IBM model product
IBM Granite 4.2 30B
2 30B is a text-only dense decoder-only reasoning LLM with native think, non-think, and low-effort modes, tool calling, and a 128K context window extendable to 512K.
Updated Sep 8, 2026. Default version: IBM Granite 4.2 30B
LLMBoard Score39.3IBM Granite 4.2 30B
Coverage40%18 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
IBM Granite 4.2 30B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
IBM Granite 4.2 30B Benchmark Results
Benchmark scores for IBM Granite 4.2 30B.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkProfBench | Score42.90% | Rank02 | Participants4 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkRULER 128k | Score81.38% | Rank02 | Participants4 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkRULER 64k | Score89.96% | Rank02 | Participants4 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkBird-SQL (dev) | Score41.85% | Rank05 | Participants9 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkTAU3-Bench | Score62.00% | Rank05 | Participants8 | Percentile42.86% | EvidenceC | Evaluated |
| BenchmarkArena-Hard v2 | Score67.93% | Rank08 | Participants19 | Percentile61.11% | EvidenceC | Evaluated |
| BenchmarkBFCL-V4 | Score61.39% | Rank09 | Participants18 | Percentile52.94% | EvidenceC | Evaluated |
| BenchmarkHMMT25 | Score89.17% | Rank09 | Participants28 | Percentile70.37% | EvidenceC | Evaluated |
| BenchmarkIFBench | Score77.17% | Rank12 | Participants39 | Percentile71.05% | EvidenceC | Evaluated |
| BenchmarkSciCode | Score38.76% | Rank15 | Participants24 | Percentile39.13% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench v6 | Score75.77% | Rank29 | Participants62 | Percentile54.10% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.1 | Score29.24% | Rank33 | Participants35 | Percentile5.88% | EvidenceC | Evaluated |
| BenchmarkSWE-bench Multilingual | Score41.89% | Rank39 | Participants43 | Percentile9.52% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score89.17% | Rank52 | Participants119 | Percentile56.78% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Pro | Score33.29% | Rank54 | Participants55 | Percentile1.85% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score77.60% | Rank69 | Participants138 | Percentile50.37% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score57.00% | Rank88 | Participants113 | Percentile22.32% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,377.83 rating | Rank113 | Participants121 | Percentile6.67% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,362.98 rating | Rank127 | Participants210 | Percentile39.71% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,341.72 rating | Rank153 | Participants210 | Percentile27.27% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score66.41% | Rank154 | Participants247 | Percentile37.80% | EvidenceC | Evaluated |
IBM Granite 4.2 30B Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext factuality | Categorycreative writing | Rank97 | Rating / score1,336.18 | Votes596 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts english | Rank100 | Rating / score1,424.02 | Votes903 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry entertainment and sports and media | Rank100 | Rating / score1,335.14 | Votes736 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank101 | Rating / score1,401.97 | Votes343 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycoding | Rank102 | Rating / score1,433.88 | Votes818 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry software and it services | Rank105 | Rating / score1,425.79 | Votes1,212 | ObservationsN/A | Result date |
| Arenatext factuality | Categorylonger query | Rank105 | Rating / score1,386.14 | Votes1,365 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryinstruction following | Rank106 | Rating / score1,370.88 | Votes1,110 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry writing and literature and language | Rank107 | Rating / score1,342.67 | Votes827 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryenglish | Rank108 | Rating / score1,401.73 | Votes1,397 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexclude ties | Rank110 | Rating / score1,357.22 | Votes2,474 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts | Rank110 | Rating / score1,400.69 | Votes2,047 | ObservationsN/A | Result date |
| Arenatext factuality | Categorynon english | Rank112 | Rating / score1,357.27 | Votes1,878 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryoverall | Rank113 | Rating / score1,377.83 | Votes3,275 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry life and physical and social science | Rank114 | Rating / score1,387.58 | Votes491 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts english | Rank115 | Rating / score1,389.74 | Votes915 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank116 | Rating / score1,405.49 | Votes194 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry software and it services | Rank116 | Rating / score1,399.49 | Votes1,212 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank117 | Rating / score1,386.48 | Votes1,397 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts | Rank120 | Rating / score1,373.88 | Votes2,047 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank121 | Rating / score1,392.07 | Votes824 | ObservationsN/A | Result date |
| Arenatext | Categorylonger query | Rank125 | Rating / score1,356.52 | Votes1,365 | ObservationsN/A | Result date |
| Arenatext | Categoryexclude ties | Rank126 | Rating / score1,331.17 | Votes2,474 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank127 | Rating / score1,362.98 | Votes3,275 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank128 | Rating / score1,347.48 | Votes618 | ObservationsN/A | Result date |
| Arenatext | Categoryinstruction following | Rank128 | Rating / score1,344.78 | Votes1,110 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexpert | Rank128 | Rating / score1,392.36 | Votes343 | ObservationsN/A | Result date |
| Arenatext | Categorynon english | Rank129 | Rating / score1,340.37 | Votes1,878 | ObservationsN/A | Result date |
| Arenatext | Categoryrussian | Rank129 | Rating / score1,347.58 | Votes337 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry legal and government | Rank133 | Rating / score1,353.63 | Votes245 | ObservationsN/A | Result date |
IBM Granite 4.2 30B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 0
No provider prices
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
IBM Granite 4.2 30B Runtime Performance
Provider-specific output speed and catalog latency for IBM Granite 4.2 30B. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
IBM Granite 4.2 30B Specifications
Technical details for the model's default version.
- Version
- IBM Granite 4.2 30B
- Released
- Aug 25, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 30B
- Context window
- N/A
- Max output
- N/A
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- Apache 2.0
IBM Granite 4.2 30B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionIBM Granite 4.2 30B | Released | LLMBoard39.32 | Parameters30B | ContextN/A | Max outputN/A | Open weightsYes | LicenseApache 2.0 |
Models similar to IBM Granite 4.2 30B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
IB
IBM Granite 4.2 8B
IBM
IB
IBM Granite 4.2 3B
IBM
IB
Granite 3.3 8B
IBM
IB
IBM Granite 4.0 Tiny
IBM
AC
Qwen3 VL 32B Thinking
Alibaba Cloud / Qwen Team
XA
Grok 4.3
xAI
What is IBM Granite 4.2 30B?
Key information about IBM Granite 4.2 30B and its available data.
0. It supports multi-step tool use and is not multimodal.
Data as of 2026-09-08.
FAQ
Common questions about IBM Granite 4.2 30B.
When was IBM Granite 4.2 30B released?
IBM Granite 4.2 30B's default version was released on Aug 25, 2026.
How much does IBM Granite 4.2 30B cost?
No official standard PAYG price is currently available for IBM Granite 4.2 30B.
Who created IBM Granite 4.2 30B?
IBM Granite 4.2 30B was created by IBM.
What is the context window for IBM Granite 4.2 30B?
A context window is not available for the default version.
Is IBM Granite 4.2 30B open weight?
Yes. The default version is marked as open weight under Apache 2.0.
How many API providers offer IBM Granite 4.2 30B?
No provider offering is currently linked to the default version.