Model comparison
Dolly 2.0-12b vs Gemma 3 4B
Gemma 3 4B is the stronger model overall, scoring 28.1 to 25.5 on the Noometry Index.
Last verified . 9 shared benchmarks.
Databricks
GoogleSummary
- They share 9 benchmarks with published results for both. Dolly 2.0-12b scores higher in 2 categories and Gemma 3 4B in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3 4B leads 42.0 to 15.2.
Side by side
| Dolly 2.0-12b | Gemma 3 4B | |
|---|---|---|
| Provider | Databricks | |
| Noometry Index | 25.5 | 28.1 |
| Released | 2023-04-11 | 2025-03-12 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.04 |
| Output $ / M tokens | — | $0.08 |
| Results tracked | 17 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3 4B leads
Dolly 2.0-12b: 23.4 (#332), Gemma 3 4B: 35.9 (#215)
| Benchmark | Dolly 2.0-12b | Gemma 3 4B |
|---|---|---|
| LMArena Coding | 776 | 1230 |
Agentic & Tool Use Not comparable
Dolly 2.0-12b: —, Gemma 3 4B: 20.9 (#142)
| Benchmark | Dolly 2.0-12b | Gemma 3 4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 19.6% |
Reasoning Dolly 2.0-12b leads
Dolly 2.0-12b: 15.3 (#316), Gemma 3 4B: 13.2 (#335)
| Benchmark | Dolly 2.0-12b | Gemma 3 4B |
|---|---|---|
| LMArena Hard Prompts | 804 | 1253 |
| Epoch Capabilities Index | 89.67 | 116.02 |
| Kagi LLM Benchmark | — | 25.2% |
| Chess Puzzles | — | 0% |
| DTBench | — | 50.9% |
| LMCA | — | 2.8% |
| HellaSwag | 70.8% | — |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |
Math Dolly 2.0-12b leads
Dolly 2.0-12b: 27.3 (#251), Gemma 3 4B: 16.8 (#292)
| Benchmark | Dolly 2.0-12b | Gemma 3 4B |
|---|---|---|
| LMArena Math | 871 | 1239 |
| OTIS Mock AIME 2024-2025 | — | 7.5% |
Knowledge Not comparable
Dolly 2.0-12b: —, Gemma 3 4B: 11.8 (#299)
| Benchmark | Dolly 2.0-12b | Gemma 3 4B |
|---|---|---|
| GPQA Diamond | — | 23.2% |
| Vectara Hallucination Rate | — | 6.4% |
| LMArena Expert | — | 1223 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| MMLU | 26.2% | — |
| OpenBookQA | 39.2% | — |
Multilingual Gemma 3 4B leads
Dolly 2.0-12b: 17.4 (#296), Gemma 3 4B: 42.5 (#194)
| Benchmark | Dolly 2.0-12b | Gemma 3 4B |
|---|---|---|
| LMArena Non-English | 836 | 1273 |
| LMArena Chinese | 836 | — |
| LMArena German | — | 1281 |
| LMArena Russian | — | 1294 |
Instruction Following Gemma 3 4B leads
Dolly 2.0-12b: 38.7 (#304), Gemma 3 4B: 65.2 (#225)
| Benchmark | Dolly 2.0-12b | Gemma 3 4B |
|---|---|---|
| LMArena Instruction Following | 814 | 1239 |
Long Context Not comparable
Dolly 2.0-12b: —, Gemma 3 4B: 38.7 (#194)
| Benchmark | Dolly 2.0-12b | Gemma 3 4B |
|---|---|---|
| LMArena Longer Query | — | 1273 |
Writing & Preference Gemma 3 4B leads
Dolly 2.0-12b: 15.2 (#311), Gemma 3 4B: 42.0 (#239)
| Benchmark | Dolly 2.0-12b | Gemma 3 4B |
|---|---|---|
| LMArena Text | 851 | 1291 |
| LMArena Creative Writing | 864 | 1271 |
| LMArena Multi-Turn | 740 | 1255 |
| EQ-Bench Creative Writing | — | 1068 |
Frequently asked questions
Is Dolly 2.0-12b better than Gemma 3 4B?
Gemma 3 4B is the stronger model overall, scoring 28.1 to 25.5 on the Noometry Index.
Is Dolly 2.0-12b or Gemma 3 4B better for coding?
Gemma 3 4B scores higher on coding benchmarks: 35.9 versus 23.4 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Gemma 3 4B share?
9 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Gemma 3 4B has 22.