Back
FR

Nous Research

DeepHermes 3 - Mistral 24B Preview (Non-reasoning)

Intelligence
6.1
Rank 657 of 782 measured models
Context window
32K
Rank 1161 of 1325 measured models

DeepHermes 3 - Mistral 24B Preview (Non-reasoning) scores 6.1 on the Artificial Analysis Intelligence Index, ranking 657th of 782 measured models. The closest models on this index are Jamba 1.7 Large (6.1), Qwen3.5 0.8B (6.1), and DeepSeek-Coder-V2 (6.0).

Artificial Analysis Indices
Intelligence6.1
Rank 657 of 782 measured models
Standard Benchmarks
MMLU Pro58.0%
Rank 274 of 349 measured models
GPQA Diamond38.2%
Rank 537 of 621 measured models
HLE3.8%
Rank 611 of 682 measured models
LiveCodeBench19.5%
Rank 272 of 343 measured models
MATH-50059.5%
Rank 161 of 202 measured models
AIME 20244.7%
Rank 155 of 194 measured models
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy