Back

IBM

Granite 3.3 8B (Non-reasoning)

Open weightsHugging Face
Intelligence
4.9
Rank 721 of 744 measured models
Output speed
44.4 t/s
Rank 339 of 403 measured models
Price/1M
$0.085
Rank 75 of 659 measured models
Context window
128K
Rank 773 of 1199 measured models

Granite 3.3 8B (Non-reasoning) scores 4.9 on the Artificial Analysis Intelligence Index, ranking 721st of 744 measured models. The closest models on this index are Gemma 3 27B Instruct (4.9), LFM2 8B A1B (4.9), and Qwen3 1.7B (4.9).

Artificial Analysis Indices
Intelligence4.9
Rank 721 of 744 measured models
Math6.7
Rank 242 of 270 measured models
Standard Benchmarks
MMLU Pro46.8%
Rank 307 of 349 measured models
GPQA Diamond33.8%
Rank 554 of 619 measured models
HLE4.2%
Rank 553 of 664 measured models
LiveCodeBench12.7%
Rank 300 of 343 measured models
MATH-50066.5%
Rank 153 of 202 measured models
AIME 20244.7%
Rank 155 of 194 measured models
AIME 20256.7%
Rank 242 of 270 measured models
IFBench22.4%
Rank 429 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