Llama-3.2-3B-Instruct: benchmark scores, price and ranking

Llama-3.2-3B-Instruct from Meta AI ranks #450 of 743 LLMs on the LLMs Tiger aggregate benchmark score (47.2), based on 1 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 deepinfra, observed 2026-10-13T20:47Z)
Aggregate rank: #450 of 743 (score 47.2)

Across the 1 benchmark where at least ten models are scored, Llama-3.2-3B-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-3.2-3B-Instruct benchmark results

Llama-3.2-3B-Instruct benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
BALROG	10.1%	#31 of 34	Epoch AI Benchmarking Hub	2026-10-13

About Llama-3.2-3B-Instruct

Llama-3.2-3B-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 deepinfra. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.

Where Llama-3.2-3B-Instruct stands

On our aggregate score, Llama-3.2-3B-Instruct is #450 of 743 ranked models, in the lower half. Its score is 47.2; the scale is centred on 50, so it sits 2.8 points below the typical model. That beats 39% of the ranked field. Among the 28 ranked Meta AI models it is #11. The next one up is Llama 4 Scout at 47.4. The next one down is Llama-4-Maverick-17B-128E-Instruct at 46.9.

Llama-3.2-3B-Instruct, benchmark by benchmark

BALROG is a weak spot. Llama-3.2-3B-Instruct scores 10.1%, #31 of 34, behind 88% 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-3.2-3B-Instruct is 17.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so Llama-3.2-3B-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 gpt-oss-120b (high) ($0.030) and Qwen3.8-27B (XHigh) ($0.040).

Release history

The Meta AI model released before it was Llama-3.2-1B-Instruct on 2024-09-24, which scores 41.1. The next one was Llama-3.2-90B-Vision-Instruct on 2024-09-24, at 45.9.

Reading these numbers

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

Models ranked nearby

#447 gpt-oss-120b (high) (47.3)
#448 Kimi K2 0905 (Novita) (47.3)
#449 gpt-5.6-terra-xhigh (codex-harness) (47.3)
#451 ollama/yi-coder:9b-chat-fp16 (47.2)
#452 Codestral 25.01 (47.2)
#453 gpt-5.6-luna-xhigh (codex-harness) (47.2)