MMODELYST
Models/Llama 3.2 Instruct 11B (Vision)
MDL

Llama 3.2 Instruct 11B (Vision)

Meta

Verified against Artificial Analysis · Jul 13, 2026
Capability
29
percentile index
Price /M
$0.345 / $0.345
in / out
Context
Avg score
18.8
11 benchmarks
AA Intelligence
3.3
index
Speed
109 tok/s
TTFT 0.5s
Released
Sep 25, 2024
About

Llama 3.2 Instruct 11B (Vision) is a open-weights model in the Llama family from Meta. Benchmarked on 11 evals, averaging 18.8.

Benchmark scores · 11
avg 18.8 — higher is better
MATH
51.6
MMLU-Pro
46.4
IFBench
30.4
GPQA Diamond
22.1
τ²-bench
14.6
AA Long-Context Reasoning
11.7
SciCode
11.2
LiveCodeBench
11
Humanity's Last Exam
5.2
AIME
1.7
Terminal-Bench Hard
0.8
Details
PublisherMeta
FamilyLlama
Parameters
License
WeightsOpen
ReleasedSep 25, 2024
Performance & price
Output speed109 tok/s
Latency (TTFT)0.5s
Price in / out$0.345 / $0.345 per 1M
Blended price$0.345 / 1M
Math index1.7

Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers
Artificial Analysis$0.345/M