Model comparison
Dolly 2.0-12b vs gpt-oss-20b
gpt-oss-20b is the stronger model overall, scoring 32.1 to 24.9 on the Noometry Index.
Last verified . 10 shared benchmarks.
DatabricksSummary
- They share 10 benchmarks with published results for both. Dolly 2.0-12b scores higher in 0 categories and gpt-oss-20b in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where gpt-oss-20b leads 42.4 to 17.4.
Side by side
| Dolly 2.0-12b | gpt-oss-20b | |
|---|---|---|
| Provider | Databricks | OpenAI |
| Noometry Index | 24.9 | 32.1 |
| Released | 2023-04-11 | 2025-08-05 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.018 |
| Output $ / M tokens | — | $0.09 |
| Results tracked | 17 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-20b leads
Dolly 2.0-12b: 23.0 (#327), gpt-oss-20b: 37.1 (#185)
| Benchmark | Dolly 2.0-12b | gpt-oss-20b |
|---|---|---|
| LMArena Coding | 776 | 1307 |
| SciCode | — | 34.4% |
| WeirdML | — | 40.9% |
| ALE-Bench | — | 566.05 |
Agentic & Tool Use Not comparable
Dolly 2.0-12b: —, gpt-oss-20b: 9.2 (#146)
| Benchmark | Dolly 2.0-12b | gpt-oss-20b |
|---|---|---|
| Terminal-Bench | — | 3.4% |
Reasoning gpt-oss-20b leads
Dolly 2.0-12b: 14.6 (#315), gpt-oss-20b: 18.8 (#251)
| Benchmark | Dolly 2.0-12b | gpt-oss-20b |
|---|---|---|
| LMArena Hard Prompts | 804 | 1274 |
| Epoch Capabilities Index | 88.94 | 137.81 |
| Kagi LLM Benchmark | — | 53.2% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 4% |
| DTBench | — | 68% |
| LMCA | — | 14.5% |
| HellaSwag | 70.8% | — |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |
Math gpt-oss-20b leads
Dolly 2.0-12b: 25.0 (#250), gpt-oss-20b: 37.6 (#93)
| Benchmark | Dolly 2.0-12b | gpt-oss-20b |
|---|---|---|
| LMArena Math | 871 | 1317 |
| OTIS Mock AIME 2024-2025 | — | 65.3% |
| Omni-MATH | — | 56.5% |
Knowledge Not comparable
Dolly 2.0-12b: —, gpt-oss-20b: 34.6 (#186)
| Benchmark | Dolly 2.0-12b | gpt-oss-20b |
|---|---|---|
| GPQA Diamond | — | 60.8% |
| MMLU-Pro | — | 74% |
| GPQA (HELM) | — | 59.4% |
| LMArena Expert | — | 1258 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| MMLU | 26.2% | — |
| OpenBookQA | 39.2% | — |
Multilingual gpt-oss-20b leads
Dolly 2.0-12b: 17.4 (#291), gpt-oss-20b: 42.4 (#192)
| Benchmark | Dolly 2.0-12b | gpt-oss-20b |
|---|---|---|
| LMArena Non-English | 836 | 1269 |
| LMArena Chinese | 836 | 1311 |
| LMArena German | — | 1249 |
| LMArena Japanese | — | 1245 |
| LMArena Korean | — | 1239 |
| LMArena Russian | — | 1279 |
| LMArena Spanish | — | 1267 |
Instruction Following gpt-oss-20b leads
Dolly 2.0-12b: 38.9 (#299), gpt-oss-20b: 62.0 (#235)
| Benchmark | Dolly 2.0-12b | gpt-oss-20b |
|---|---|---|
| LMArena Instruction Following | 814 | 1236 |
| IFEval | — | 73.2% |
Long Context Not comparable
Dolly 2.0-12b: —, gpt-oss-20b: 37.9 (#203)
| Benchmark | Dolly 2.0-12b | gpt-oss-20b |
|---|---|---|
| LMArena Longer Query | — | 1251 |
Writing & Preference gpt-oss-20b leads
Dolly 2.0-12b: 15.3 (#306), gpt-oss-20b: 35.8 (#260)
| Benchmark | Dolly 2.0-12b | gpt-oss-20b |
|---|---|---|
| LMArena Text | 851 | 1288 |
| LMArena Creative Writing | 864 | 1201 |
| LMArena Multi-Turn | 740 | 1268 |
| EQ-Bench Creative Writing | — | 666 |
| WildBench | — | 73.7% |
Frequently asked questions
Is Dolly 2.0-12b better than gpt-oss-20b?
gpt-oss-20b is the stronger model overall, scoring 32.1 to 24.9 on the Noometry Index.
Is Dolly 2.0-12b or gpt-oss-20b better for coding?
gpt-oss-20b scores higher on coding benchmarks: 37.1 versus 23.0 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and gpt-oss-20b share?
10 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and gpt-oss-20b has 34.