tensor
.news
Integrity Index
Models
Compare
Labs
Papers
Methodology
About
← Labs
Meta AI
30 models tracked · known for opt-125m, Llama-3.2-1B-Instruct, Llama-3.1-8B-Instruct
30
Models tracked
30
In our data
93.73
Best score
3
Notable
Models
Llama 3.1-405B
independently reproduced
93.73
Muse Spark
independently reproduced
88.89
Llama 2-70B
independently reproduced
87.6
LLaMA-65B
self-reported
86
Llama 2-34B
self-reported
84.6
LLaMA-33B
self-reported
83.8
Llama 3.1-8B
independently reproduced
82.4
Llama 3.3 70B
independently reproduced
81.73
Llama 2-13B
self-reported
79.6
LLaMA-13B
self-reported
77.9
Llama 3-8B
independently reproduced
77.07
Llama 3.2 90B
independently reproduced
73.73
Llama 2-7B
self-reported
73.7
Llama 3.1-70B
independently reproduced
73.47
LLaMA-7B
self-reported
73.3
Llama 4 Maverick
independently reproduced
73.02
Llama 3-70B
independently reproduced
72.4
Llama 4 Scout
independently reproduced
62.27
opt-125m
unverified
—
Llama-3.2-1B-Instruct
unverified
—
Llama-3.1-8B-Instruct
unverified
—
Llama-3.2-3B-Instruct
unverified
—
Llama-3.2-1B
unverified
—
Llama-3.1-8B
unverified
—
Meta-Llama-3-8B-Instruct
unverified
—
Meta-Llama-3-8B
unverified
—
Llama-3.1-70B-Instruct
unverified
—
Llama-3.3-70B-Instruct
unverified
—
Llama-2-7b-hf
unverified
—
Llama-3.2-3B
unverified
—
185 source records · huggingface_models, epoch_benchmarks. Every score is evidence-linked.
Follow the record
Other labs
Qwen
OpenAI
DeepSeek
NVIDIA
Google DeepMind
EleutherAI
Zhipu AI
Hugging Face
Explore the record
Benchmark Integrity Index
Model Claim Ledger
Head-to-head comparisons