Model comparison
gpt-oss-20b vs Granite 4.0 H Small
Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 32.1 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. gpt-oss-20b scores higher in 5 categories and Granite 4.0 H Small in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-20b leads 37.6 to 29.3.
- The biggest single-benchmark swing is Omni-MATH: 56.5% for gpt-oss-20b and 29.6% for Granite 4.0 H Small.
Side by side
| gpt-oss-20b | Granite 4.0 H Small | |
|---|---|---|
| Provider | OpenAI | IBM |
| Noometry Index | 32.1 | 35.9 |
| Released | 2025-08-05 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.018 | — |
| Output $ / M tokens | $0.09 | — |
| Results tracked | 34 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-20b leads
gpt-oss-20b: 37.1 (#185), Granite 4.0 H Small: 35.8 (#207)
| Benchmark | gpt-oss-20b | Granite 4.0 H Small |
|---|---|---|
| LMArena Coding | 1307 | 1247 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| ALE-Bench | 566.05 | — |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.2 (#146), Granite 4.0 H Small: —
| Benchmark | gpt-oss-20b | Granite 4.0 H Small |
|---|---|---|
| Terminal-Bench | 3.4% | — |
Reasoning Granite 4.0 H Small leads
gpt-oss-20b: 18.8 (#251), Granite 4.0 H Small: 23.4 (#164)
| Benchmark | gpt-oss-20b | Granite 4.0 H Small |
|---|---|---|
| LMArena Hard Prompts | 1274 | 1240 |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |
| Epoch Capabilities Index | 137.81 | — |
Math gpt-oss-20b leads
gpt-oss-20b: 37.6 (#93), Granite 4.0 H Small: 29.3 (#219)
| Benchmark | gpt-oss-20b | Granite 4.0 H Small |
|---|---|---|
| Omni-MATH | 56.5% | 29.6% |
| LMArena Math | 1317 | 1251 |
| OTIS Mock AIME 2024-2025 | 65.3% | — |
Knowledge gpt-oss-20b leads
gpt-oss-20b: 34.6 (#186), Granite 4.0 H Small: 31.5 (#210)
| Benchmark | gpt-oss-20b | Granite 4.0 H Small |
|---|---|---|
| MMLU-Pro | 74% | 56.9% |
| GPQA (HELM) | 59.4% | 38.3% |
| LMArena Expert | 1258 | 1244 |
| GPQA Diamond | 60.8% | — |
| Vectara Hallucination Rate | — | 5.2% |
Multilingual gpt-oss-20b leads
gpt-oss-20b: 42.4 (#192), Granite 4.0 H Small: 38.7 (#223)
| Benchmark | gpt-oss-20b | Granite 4.0 H Small |
|---|---|---|
| LMArena Non-English | 1269 | 1216 |
| LMArena Chinese | 1311 | 1250 |
| LMArena Russian | 1279 | 1198 |
| LMArena Spanish | 1267 | 1258 |
| LMArena German | 1249 | — |
| LMArena Japanese | 1245 | — |
| LMArena Korean | 1239 | — |
Instruction Following Granite 4.0 H Small leads
gpt-oss-20b: 62.0 (#235), Granite 4.0 H Small: 68.9 (#178)
| Benchmark | gpt-oss-20b | Granite 4.0 H Small |
|---|---|---|
| IFEval | 73.2% | 89% |
| LMArena Instruction Following | 1236 | 1221 |
Long Context Too close to call
gpt-oss-20b: 37.9 (#203), Granite 4.0 H Small: 37.6 (#209)
| Benchmark | gpt-oss-20b | Granite 4.0 H Small |
|---|---|---|
| LMArena Longer Query | 1251 | 1240 |
Writing & Preference Granite 4.0 H Small leads
gpt-oss-20b: 35.8 (#260), Granite 4.0 H Small: 44.0 (#222)
| Benchmark | gpt-oss-20b | Granite 4.0 H Small |
|---|---|---|
| LMArena Text | 1288 | 1241 |
| LMArena Creative Writing | 1201 | 1210 |
| WildBench | 73.7% | 73.9% |
| LMArena Multi-Turn | 1268 | 1243 |
| EQ-Bench Creative Writing | 666 | — |
Frequently asked questions
Is gpt-oss-20b better than Granite 4.0 H Small?
Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 32.1 on the Noometry Index.
Is gpt-oss-20b or Granite 4.0 H Small better for coding?
gpt-oss-20b scores higher on coding benchmarks: 37.1 versus 35.8 in the Noometry coding category.
How many benchmarks do gpt-oss-20b and Granite 4.0 H Small share?
18 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Granite 4.0 H Small has 19.