跳转到主要内容

Granite 4.2 30B

IBM开源权重Apache 2.0 · 商用许可

描述

IBM Granite 4.2 30B is the flagship dense decoder-only reasoning LLM in the Granite 4.2 family. It supports native think, non-think, and low-effort modes, tool calling, and a 128K native context window with extension to 512K. The 8B and 30B sizes received additional agentic reinforcement learning for multi-step tool use. Open weights on Hugging Face under Apache 2.0. Text-only (not multimodal).

发布日期
2026-08-25
参数规模
30.0B
上下文长度
—
支持模态
text

能力雷达图

12
general
31
coding
64
reasoning
44
science
50
agents
0
multimodal

排行榜排名

领域#排名分数来源
智能体能力模型榜59
48.0
LS
代码能力榜262
43.0
AA
通用能力榜493
18.0
AA
科学能力247
44.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Agents

TAU3-Bench62.0%自报

General

Arena-Hard v267.9%自报

Instruction Following

IFBench77.2%自报

Language

MMLU-Pro77.6%自报

Long Context

RULER 64k90.0%自报
RULER 128k81.4%自报

Math

HMMT2589.2%自报
AIME 202589.2%自报

Reasoning

LiveCodeBench v675.8%自报
GPQANYU + Cohere + Anthropic (2023)66.4%自报
SWE-Bench Verified57.0%自报
ProfBench42.9%自报
SWE-bench Multilingual41.9%自报
Bird-SQL (dev)41.9%自报
SciCode38.8%自报
SWE-Bench ProPrinceton NLP (2024)33.3%自报
Terminal-Bench 2.129.2%自报

Tool Calling

BFCL-V461.4%自报

AA 评测指数

(Artificial Analysis)
Gpqa(NYU + Cohere + Anthropic (2023))
64.4
Lcr(Artificial Analysis)
49.0
Scicode(UIUC + Argonne National Lab (2024))
37.8
Coding Index(Artificial Analysis)
29.9
Terminalbench V2 1
26.6
Tau Banking
14.4
Intelligence Index(Artificial Analysis)
12.7
Hle(Center for AI Safety + Scale AI (2025))
11.2
Terminalbench V4 0
0.0

LLM Stats 分类评分

(LLM Stats (zeroeval))
Long Context
90
Instruction Following
80
Language
80
Legal
80
Finance
80
Healthcare
80
Math
70
Creativity
70
Writing
70
Reasoning
60
Frontend Development
60
General
60
Physics
50
Agents
50
Biology
50
Chemistry
50
Tool Calling
50
Knowledge
40
Code
40

定价

输入价格$0.16 / 1M tokens
输出价格$0.65 / 1M tokens
混合价格(3:1)$0.282 / 1M tokens

速度

Tokens/秒38.9
首Token延迟0.38s
首回答延迟51.85s

供应商价格排行

供应商价格排行

2 个供应商

最便宜: DeepInfra最贵: IBM
供应商输入输出
1DeepInfra最便宜
$0
$0
2IBM主要
$0.16
$0.65

比较该模型在不同 API 供应商之间的定价。

外部链接