Model comparison
Dolly 2.0-12b vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 25.5 on the Noometry Index.
Last verified . 9 shared benchmarks.
Databricks
StepFunSummary
- They share 9 benchmarks with published results for both. Dolly 2.0-12b scores higher in 0 categories and Step 3 in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3 leads 54.3 to 15.2.
Side by side
| Dolly 2.0-12b | Step 3 | |
|---|---|---|
| Provider | Databricks | StepFun |
| Noometry Index | 25.5 | 40.5 |
| Released | 2023-04-11 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Dolly 2.0-12b: 23.4 (#332), Step 3: 40.1 (#147)
| Benchmark | Dolly 2.0-12b | Step 3 |
|---|---|---|
| LMArena Coding | 776 | 1367 |
Reasoning Step 3 leads
Dolly 2.0-12b: 15.3 (#316), Step 3: 28.4 (#105)
| Benchmark | Dolly 2.0-12b | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 804 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| Epoch Capabilities Index | 89.67 | — |
| HellaSwag | 70.8% | — |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |
Math Step 3 leads
Dolly 2.0-12b: 27.3 (#251), Step 3: 37.6 (#148)
| Benchmark | Dolly 2.0-12b | Step 3 |
|---|---|---|
| LMArena Math | 871 | 1366 |
Knowledge Not comparable
Dolly 2.0-12b: —, Step 3: 36.8 (#164)
| Benchmark | Dolly 2.0-12b | Step 3 |
|---|---|---|
| LMArena Expert | — | 1333 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| MMLU | 26.2% | — |
| OpenBookQA | 39.2% | — |
Multimodal Not comparable
Dolly 2.0-12b: —, Step 3: 35.5 (#86)
| Benchmark | Dolly 2.0-12b | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
Dolly 2.0-12b: 17.4 (#296), Step 3: 46.3 (#159)
| Benchmark | Dolly 2.0-12b | Step 3 |
|---|---|---|
| LMArena Non-English | 836 | 1327 |
| LMArena Chinese | 836 | 1397 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1269 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1371 |
Instruction Following Step 3 leads
Dolly 2.0-12b: 38.7 (#304), Step 3: 70.4 (#164)
| Benchmark | Dolly 2.0-12b | Step 3 |
|---|---|---|
| LMArena Instruction Following | 814 | 1332 |
Long Context Not comparable
Dolly 2.0-12b: —, Step 3: 40.3 (#157)
| Benchmark | Dolly 2.0-12b | Step 3 |
|---|---|---|
| LMArena Longer Query | — | 1326 |
Writing & Preference Step 3 leads
Dolly 2.0-12b: 15.2 (#311), Step 3: 54.3 (#151)
| Benchmark | Dolly 2.0-12b | Step 3 |
|---|---|---|
| LMArena Text | 851 | 1350 |
| LMArena Creative Writing | 864 | 1321 |
| LMArena Multi-Turn | 740 | 1341 |
Frequently asked questions
Is Dolly 2.0-12b better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 25.5 on the Noometry Index.
Is Dolly 2.0-12b or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 23.4 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Step 3 share?
9 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Step 3 has 17.