Model comparison
Granite 4.0 H Small vs Qwen3-4B
Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 31.5 on the Noometry Index.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. Granite 4.0 H Small scores higher in 2 categories and Qwen3-4B in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Granite 4.0 H Small leads 23.4 to 18.5.
Side by side
| Granite 4.0 H Small | Qwen3-4B | |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 35.9 | 31.5 |
| Released | — | 2025-04-29 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Granite 4.0 H Small: 35.8 (#207), Qwen3-4B: —
| Benchmark | Granite 4.0 H Small | Qwen3-4B |
|---|---|---|
| LMArena Coding | 1247 | — |
Agentic & Tool Use Not comparable
Granite 4.0 H Small: —, Qwen3-4B: 27.3 (#94)
| Benchmark | Granite 4.0 H Small | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 35.7% |
Reasoning Granite 4.0 H Small leads
Granite 4.0 H Small: 23.4 (#164), Qwen3-4B: 18.5 (#264)
| Benchmark | Granite 4.0 H Small | Qwen3-4B |
|---|---|---|
| Chess Puzzles | — | 4% |
| LMArena Hard Prompts | 1240 | — |
Math Too close to call
Granite 4.0 H Small: 29.3 (#219), Qwen3-4B: 28.5 (#228)
| Benchmark | Granite 4.0 H Small | Qwen3-4B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 38.5% |
| OTIS Mock AIME 2024-2025 | — | 52.2% |
| Omni-MATH | 29.6% | — |
| LMArena Math | 1251 | — |
Knowledge Qwen3-4B leads
Granite 4.0 H Small: 31.5 (#210), Qwen3-4B: 33.0 (#198)
| Benchmark | Granite 4.0 H Small | Qwen3-4B |
|---|---|---|
| Vectara Hallucination Rate | 5.2% | 5.7% |
| GPQA Diamond | — | 52.3% |
| MMLU-Pro | 56.9% | — |
| GPQA (HELM) | 38.3% | — |
| LMArena Expert | 1244 | — |
Multilingual Not comparable
Granite 4.0 H Small: 38.7 (#223), Qwen3-4B: —
| Benchmark | Granite 4.0 H Small | Qwen3-4B |
|---|---|---|
| LMArena Non-English | 1216 | — |
| LMArena Chinese | 1250 | — |
| LMArena Russian | 1198 | — |
| LMArena Spanish | 1258 | — |
Instruction Following Not comparable
Granite 4.0 H Small: 68.9 (#178), Qwen3-4B: —
| Benchmark | Granite 4.0 H Small | Qwen3-4B |
|---|---|---|
| IFEval | 89% | — |
| LMArena Instruction Following | 1221 | — |
Long Context Not comparable
Granite 4.0 H Small: 37.6 (#209), Qwen3-4B: —
| Benchmark | Granite 4.0 H Small | Qwen3-4B |
|---|---|---|
| LMArena Longer Query | 1240 | — |
Writing & Preference Not comparable
Granite 4.0 H Small: 44.0 (#222), Qwen3-4B: —
| Benchmark | Granite 4.0 H Small | Qwen3-4B |
|---|---|---|
| LMArena Text | 1241 | — |
| LMArena Creative Writing | 1210 | — |
| WildBench | 73.9% | — |
| LMArena Multi-Turn | 1243 | — |
Frequently asked questions
Is Granite 4.0 H Small better than Qwen3-4B?
Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 31.5 on the Noometry Index.
How many benchmarks do Granite 4.0 H Small and Qwen3-4B share?
1 benchmark has published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Qwen3-4B has 6.