Model comparison
Granite 3.1 2b Instruct vs Qwen3 14B
Qwen3 14B is the stronger model overall, scoring 35.0 to 32.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in knowledge, where Qwen3 14B leads 39.2 to 30.3.
Side by side
| Granite 3.1 2b Instruct | Qwen3 14B | |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 32.6 | 35.0 |
| Released | — | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.35 |
| Output $ / M tokens | — | $1.40 |
| Results tracked | 12 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 14B leads
Granite 3.1 2b Instruct: 32.9 (#255), Qwen3 14B: 36.7 (#191)
| Benchmark | Granite 3.1 2b Instruct | Qwen3 14B |
|---|---|---|
| SciCode | — | 31.6% |
| LMArena Coding | 1149 | — |
Agentic & Tool Use Not comparable
Granite 3.1 2b Instruct: —, Qwen3 14B: 29.4 (#78)
| Benchmark | Granite 3.1 2b Instruct | Qwen3 14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41% |
Reasoning Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 21.0 (#206), Qwen3 14B: 18.1 (#272)
| Benchmark | Granite 3.1 2b Instruct | Qwen3 14B |
|---|---|---|
| Kagi LLM Benchmark | — | 49.1% |
| CritPt | — | 0% |
| Chess Puzzles | — | 4% |
| LMArena Hard Prompts | 1138 | — |
| DTBench | — | 64% |
| LMCA | — | 18.2% |
| Epoch Capabilities Index | — | 138.23 |
Math Qwen3 14B leads
Granite 3.1 2b Instruct: 30.6 (#206), Qwen3 14B: 37.0 (#102)
| Benchmark | Granite 3.1 2b Instruct | Qwen3 14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 66.4% |
| LMArena Math | 1159 | — |
Knowledge Qwen3 14B leads
Granite 3.1 2b Instruct: 30.3 (#223), Qwen3 14B: 39.2 (#124)
| Benchmark | Granite 3.1 2b Instruct | Qwen3 14B |
|---|---|---|
| GPQA Diamond | — | 63.8% |
| Vectara Hallucination Rate | — | 5.4% |
| LMArena Expert | 1131 | — |
Multilingual Not comparable
Granite 3.1 2b Instruct: 29.2 (#264), Qwen3 14B: —
| Benchmark | Granite 3.1 2b Instruct | Qwen3 14B |
|---|---|---|
| LMArena Non-English | 1068 | — |
| LMArena Chinese | 1138 | — |
| LMArena Russian | 1063 | — |
Instruction Following Not comparable
Granite 3.1 2b Instruct: 58.0 (#259), Qwen3 14B: —
| Benchmark | Granite 3.1 2b Instruct | Qwen3 14B |
|---|---|---|
| LMArena Instruction Following | 1116 | — |
Long Context Qwen3 14B leads
Granite 3.1 2b Instruct: 35.0 (#239), Qwen3 14B: 38.0 (#201)
| Benchmark | Granite 3.1 2b Instruct | Qwen3 14B |
|---|---|---|
| Fiction.LiveBench | — | 62.5% |
| LMArena Longer Query | 1155 | — |
Writing & Preference Not comparable
Granite 3.1 2b Instruct: 34.3 (#269), Qwen3 14B: —
| Benchmark | Granite 3.1 2b Instruct | Qwen3 14B |
|---|---|---|
| LMArena Text | 1127 | — |
| LMArena Creative Writing | 1116 | — |
| LMArena Multi-Turn | 1099 | — |
Frequently asked questions
Is Granite 3.1 2b Instruct better than Qwen3 14B?
Qwen3 14B is the stronger model overall, scoring 35.0 to 32.6 on the Noometry Index.
Is Granite 3.1 2b Instruct or Qwen3 14B better for coding?
Qwen3 14B scores higher on coding benchmarks: 36.7 versus 32.9 in the Noometry coding category.
How many benchmarks do Granite 3.1 2b Instruct and Qwen3 14B share?
0 benchmarks have published results for both models. Granite 3.1 2b Instruct has 12 scored results on Noometry and Qwen3 14B has 12.