Skip to main content
AITier

Granite 3.3 8B (Non-reasoning)

IBMOpen WeightApache 2.0 · Commercial OK

Description

Granite-3.3-8B-Base is a decoder-only language model with a 128K token context window. It improves upon Granite-3.1-8B-Base by adding support for Fill-in-the-Middle (FIM) using specialized tokens, enabling the model to generate content conditioned on both prefix and suffix. This makes it well-suited for code completion tasks

Release Date
2025-04-16
Parameters
8.2B
Context Length
—
Modalities
text

Capability Radar

19
general
7
coding
18
reasoning
20
scienceest.
0
agents
0
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Code Ranking449
6.0
AA
General Ranking455
17.0
AA
Math Reasoning314
18.0
AA
Reasoning24
83.0
LS
Science439
17.0
AA

Benchmark Scores (LLM Stats)

Code

HumanEval89.7%SR

Creativity

AlpacaEval 2.062.7%SR
Arena Hard57.6%SR

Finance

MMLU63.9%SR
TruthfulQA52.1%SR

General

TriviaQA78.2%SR
IFEval74.8%SR
ARC-C50.8%SR
AGIEval49.3%SR
NQ36.5%SR
PopQA26.2%SR

Language

Winogrande74.4%SR
BIG-Bench Hard69.1%SR

Math

AIME 202481.2%SR
MATH-50069.0%SR
GSM8k59.0%SR
DROP36.1%SR

Reasoning

HumanEval+86.1%SR
HellaSwag80.1%SR

Safety

AttaQ88.5%SR

AA Evaluation Indices

Intelligence Index
7.0
Math Index
6.7
Coding Index
3.4
Math 500
0.7
Mmlu Pro
0.5
Gpqa
0.3
Ifbench
0.2
Livecodebench
0.1
Tau2
0.1
Scicode
0.1
Aime 25
0.1
Aime
0.0
Lcr
0.0
Hle
0.0
Terminalbench Hard
0.0

LLM Stats Category Scores

Code
90
Safety
90
Structured Output
70
Instruction Following
70
Language
70
Writing
60
Creativity
60
Finance
60
General
60
Healthcare
60
Legal
60
Math
60
Reasoning
60

Pricing

Input Price$0.03 / 1M tokens
Output Price$0.25 / 1M tokens
Blended Price (3:1)$0.085 / 1M tokens

Speed

Tokens/sec308.3 tokens/s
Time to First Token21.55s
Time to Answer21.55s

Available Providers

(LS internal units)

No provider data available

External Sources

LLM Stats