Model comparison
Granite 4.2 3b vs Qwen3 14B
Granite 4.2 3b is the stronger model overall, scoring 39.4 to 35.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in reasoning, where Granite 4.2 3b leads 26.0 to 18.5.
Side by side
| Granite 4.2 3b | Qwen3 14B | |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 39.4 | 35.5 |
| Released | — | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.35 |
| Output $ / M tokens | — | $1.40 |
| Results tracked | 11 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.2 3b leads
Granite 4.2 3b: 40.0 (#151), Qwen3 14B: 37.3 (#195)
| Benchmark | Granite 4.2 3b | Qwen3 14B |
|---|---|---|
| SciCode | — | 31.6% |
| LMArena Coding | 1361 | — |
Agentic & Tool Use Not comparable
Granite 4.2 3b: —, Qwen3 14B: 29.6 (#83)
| Benchmark | Granite 4.2 3b | Qwen3 14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41% |
Reasoning Granite 4.2 3b leads
Granite 4.2 3b: 26.0 (#138), Qwen3 14B: 18.5 (#280)
| Benchmark | Granite 4.2 3b | Qwen3 14B |
|---|---|---|
| Kagi LLM Benchmark | — | 49.1% |
| CritPt | — | 0% |
| Chess Puzzles | — | 4% |
| LMArena Hard Prompts | 1306 | — |
| DTBench | — | 64% |
| LMCA | — | 18.2% |
| Epoch Capabilities Index | — | 138.23 |
Math Not comparable
Granite 4.2 3b: —, Qwen3 14B: 38.6 (#133)
| Benchmark | Granite 4.2 3b | Qwen3 14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 66.4% |
Knowledge Qwen3 14B leads
Granite 4.2 3b: 36.3 (#171), Qwen3 14B: 39.3 (#134)
| Benchmark | Granite 4.2 3b | Qwen3 14B |
|---|---|---|
| GPQA Diamond | — | 63.8% |
| Vectara Hallucination Rate | — | 5.4% |
| LMArena Expert | 1315 | — |
Multilingual Not comparable
Granite 4.2 3b: 42.1 (#198), Qwen3 14B: —
| Benchmark | Granite 4.2 3b | Qwen3 14B |
|---|---|---|
| LMArena Non-English | 1268 | — |
| LMArena Chinese | 1269 | — |
| LMArena Russian | 1249 | — |
Instruction Following Not comparable
Granite 4.2 3b: 67.1 (#200), Qwen3 14B: —
| Benchmark | Granite 4.2 3b | Qwen3 14B |
|---|---|---|
| LMArena Instruction Following | 1273 | — |
Long Context Granite 4.2 3b leads
Granite 4.2 3b: 39.2 (#185), Qwen3 14B: 38.1 (#204)
| Benchmark | Granite 4.2 3b | Qwen3 14B |
|---|---|---|
| Fiction.LiveBench | — | 62.5% |
| LMArena Longer Query | 1291 | — |
Writing & Preference Not comparable
Granite 4.2 3b: 47.2 (#212), Qwen3 14B: —
| Benchmark | Granite 4.2 3b | Qwen3 14B |
|---|---|---|
| LMArena Text | 1293 | — |
| LMArena Creative Writing | 1205 | — |
| LMArena Multi-Turn | 1290 | — |
Frequently asked questions
Is Granite 4.2 3b better than Qwen3 14B?
Granite 4.2 3b is the stronger model overall, scoring 39.4 to 35.5 on the Noometry Index.
Is Granite 4.2 3b or Qwen3 14B better for coding?
Granite 4.2 3b scores higher on coding benchmarks: 40.0 versus 37.3 in the Noometry coding category.
How many benchmarks do Granite 4.2 3b and Qwen3 14B share?
0 benchmarks have published results for both models. Granite 4.2 3b has 11 scored results on Noometry and Qwen3 14B has 12.