AI Benchmark Model

Llama 3.3 Instruct 70B

Benchmark scores, pricing, speed, and model comparisons for Llama 3.3 Instruct 70B.

Key scores

Intelligence14.5Index score
Coding10.7Index score
Math7.7Index score
Speed87.8Tokens/sec
Blended Cost$0.62Per 1M tokens

Review benchmark scores, pricing, performance data, and generated comparisons for this AI model.

Benchmark results

12 tracked benchmark rows for Llama 3.3 Instruct 70B.

MATH 500 Math
77.3%
MMLU Pro Knowledge
71.3%
GPQA Reasoning
49.8%
IFBench Other
47.1%
AIME Math
30.0%
LiveCodeBench Code
28.8%
TAU2 Other
26.6%
SciCode Other
26.0%
LCR Other
15.0%
AIME 2025 Math
7.7%
HLE Other
4.0%
TerminalBench Hard Other
3.0%

Comments (0)

No comments yet

Be the first to share your thoughts!