IBM

Granite 4.2 30B Instruct开源

IBM Granite 4.2 30B enterprise open foundation model optimized for coding and tool calling.

#289发布于 2026年7月20日·Open Weights·30 billion

textimage128K ctx

API providers 排行榜

Intelligence

58.6 #289

AAQI 51.0

Output speed

78 t/s

TTFT 280 ms · ITL 12.8 ms/tok

Blended price (3:1)

$0.6 /1M

In $0.4/M · Out $1.2/M

Context

128K

≈ 320 A4 pages · max out 8192

Quality Domain Radar

6-Axis Frontier Evaluation vs Category Average & Flagship

Granite 4.2 30B Instruct

Claude Mythos Preview (#1)

Average (68)

Radar axes are approximated from category scores where direct benchmark measurements are missing — see 评分方法.

API deployment

Compare hosts & latency

Throughput, TTFT and cache pricing across Groq, Cerebras, Together, DeepInfra, Fireworks, Bedrock and Azure.

GroqCerebrasTogether AIDeepInfraFireworks AIAWS BedrockAzure AI

View providers matrix →

各榜单得分

Arena.ai ↗

1380.0

#82 · 8.5k votes · ±8

Artificial Analysis ↗

分类能力得分

Value78.0 Long Context70.0 Agentic58.0 Coding56.0 Speed55.0 Reasoning54.5 Knowledge52.0 intelligence51.0

基准测试分项

GPQA Diamond68%LiveCodeBench58%SWE-Bench Pro46.5%

模型详细参数

发布日期

2026年7月20日

参数量

30 billion

开源协议

Open Weights

上下文窗口

128,000 tokens

输入价格

$0.4/M

输出价格

$1.2/M

输出速度

78 t/s

首Token延迟

280 ms

Estimated monthly bill

Monthly API requests: 100,000Avg input tokens: 1,500Avg output tokens: 500Prompt cache hit rate: 50%

Estimated monthly spend

$0.00

Calculating savings vs GPT-4o...

Cite & embed

GitHub Markdown badge

[![LLMPodium Rank](https://llmpodium.com/badge/granite-4-2-30b/rank.svg)](https://llmpodium.com/models/granite-4-2-30b)

BibTeX

@misc{llmpodium2026granite4230b,
  title = {Benchmark Analysis and Intelligence Evaluation of Granite 4.2 30B Instruct},
  author = {LLMPodium Research},
  year = {2026},
  url = {https://llmpodium.com/models/granite-4-2-30b}
}

More from IBM

Granite 4.1 8b

Unknown · 50 t/s

65.0

Granite 3.1 8b Instruct

Unknown · 50 t/s

60.0

Granite 3.0 8b Instruct

Unknown · 50 t/s

59.0

Granite 3.1 2b Instruct

Unknown · 50 t/s

59.0

Granite 3.0 2b Instruct

Unknown · 50 t/s

58.0

Granite 4.2 8B Instruct

Open Weights · 115 t/s

49.2

替代模型推荐

基于能力、定价和基准测试得分与 Granite 4.2 30B Instruct 最接近的替代模型。