Mock AIME	0.6%	#186 of 189	Epoch AI Benchmarking Hub	2026-10-13

About Llama-3.2-1B-Instruct

Llama-3.2-1B-Instruct is an open-weight model that can run on your own hardware from Meta AI. It was released on 2024-09-24, according to Epoch AI. The cheapest API listing we track charges $0.020 per million input tokens and $0.020 per million output tokens, through novita. We hold 4 benchmark results for it across 3 areas, and none is in the top tenth of its board.

Where Llama-3.2-1B-Instruct stands

On our aggregate score, Llama-3.2-1B-Instruct is #729 of 743 ranked models, in the lower half. Its score is 41.1; the scale is centred on 50, so it sits 8.9 points below the typical model. That beats 2% of the ranked field. Among the 28 ranked Meta AI models it is #24. The next one up is Llama 4 Maverick at 42.0. The next one down is Llama-3.3-70B-Instruct at 40.7.

Llama-3.2-1B-Instruct, benchmark by benchmark

Chess Puzzles is a weak spot. Llama-3.2-1B-Instruct scores 0.0%, #115 of 122, behind 93% of the models measured. The leader, GPT-6 Astra (max), reaches 72.0%. It covers chess tactics puzzles. The board median is 12.5%, so Llama-3.2-1B-Instruct is 12.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

BALROG is a weak spot. Llama-3.2-1B-Instruct scores 6.6%, #33 of 34, behind 94% of the models measured. The leader, GPT-6 Astra (max), reaches 68.3%. It covers long-horizon game-playing agents. The board median is 27.6%, so Llama-3.2-1B-Instruct is 21.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

GPQA Diamond is a weak spot. Llama-3.2-1B-Instruct scores 18.7%, #270 of 275, behind 98% of the models measured. The leader, GPT-6 Astra (max), reaches 95.8%. It covers expert-level science questions. The board median is 71.7%, so Llama-3.2-1B-Instruct is 53.0 points below it. Source: HuggingFace GPQA Diamond leaderboard, captured 2026-10-13.

OTIS Mock AIME is a weak spot. Llama-3.2-1B-Instruct scores 0.6%, #186 of 189, behind 98% of the models measured. The leader, Claude Fable 5.1 (max), reaches 100.0%. It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so Llama-3.2-1B-Instruct is 57.2 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Strengths and weaknesses

Reasoning, maths and science: weak, ahead of 2% of the field on average across 2 benchmarks. Its best board here is GPQA Diamond (#270 of 275) and its weakest is OTIS Mock AIME (#186 of 189).

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so Llama-3.2-1B-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 qwen2.5-7b-instruct ($0.040) and Llama-4-Scout-17B-16E-Instruct ($0.050).

Release history

The Meta AI model released before it was Llama 3.2 1B on 2024-09-24, which scores 42.0. The next one was Llama-3.2-3B-Instruct on 2024-09-24, at 47.2.

Reading these numbers

The 4 scores on this page come from 2 sources: Epoch AI Benchmarking Hub (3), HuggingFace GPQA Diamond leaderboard (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 4 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#726 c4ai-command-r-08-2024 (41.3)
#727 GPT-4 (Jun 2023) (41.2)
#728 c4ai-command-r-plus-08-2024 (41.2)
#730 open-mistral-7b (41.0)
#731 Llama-3.3-70B-Instruct (40.7)
#732 claude-2.1 (40.6)