Model comparison
Granite 3.1 2b Instruct vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 38.8 to 32.6 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 1 category and Qwen3 32B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3 32B leads 53.1 to 34.3.
Side by side
| Granite 3.1 2b Instruct | Qwen3 32B | |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 32.6 | 38.8 |
| Released | — | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 12 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 32B leads
Granite 3.1 2b Instruct: 32.9 (#255), Qwen3 32B: 37.3 (#184)
| Benchmark | Granite 3.1 2b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Coding | 1149 | 1358 |
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
Agentic & Tool Use Not comparable
Granite 3.1 2b Instruct: —, Qwen3 32B: 32.3 (#58)
| Benchmark | Granite 3.1 2b Instruct | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |
Reasoning Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 21.0 (#206), Qwen3 32B: 19.6 (#233)
| Benchmark | Granite 3.1 2b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Hard Prompts | 1138 | 1335 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
| Epoch Capabilities Index | — | 138.51 |
Math Qwen3 32B leads
Granite 3.1 2b Instruct: 30.6 (#206), Qwen3 32B: 37.9 (#89)
| Benchmark | Granite 3.1 2b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Math | 1159 | 1399 |
| OTIS Mock AIME 2024-2025 | — | 66.9% |
Knowledge Qwen3 32B leads
Granite 3.1 2b Instruct: 30.3 (#223), Qwen3 32B: 40.0 (#112)
| Benchmark | Granite 3.1 2b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Expert | 1131 | 1362 |
| GPQA Diamond | — | 65.7% |
| Vectara Hallucination Rate | — | 5.9% |
Multilingual Qwen3 32B leads
Granite 3.1 2b Instruct: 29.2 (#264), Qwen3 32B: 45.8 (#162)
| Benchmark | Granite 3.1 2b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1068 | 1317 |
| LMArena Chinese | 1138 | 1357 |
| LMArena Russian | 1063 | 1311 |
| LMArena German | — | 1341 |
Instruction Following Qwen3 32B leads
Granite 3.1 2b Instruct: 58.0 (#259), Qwen3 32B: 69.1 (#174)
| Benchmark | Granite 3.1 2b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1116 | 1305 |
Long Context Qwen3 32B leads
Granite 3.1 2b Instruct: 35.0 (#239), Qwen3 32B: 43.7 (#83)
| Benchmark | Granite 3.1 2b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 1155 | 1327 |
| Fiction.LiveBench | — | 74.2% |
Writing & Preference Qwen3 32B leads
Granite 3.1 2b Instruct: 34.3 (#269), Qwen3 32B: 53.1 (#158)
| Benchmark | Granite 3.1 2b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Text | 1127 | 1340 |
| LMArena Creative Writing | 1116 | 1297 |
| LMArena Multi-Turn | 1099 | 1331 |
Frequently asked questions
Is Granite 3.1 2b Instruct better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 38.8 to 32.6 on the Noometry Index.
Is Granite 3.1 2b Instruct or Qwen3 32B better for coding?
Qwen3 32B scores higher on coding benchmarks: 37.3 versus 32.9 in the Noometry coding category.
How many benchmarks do Granite 3.1 2b Instruct and Qwen3 32B share?
12 benchmarks have published results for both models. Granite 3.1 2b Instruct has 12 scored results on Noometry and Qwen3 32B has 26.