MDL
Llama 3.2 Instruct 3B
Meta
Verified against Artificial Analysis · Jul 13, 2026
Capability
25
percentile index
Price /M
$0.15 / $0.15
in / out
Context
—
Avg score
18.0
10 benchmarks
AA Intelligence
4.2
index
Speed
53 tok/s
TTFT 0.6s
Released
Sep 25, 2024
About
Llama 3.2 Instruct 3B is a open-weights model in the Llama family from Meta. Benchmarked on 10 evals, averaging 18.0.
Benchmark scores · 10
avg 18.0 — higher is betterThe research behind this model
all papers mentioning it →Information-Aware KV Cache Compression for Long Reasoning▲ 11 on HF · Jun 25, 2026Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning▲ 7 on HF · Jun 1, 2026BioRefusalAudit: Auditing Biosecurity Refusal Depth Using General and Domain-Fine-Tuned Sparse AutoencodersMay 28, 2026Analyzing Quality-Latency-Resource Trade-offs in a Technical Documentation RAG Assistant Using LoRA AdaptationMay 27, 2026NestedKV: Nested Memory Routing for Long-Context KV Cache CompressionMay 26, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Performance & price
Output speed53 tok/s
Latency (TTFT)0.6s
Price in / out$0.15 / $0.15 per 1M
Blended price$0.15 / 1M
Math index3.3
Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$0.15/M