IBM, open weights
Granite 3.0 2b Instruct
Granite 3.0 2b Instruct by IBM ranks 286th of 354 ranked models on the Noometry Index as of October 2026, with a score of 30.8. Its strongest category is math, where it ranks 217th.
Last verified
Specifications
- Noometry rank
- #286 of 354
- Index score
- 30.8
- Evidence
- Confirmed 13 results
- Provider
- IBM
- Released
- Unknown
- Weights
- Open weights
- Reasoning
- Unknown
- Context window
- —
- Max output
- —
- Input price
- Not listed
- Output price
- Not listed
- Blended price
- Not listed
- Output speed
- Not measured
- Value
- Not ranked
- Knowledge cutoff
- Unknown
Category scores
Each category score combines every public result we have in that category.
- Coding 28.3
- Reasoning 20.5
- Math 32.2
- Knowledge 29.0
- Multilingual 27.0
- Instruction Following 53.9
- Long Context 32.5
- Writing & Preference 29.6
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 28.3 | #316 | 2 |
| Reasoning | 20.5 | #235 | 1 |
| Math | 32.2 | #217 | 1 |
| Knowledge | 29.0 | #241 | 1 |
| Multilingual | 27.0 | #278 | 1 |
| Instruction Following | 53.9 | #284 | 1 |
| Long Context | 32.5 | #268 | 1 |
| Writing & Preference | 29.6 | #292 | 3 |
Strengths and weaknesses
Categories where Granite 3.0 2b Instruct 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 |
|---|---|---|---|
| Multilingual | 27.0 | −20.4 | #278 of 297, top 94% |
| Writing & Preference | 29.6 | −24.1 | #292 of 312, top 94% |
| Instruction Following | 53.9 | −17.3 | #284 of 305, top 94% |
Closest competitors
The models ranked just above and below Granite 3.0 2b Instruct. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Llama 4 Maverick | #282 | 30.9 | $0.30 | 456 | Compare |
| Phi-4 Mini | #283 | 30.9 | $0.13 | — | Compare |
| Gemma 3 27B | #284 | 30.8 | $0.10 | 62 | Compare |
| Qwen1.5-72B | #285 | 30.8 | — | — | Compare |
| Codellama 34b Instruct | #287 | 30.8 | — | — | Compare |
| Llama 3.1-405B | #288 | 30.7 | — | 78 | Compare |
| Yi-1.5-34B | #289 | 30.6 | — | — | Compare |
| Codestral | #290 | 30.6 | $0.45 | 271 | 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 |
|---|---|---|---|---|---|
| BigCodeBench Instruct | 20.5% | #61 of 64, top 96% | BigCodeBench | 2024-10-21 | |
| LMArena Coding | 1090 | #274 of 294, top 94% | LMArena | 2026-10-08 |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Hard Prompts | 1073 | #273 of 297, top 92% | LMArena | 2026-10-08 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Math | 1117 | #261 of 285, top 92% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Expert | 1064 | #258 of 273, top 95% | LMArena | 2026-10-08 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1033 | #278 of 297, top 94% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1070 | #261 of 285, top 92% | LMArena | 2026-10-08 | |
| LMArena Russian | 1045 | #270 of 283, top 96% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1056 | #280 of 298, top 94% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1070 | #273 of 291, top 94% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1080 | #280 of 297, top 95% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1046 | #279 of 295, top 95% | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 1053 | #276 of 295, top 94% | LMArena | 2026-10-08 |
Compare Granite 3.0 2b Instruct
- Granite 3.0 2b Instruct vs Qwen1.5-72B
- Granite 3.0 2b Instruct vs Codellama 34b Instruct
- Granite 3.0 2b Instruct vs Gemma 3 27B
- Granite 3.0 2b Instruct vs Llama 3.1-405B
- Granite 3.0 2b Instruct vs Phi-4 Mini
- Granite 3.0 2b Instruct vs Yi-1.5-34B
- Granite 3.0 2b Instruct vs GPT-6 Astra
- Granite 3.0 2b Instruct vs Claude Fable 5.1
- Granite 3.0 2b Instruct vs Gemini 3.8 Flash
- Granite 3.0 2b Instruct vs Kimi K3
- Granite 3.0 2b Instruct vs Grok 4.6
- Granite 3.0 2b Instruct vs Qwen3.8 Max
- Granite 3.0 2b Instruct vs GLM-5.3
- Granite 3.0 2b Instruct vs Muse Spark 1.3
Other IBM models
Frequently asked questions
How good is Granite 3.0 2b Instruct?
Granite 3.0 2b Instruct by IBM ranks 286th of 354 ranked models on the Noometry Index as of October 2026, with a score of 30.8. Its strongest category is math, where it ranks 217th.
Is Granite 3.0 2b Instruct open source?
Yes. Granite 3.0 2b Instruct's weights are downloadable; check the license for commercial terms.
What are Granite 3.0 2b Instruct's strengths and weaknesses?
Relative to other ranked models, Granite 3.0 2b Instruct places best in math, reasoning, knowledge and lowest in multilingual, writing & preference, instruction following.
What is Granite 3.0 2b Instruct best at?
Its best category is math, where it ranks 217th on Noometry.