BENCHMARK REGISTRY
Public Artificial Intelligence Benchmark Records Database

Llama 3.1 Tulu3 405B

MODEL RECORD: AI2-LLAMA31TULU3405B

Organization
Allen Institute for AI
Family
LLAMA31TULU3405B
Model number
Unknown
Tier
Unknown
Status
ACTIVE
Release date
2025-01-30

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-018LLAMA31TULU3405B-001 Llama 3.1 Tulu3 405B Artificial Analysis Intelligence Index Overall 8.3 Unknown Primary source AI2-LLAMA31TULU3405B
BR-018LLAMA31TULU3405B-002 Llama 3.1 Tulu3 405B GPQA Diamond Accuracy 51.6% Unknown Primary source AI2-LLAMA31TULU3405B
BR-018LLAMA31TULU3405B-003 Llama 3.1 Tulu3 405B Humanity's Last Exam No tools Overall 3.5% Unknown Primary source AI2-LLAMA31TULU3405B
BR-018LLAMA31TULU3405B-004 Llama 3.1 Tulu3 405B SciCode Overall 30.2% Unknown Primary source AI2-LLAMA31TULU3405B