Back

OpenAI

GPT-4o mini

Closed weightsModels.dev
Intelligence
6.7
Rank 587 of 744 measured models
Coding
11.4
Rank 263 of 298 measured models
Output speed
113 t/s
Rank 149 of 403 measured models
Price/1M
$0.262
Rank 192 of 659 measured models
Context window
128K
Rank 773 of 1199 measured models

GPT-4o mini scores 6.7 on the Artificial Analysis Intelligence Index, ranking 587th of 744 measured models. The closest models on this index are GLM-4.5V (6.7), GPT-4 (6.7), and Hermes 4 - Llama-3.1 70B (6.7). At $0.262 per million tokens (3:1 input/output blended price), it is cheaper than GLM-4.5V ($0.90) and GPT-4 ($37.50). With an output speed of 113 t/s, it is faster than GLM-4.5V (46.3 t/s).

Artificial Analysis Indices
Intelligence6.7
Rank 587 of 744 measured models
Coding11.4
Rank 263 of 298 measured models
Math14.7
Rank 220 of 270 measured models
Standard Benchmarks
MMLU Pro64.8%
Rank 256 of 349 measured models
GPQA Diamond42.6%
Rank 512 of 619 measured models
HLE4.2%
Rank 553 of 664 measured models
LiveCodeBench23.4%
Rank 258 of 343 measured models
MATH-50078.9%
Rank 112 of 202 measured models
AIME 202411.7%
Rank 122 of 194 measured models
AIME 202514.7%
Rank 220 of 270 measured models
IFBench31.0%
Rank 382 of 450 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