IBM, open weights
Granite 3.1 8b Instruct
Granite 3.1 8b Instruct by IBM ranks 258th of 354 ranked models on the Noometry Index as of October 2026, with a score of 32.4. Its strongest category is agentic & tool use, where it ranks 120th.
Last verified
Specifications
- Noometry rank
- #258 of 354
- Index score
- 32.4
- 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 34.5
- Agentic & Tool Use 24.1
- Reasoning 22.1
- Math 33.0
- Knowledge 31.1
- Multilingual 30.9
- Instruction Following 58.6
- Long Context 35.2
- Writing & Preference 35.5
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 34.5 | #233 | 1 |
| Agentic & Tool Use | 24.1 | #120 | 1 |
| Reasoning | 22.1 | #207 | 1 |
| Math | 33.0 | #209 | 1 |
| Knowledge | 31.1 | #220 | 1 |
| Multilingual | 30.9 | #260 | 1 |
| Instruction Following | 58.6 | #259 | 1 |
| Long Context | 35.2 | #241 | 1 |
| Writing & Preference | 35.5 | #266 | 3 |
Strengths and weaknesses
Categories where Granite 3.1 8b 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 | 30.9 | −16.5 | #260 of 297, top 88% |
| Writing & Preference | 35.5 | −18.2 | #266 of 312, top 86% |
| Instruction Following | 58.6 | −12.6 | #259 of 305, top 85% |
Closest competitors
The models ranked just above and below Granite 3.1 8b Instruct. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Olmo 2 0325 32b Instruct | #254 | 32.7 | — | — | Compare |
| gpt-oss-20b | #255 | 32.5 | $0.036 | 96 | Compare |
| Laguna M.1 | #256 | 32.5 | — | — | Compare |
| Command R+ | #257 | 32.4 | $4.38 | — | Compare |
| Pixtral Large | #259 | 32.2 | $3 | — | Compare |
| Falcon-180B | #260 | 32.2 | — | — | Compare |
| Gemini 1.5 Pro (May 2024) | #261 | 32.1 | — | — | Compare |
| Gemma 3 12B | #262 | 32.1 | $0.075 | — | 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 | 1186 | #246 of 294, top 84% | LMArena | 2026-10-08 |
Agentic & Tool Use
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | #39 of 49, top 80% | fc | Berkeley Function Calling Leaderboard |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Hard Prompts | 1145 | #256 of 297, top 87% | LMArena | 2026-10-08 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Math | 1152 | #250 of 285, top 88% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Expert | 1142 | #241 of 273, top 89% | LMArena | 2026-10-08 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1099 | #260 of 297, top 88% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1145 | #248 of 285, top 88% | LMArena | 2026-10-08 | |
| LMArena Russian | 1092 | #258 of 283, top 92% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1131 | #257 of 298, top 87% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1162 | #250 of 291, top 86% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1150 | #258 of 297, top 87% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1129 | #258 of 295, top 88% | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 1108 | #265 of 295, top 90% | LMArena | 2026-10-08 |
Compare Granite 3.1 8b Instruct
- Granite 3.1 8b Instruct vs Command R+
- Granite 3.1 8b Instruct vs Pixtral Large
- Granite 3.1 8b Instruct vs Laguna M.1
- Granite 3.1 8b Instruct vs Falcon-180B
- Granite 3.1 8b Instruct vs gpt-oss-20b
- Granite 3.1 8b Instruct vs Gemini 1.5 Pro (May 2024)
- Granite 3.1 8b Instruct vs GPT-6 Astra
- Granite 3.1 8b Instruct vs Claude Fable 5.1
- Granite 3.1 8b Instruct vs Gemini 3.8 Flash
- Granite 3.1 8b Instruct vs Kimi K3
- Granite 3.1 8b Instruct vs Grok 4.6
- Granite 3.1 8b Instruct vs Qwen3.8 Max
- Granite 3.1 8b Instruct vs GLM-5.3
- Granite 3.1 8b Instruct vs Muse Spark 1.3
Other IBM models
Frequently asked questions
How good is Granite 3.1 8b Instruct?
Granite 3.1 8b Instruct by IBM ranks 258th of 354 ranked models on the Noometry Index as of October 2026, with a score of 32.4. Its strongest category is agentic & tool use, where it ranks 120th.
Is Granite 3.1 8b Instruct open source?
Yes. Granite 3.1 8b Instruct's weights are downloadable; check the license for commercial terms.
What are Granite 3.1 8b Instruct's strengths and weaknesses?
Relative to other ranked models, Granite 3.1 8b Instruct places best in reasoning, math, coding and lowest in multilingual, writing & preference, instruction following.
What is Granite 3.1 8b Instruct best at?
Its best category is agentic & tool use, where it ranks 120th on Noometry.