The Open-Source AI Stack
RSS
All models

Models · Compare

Llama 3.2 11B Vision Instruct vs Claude 3.5 Haiku

Rows highlighted in warm gray are where the models differ. Numbers carry their as-of date and primary source.

Specs

Field A: Llama 3.2 11B Vision Instruct B: Claude 3.5 Haiku
Released 2024-09-252024-11-04
Developer MetaAnthropic
Openness Source-availableProprietary
License Llama 3.2 Community LicenseProprietary
OSI-approved nono
Data released nono
Training code nono
Architecture denseunknown
Total params
Active params
Experts
Context window 131K200K
Attention gqaunknown
Position enc. rope-llama3unknown
Pretraining tokens
Post-training sft, rlhfrlhf, constitutional
Training hardware H100
$/M input $0.80
$/M output $4.00
Output tok/sec 0

Benchmarks

Missing scores render as not reported; never inferred. Bold highlights the leader per benchmark.

General reasoning

MMLU-Pro 63.4 2026-05-21
GPQA-Diamond 40.8 2026-05-21

Code

SWE-Bench Verified 40.6 2024-10-22
LiveCodeBench 31.4 2026-05-21

Math

MATH 72.1 2026-05-21
AIME 2024 3.3 2026-05-21

Context · A

Llama's first openly released vision-language checkpoint at small-medium scale, built by training a cross-attention adapter that integrates a pre-trained image encoder into the Llama 3.1 8B text backbone. The text-only behavior of the underlying language model is preserved so the model can substitute for the dense text checkpoint.

Context · B

Announced October 22 2024 alongside the upgraded Claude 3.5 Sonnet and the computer-use beta; generally available in early November. Anthropic positioned it as matching Claude 3 Opus on many intelligence benchmarks at Haiku-tier speeds, with a SWE-Bench Verified score of 40.6% making it briefly the best small-tier coding model from a major lab.

Llama 3.2 11B Vision Instruct detail → · Claude 3.5 Haiku detail →