IBM, open weights
Granite 4.2 8B
Granite 4.2 8B by IBM ranks 148th of 354 ranked models on the Noometry Index as of October 2026, with a score of 40.5. Its strongest category is reasoning, where it ranks 131st. API pricing starts at $0.06 per million input tokens and $0.25 per million output tokens, with a 131K-token context window.
Last verified
Specifications
- Noometry rank
- #148 of 354
- Index score
- 40.5
- Evidence
- Confirmed 11 results
- Provider
- IBM
- Released
- Unknown
- Weights
- Open weights
- Reasoning
- Yes
- Context window
- 131K
- Max output
- 118K
- Input price
- $0.06 / M
- Output price
- $0.25 / M
- Blended price
- $0.11 / M
- Output speed
- Not measured
- Value
- #14 of 219
- Knowledge cutoff
- Unknown
- Input
- text
- Hugging Face
- ibm-granite/granite-4.2-8b
Category scores
Each category score combines every public result we have in that category.
- Coding 40.5
- Reasoning 26.6
- Knowledge 38.4
- Multilingual 44.5
- Instruction Following 68.7
- Long Context 40.3
- Writing & Preference 49.6
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 40.5 | #137 | 1 |
| Reasoning | 26.6 | #131 | 1 |
| Knowledge | 38.4 | #145 | 1 |
| Multilingual | 44.5 | #178 | 1 |
| Instruction Following | 68.7 | #184 | 1 |
| Long Context | 40.3 | #159 | 1 |
| Writing & Preference | 49.6 | #189 | 3 |
Strengths and weaknesses
Categories where Granite 4.2 8B places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Writing & Preference | 49.6 | −4.2 | #189 of 312, top 61% |
| Instruction Following | 68.7 | −2.6 | #184 of 305, top 61% |
| Multilingual | 44.5 | −2.9 | #178 of 297, top 60% |
Closest competitors
The models ranked just above and below Granite 4.2 8B. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Gemini 3.1 Flash Lite | #144 | 40.8 | $0.56 | 10 | Compare |
| Claude Sonnet 4 | #145 | 40.8 | $6 | 31 | Compare |
| Qwen2.5-Max | #146 | 40.7 | — | — | Compare |
| Nemotron 3 Nano 30B A3B | #147 | 40.6 | $0.0875 | — | Compare |
| Step 3 | #149 | 40.5 | — | 7 | Compare |
| MiniMax M1 | #150 | 40.3 | $0.96 | — | Compare |
| Nvidia Llama 3.3 Nemotron Super 49b v1.5 | #151 | 40.3 | $0.40 | — | Compare |
| Mistral Medium 3.5 | #152 | 40.2 | $3 | 50 | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Coding | 1380 | #149 of 294, top 51% | LMArena | 2026-10-08 |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Hard Prompts | 1329 | #174 of 297, top 59% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Expert | 1384 | #136 of 273, top 50% | LMArena | 2026-10-08 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1302 | #178 of 297, top 60% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1366 | #158 of 285, top 56% | LMArena | 2026-10-08 | |
| LMArena Russian | 1285 | #187 of 283, top 67% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1301 | #178 of 298, top 60% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1324 | #170 of 291, top 59% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1320 | #179 of 297, top 61% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1236 | #216 of 295, top 74% | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 1301 | #187 of 295, top 64% | LMArena | 2026-10-08 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| openrouter | $0.06 | $0.25 | $0.015 | 2026-10-10 |
Compare Granite 4.2 8B
- Granite 4.2 8B vs Nemotron 3 Nano 30B A3B
- Granite 4.2 8B vs Step 3
- Granite 4.2 8B vs Qwen2.5-Max
- Granite 4.2 8B vs MiniMax M1
- Granite 4.2 8B vs Claude Sonnet 4
- Granite 4.2 8B vs Nvidia Llama 3.3 Nemotron Super 49b v1.5
- Granite 4.2 8B vs GPT-6 Astra
- Granite 4.2 8B vs Claude Fable 5.1
- Granite 4.2 8B vs Gemini 3.8 Flash
- Granite 4.2 8B vs Kimi K3
- Granite 4.2 8B vs Grok 4.6
- Granite 4.2 8B vs Qwen3.8 Max
- Granite 4.2 8B vs GLM-5.3
- Granite 4.2 8B vs Muse Spark 1.3
Other IBM models
Frequently asked questions
How good is Granite 4.2 8B?
Granite 4.2 8B by IBM ranks 148th of 354 ranked models on the Noometry Index as of October 2026, with a score of 40.5. Its strongest category is reasoning, where it ranks 131st. API pricing starts at $0.06 per million input tokens and $0.25 per million output tokens, with a 131K-token context window.
How much does Granite 4.2 8B cost?
Granite 4.2 8B costs $0.06 per million input tokens and $0.25 per million output tokens on openrouter, with cached input at $0.015.
What is Granite 4.2 8B's context window?
Granite 4.2 8B accepts up to 131K tokens of input and can write up to 118K tokens in one response.
Is Granite 4.2 8B open source?
Yes. Granite 4.2 8B's weights are downloadable from Hugging Face (ibm-granite/granite-4.2-8b); check the license for commercial terms.
What are Granite 4.2 8B's strengths and weaknesses?
Relative to other ranked models, Granite 4.2 8B places best in reasoning, coding, knowledge and lowest in writing & preference, instruction following, multilingual.
What is Granite 4.2 8B best at?
Its best category is reasoning, where it ranks 131st on Noometry.