BENCHMARK REGISTRY
Public Artificial Intelligence Benchmark Records Database

Llama 3.3 Instruct 70B

MODEL RECORD: META-LLAMA33INSTRUCT70B

Organization
Meta
Family
LLAMA33INSTRUCT70B
Model number
Unknown
Tier
Unknown
Status
ACTIVE
Release date
2024-12-06

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-009LLAMA33INSTRUCT70B-001 Llama 3.3 Instruct 70B Artificial Analysis Intelligence Index Overall 9.4 Unknown Primary source META-LLAMA33INSTRUCT70B
BR-009LLAMA33INSTRUCT70B-002 Llama 3.3 Instruct 70B GPQA Diamond Accuracy 49.8% Unknown Primary source META-LLAMA33INSTRUCT70B
BR-009LLAMA33INSTRUCT70B-003 Llama 3.3 Instruct 70B Humanity's Last Exam No tools Overall 4% Unknown Primary source META-LLAMA33INSTRUCT70B
BR-009LLAMA33INSTRUCT70B-004 Llama 3.3 Instruct 70B SciCode Overall 26% Unknown Primary source META-LLAMA33INSTRUCT70B
BR-009LLAMA33INSTRUCT70B-005 Llama 3.3 Instruct 70B tau2-bench Overall 26.6% Unknown Primary source META-LLAMA33INSTRUCT70B
BR-009LLAMA33INSTRUCT70B-006 Llama 3.3 Instruct 70B tau3-Banking Overall 1% Unknown Primary source META-LLAMA33INSTRUCT70B
BR-009LLAMA33INSTRUCT70B-007 Llama 3.3 Instruct 70B Terminal-Bench Hard Overall 3% Unknown Primary source META-LLAMA33INSTRUCT70B
BR-009LLAMA33INSTRUCT70B-008 Llama 3.3 Instruct 70B Terminal-Bench 2.1 Overall 4.9% Unknown Primary source META-LLAMA33INSTRUCT70B
BR-009LLAMA33INSTRUCT70B-009 Llama 3.3 Instruct 70B CritPt Overall 0% Unknown Primary source META-LLAMA33INSTRUCT70B
BR-009LLAMA33INSTRUCT70B-010 Llama 3.3 Instruct 70B AA-Omniscience Overall -51.9 Unknown Primary source META-LLAMA33INSTRUCT70B
BR-009LLAMA33INSTRUCT70B-011 Llama 3.3 Instruct 70B AA-Omniscience Accuracy 17.9% Unknown Primary source META-LLAMA33INSTRUCT70B
BR-009LLAMA33INSTRUCT70B-012 Llama 3.3 Instruct 70B IFBench Overall 47.1% Unknown Primary source META-LLAMA33INSTRUCT70B
BR-009LLAMA33INSTRUCT70B-013 Llama 3.3 Instruct 70B ITBench SRE Overall 0.6% Unknown Primary source META-LLAMA33INSTRUCT70B
BR-009LLAMA33INSTRUCT70B-014 Llama 3.3 Instruct 70B GDPval-AA Average Normalized Score 0% Unknown Primary source META-LLAMA33INSTRUCT70B
BR-009LLAMA33INSTRUCT70B-015 Llama 3.3 Instruct 70B AA-LCR Overall 15% Unknown Primary source META-LLAMA33INSTRUCT70B