AI Benchmark Model

Hermes 4 - Llama-3.1 70B (Reasoning)

Benchmark scores, pricing, speed, and model comparisons for Hermes 4 - Llama-3.1 70B (Reasoning).

Key scores

Intelligence16.0Index score
Coding14.4Index score
Math68.7Index score
Speed70.7Tokens/sec
Blended Cost$0.20Per 1M tokens

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

Benchmark results

10 tracked benchmark rows for Hermes 4 - Llama-3.1 70B (Reasoning).

MMLU Pro Knowledge
81.1%
GPQA Reasoning
69.9%
AIME 2025 Math
68.7%
LiveCodeBench Code
65.3%
SciCode Other
34.1%
IFBench Other
31.3%
TAU2 Other
22.5%
HLE Other
7.9%
LCR Other
6.7%
TerminalBench Hard Other
4.5%

Comments (0)

No comments yet

Be the first to share your thoughts!