Model comparison
Granite 3.1 2b Instruct vs Qwen3.5 397B-A17B
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 33.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Granite 3.1 2b Instruct scores higher in 0 categories and Qwen3.5 397B-A17B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.5 397B-A17B leads 62.3 to 34.1.
Side by side
| Granite 3.1 2b Instruct | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 33.2 | 46.0 |
| Released | — | 2026-02-01 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.60 |
| Output $ / M tokens | — | $3.60 |
| Results tracked | 12 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 397B-A17B leads
Granite 3.1 2b Instruct: 33.4 (#257), Qwen3.5 397B-A17B: 42.0 (#114)
| Benchmark | Granite 3.1 2b Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Coding | 1149 | 1465 |
| LMArena WebDev | — | 1400 |
Agentic & Tool Use Not comparable
Granite 3.1 2b Instruct: —, Qwen3.5 397B-A17B: 33.3 (#53)
| Benchmark | Granite 3.1 2b Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | — | 24.9% |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
Reasoning Qwen3.5 397B-A17B leads
Granite 3.1 2b Instruct: 22.0 (#209), Qwen3.5 397B-A17B: 34.5 (#70)
| Benchmark | Granite 3.1 2b Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Hard Prompts | 1138 | 1448 |
| Kagi LLM Benchmark | — | 73.7% |
| NYT Connections (extended) | — | 58.9% |
| Chess Puzzles | — | 13% |
| Thematic Generalization | — | 65.1% |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 87.5% |
| LMCA | — | 37.9% |
| Epoch Capabilities Index | — | 146.65 |
Math Qwen3.5 397B-A17B leads
Granite 3.1 2b Instruct: 33.1 (#206), Qwen3.5 397B-A17B: 46.1 (#73)
| Benchmark | Granite 3.1 2b Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Math | 1159 | 1454 |
| FrontierMath (Tiers 1-3) | — | 31.2% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
Knowledge Qwen3.5 397B-A17B leads
Granite 3.1 2b Instruct: 30.8 (#224), Qwen3.5 397B-A17B: 53.3 (#58)
| Benchmark | Granite 3.1 2b Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Expert | 1131 | 1462 |
| GPQA Diamond | — | 86.4% |
Multimodal Not comparable
Granite 3.1 2b Instruct: —, Qwen3.5 397B-A17B: 40.7 (#44)
| Benchmark | Granite 3.1 2b Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | — | 1263 |
Multilingual Qwen3.5 397B-A17B leads
Granite 3.1 2b Instruct: 29.1 (#269), Qwen3.5 397B-A17B: 53.7 (#59)
| Benchmark | Granite 3.1 2b Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1068 | 1430 |
| LMArena Chinese | 1139 | 1500 |
| LMArena Russian | 1063 | 1429 |
| LMArena French | — | 1461 |
| LMArena German | — | 1447 |
| LMArena Japanese | — | 1426 |
| LMArena Korean | — | 1384 |
| LMArena Spanish | — | 1441 |
Instruction Following Qwen3.5 397B-A17B leads
Granite 3.1 2b Instruct: 57.7 (#264), Qwen3.5 397B-A17B: 75.0 (#77)
| Benchmark | Granite 3.1 2b Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1116 | 1424 |
Long Context Qwen3.5 397B-A17B leads
Granite 3.1 2b Instruct: 35.0 (#244), Qwen3.5 397B-A17B: 44.1 (#74)
| Benchmark | Granite 3.1 2b Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1155 | 1442 |
Writing & Preference Qwen3.5 397B-A17B leads
Granite 3.1 2b Instruct: 34.1 (#274), Qwen3.5 397B-A17B: 62.3 (#79)
| Benchmark | Granite 3.1 2b Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1127 | 1438 |
| LMArena Creative Writing | 1116 | 1401 |
| LMArena Multi-Turn | 1099 | 1446 |
| EQ-Bench Creative Writing | — | 1478 |
Frequently asked questions
Is Granite 3.1 2b Instruct better than Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 33.2 on the Noometry Index.
Is Granite 3.1 2b Instruct or Qwen3.5 397B-A17B better for coding?
Qwen3.5 397B-A17B scores higher on coding benchmarks: 42.0 versus 33.4 in the Noometry coding category.
How many benchmarks do Granite 3.1 2b Instruct and Qwen3.5 397B-A17B share?
12 benchmarks have published results for both models. Granite 3.1 2b Instruct has 12 scored results on Noometry and Qwen3.5 397B-A17B has 36.