Ctrl K
Back to models

Meta

Llama 3.2 Instruct 11B (Vision)

  • Released
  • Gated weights
  • Llama 3.2 Community License Agreement
Compare
Intelligence Index

Standard setting

5.4
Estimated · Artificial Analysis v4.3.2
Context window
128K tok

Performance profile

ReasoningRank #107 of 107
22.1%
GPQA Diamond

Capabilities

Context window

Modalities

Measured setting

Reasoning trade-offs

Source (opens in a new tab)
Intelligence Index v4.3.2
VisionEstimated
Intelligence Index
5.4

Pricing & access

No API offering listed in our tracked sources.

Run locally

Original download
21.3 GB
App memory
Unverified
Documented software
TransformersSetup guide (opens in a new tab)
Find GGUF downloads (opens in a new tab)Original weights (opens in a new tab)Access approval required

Benchmarks

Full leaderboardSource (opens in a new tab)

Humanity’s Last Exam

Frontier reasoning

Llama 3.2 Instruct 11B (Vision) · Standard#104 of 126

  1. 1Claude Opus 5.5Max61.4%
  2. 2Claude Fable 5.1Max59.1%
  3. 3Gemini 4 ArgonHigh57.1%
  5. 101Celeris-1Standard6.8%
  6. 102Granite 4.2 3BReasoning6.6%
  7. 103LFM2.5-2.6BReasoning6.2%
  8. 104Llama 3.2 Instruct 11B (Vision)Standard5.5%
  9. 105NVIDIA Nemotron Nano 12B v2 VLReasoning5.5%
  10. 106Ministral 3 3BStandard5.4%
  11. 106K2 Horizon 0.9BReasoning5.4%

Peers use their best measured result on this benchmark.