Model comparison
gpt-oss-20b vs Granite 3.0 2b Instruct
gpt-oss-20b is the stronger model overall, scoring 32.5 to 30.8 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. gpt-oss-20b scores higher in 7 categories and Granite 3.0 2b Instruct in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where gpt-oss-20b leads 42.2 to 27.0.
Side by side
| gpt-oss-20b | Granite 3.0 2b Instruct | |
|---|---|---|
| Provider | OpenAI | IBM |
| Noometry Index | 32.5 | 30.8 |
| 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 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-20b leads
gpt-oss-20b: 37.6 (#192), Granite 3.0 2b Instruct: 28.3 (#316)
| Benchmark | gpt-oss-20b | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Coding | 1306 | 1090 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| BigCodeBench Instruct | — | 20.5% |
| ALE-Bench | 566.05 | — |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.3 (#154), Granite 3.0 2b Instruct: —
| Benchmark | gpt-oss-20b | Granite 3.0 2b Instruct |
|---|---|---|
| Terminal-Bench | 3.4% | — |
Reasoning Granite 3.0 2b Instruct leads
gpt-oss-20b: 19.3 (#261), Granite 3.0 2b Instruct: 20.5 (#235)
| Benchmark | gpt-oss-20b | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1274 | 1073 |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |
| Epoch Capabilities Index | 137.82 | — |
Math gpt-oss-20b leads
gpt-oss-20b: 39.4 (#103), Granite 3.0 2b Instruct: 32.2 (#217)
| Benchmark | gpt-oss-20b | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Math | 1317 | 1117 |
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| Omni-MATH | 56.5% | — |
Knowledge gpt-oss-20b leads
gpt-oss-20b: 34.6 (#195), Granite 3.0 2b Instruct: 29.0 (#241)
| Benchmark | gpt-oss-20b | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Expert | 1258 | 1064 |
| GPQA Diamond | 60.8% | — |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
Multilingual gpt-oss-20b leads
gpt-oss-20b: 42.2 (#197), Granite 3.0 2b Instruct: 27.0 (#278)
| Benchmark | gpt-oss-20b | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Non-English | 1268 | 1033 |
| LMArena Chinese | 1314 | 1070 |
| LMArena Russian | 1278 | 1045 |
| LMArena German | 1255 | — |
| LMArena Japanese | 1244 | — |
| LMArena Korean | 1236 | — |
| LMArena Spanish | 1267 | — |
Instruction Following gpt-oss-20b leads
gpt-oss-20b: 61.8 (#240), Granite 3.0 2b Instruct: 53.9 (#284)
| Benchmark | gpt-oss-20b | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Instruction Following | 1236 | 1056 |
| IFEval | 73.2% | — |
Long Context gpt-oss-20b leads
gpt-oss-20b: 37.9 (#209), Granite 3.0 2b Instruct: 32.5 (#268)
| Benchmark | gpt-oss-20b | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Longer Query | 1250 | 1070 |
Writing & Preference gpt-oss-20b leads
gpt-oss-20b: 35.5 (#265), Granite 3.0 2b Instruct: 29.6 (#292)
| Benchmark | gpt-oss-20b | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Text | 1287 | 1080 |
| LMArena Creative Writing | 1201 | 1046 |
| LMArena Multi-Turn | 1268 | 1053 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
Frequently asked questions
Is gpt-oss-20b better than Granite 3.0 2b Instruct?
gpt-oss-20b is the stronger model overall, scoring 32.5 to 30.8 on the Noometry Index.
Is gpt-oss-20b or Granite 3.0 2b Instruct better for coding?
gpt-oss-20b scores higher on coding benchmarks: 37.6 versus 28.3 in the Noometry coding category.
How many benchmarks do gpt-oss-20b and Granite 3.0 2b Instruct share?
12 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Granite 3.0 2b Instruct has 13.