Model comparison
Dolly 2.0-12b vs Gemini 3 Flash Preview
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 25.5 on the Noometry Index.
Last verified . 10 shared benchmarks.
Databricks
GoogleSummary
- They share 10 benchmarks with published results for both. Dolly 2.0-12b scores higher in 0 categories and Gemini 3 Flash Preview in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 3 Flash Preview leads 65.5 to 15.2.
- Dolly 2.0-12b has downloadable open weights; the other is API-only.
Side by side
| Dolly 2.0-12b | Gemini 3 Flash Preview | |
|---|---|---|
| Provider | Databricks | |
| Noometry Index | 25.5 | 52.3 |
| Released | 2023-04-11 | 2025-12-17 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $3 |
| Results tracked | 17 | 59 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Flash Preview leads
Dolly 2.0-12b: 23.4 (#332), Gemini 3 Flash Preview: 50.9 (#42)
| Benchmark | Dolly 2.0-12b | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Coding | 776 | 1460 |
| SWE-bench Verified | — | 75.4% |
| SWE-bench Verified (bash only) | — | 75.8% |
| LMArena WebDev | — | 1439 |
| SWE-bench Multilingual | — | 72.7% |
| GSO | — | 9.8% |
| WeirdML | — | 61.6% |
| ALE-Bench | — | 1,367 |
Agentic & Tool Use Not comparable
Dolly 2.0-12b: —, Gemini 3 Flash Preview: 38.7 (#29)
| Benchmark | Dolly 2.0-12b | Gemini 3 Flash Preview |
|---|---|---|
| Terminal-Bench | — | 64.3% |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 27.3% |
| τ²-bench Retail | — | 76.8% |
| τ²-bench Telecom | — | 91.2% |
| DeepResearch Bench | — | 49.8% |
| BALROG | — | 48.1% |
| GDP.pdf | — | 10% |
| LMArena Search | — | 1198 |
| Vending-Bench 2 | — | 3,635 |
Reasoning Gemini 3 Flash Preview leads
Dolly 2.0-12b: 15.3 (#316), Gemini 3 Flash Preview: 49.2 (#37)
| Benchmark | Dolly 2.0-12b | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Hard Prompts | 804 | 1465 |
| Epoch Capabilities Index | 89.67 | 151.8 |
| ARC-AGI-2 | — | 33.6% |
| SimpleBench | — | 61.1% |
| NYT Connections (extended) | — | 83.1% |
| ARC-AGI-1 | — | 84.7% |
| Chess Puzzles | — | 40% |
| Mystery Game Puzzles | — | 26% |
| DTBench | — | 89.1% |
| LMCA | — | 43.1% |
| ForecastBench | — | 58.5 |
| HellaSwag | 70.8% | — |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |
Math Gemini 3 Flash Preview leads
Dolly 2.0-12b: 27.3 (#251), Gemini 3 Flash Preview: 51.7 (#55)
| Benchmark | Dolly 2.0-12b | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Math | 871 | 1473 |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 17.1% |
| MathArena Final-Answer Competitions | — | 67.6% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 15% |
| FrontierMath (Feb 2025 set) | — | 35.6% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Not comparable
Dolly 2.0-12b: —, Gemini 3 Flash Preview: 58.8 (#33)
| Benchmark | Dolly 2.0-12b | Gemini 3 Flash Preview |
|---|---|---|
| GPQA Diamond | — | 89.4% |
| SimpleQA Verified | — | 66.8% |
| Vectara Hallucination Rate | — | 13.5% |
| LMArena Expert | — | 1462 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| MMLU | 26.2% | — |
| OpenBookQA | 39.2% | — |
Multimodal Not comparable
Dolly 2.0-12b: —, Gemini 3 Flash Preview: 45.5 (#16)
| Benchmark | Dolly 2.0-12b | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Vision | — | 1285 |
| GeoBench | — | 88% |
| VPCT | — | 72.6% |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1413 |
Multilingual Gemini 3 Flash Preview leads
Dolly 2.0-12b: 17.4 (#296), Gemini 3 Flash Preview: 55.7 (#27)
| Benchmark | Dolly 2.0-12b | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Non-English | 836 | 1458 |
| LMArena Chinese | 836 | 1511 |
| LMArena French | — | 1477 |
| LMArena German | — | 1497 |
| LMArena Japanese | — | 1489 |
| LMArena Korean | — | 1443 |
| LMArena Russian | — | 1480 |
| LMArena Spanish | — | 1469 |
Instruction Following Gemini 3 Flash Preview leads
Dolly 2.0-12b: 38.7 (#304), Gemini 3 Flash Preview: 75.7 (#56)
| Benchmark | Dolly 2.0-12b | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Instruction Following | 814 | 1437 |
Long Context Not comparable
Dolly 2.0-12b: —, Gemini 3 Flash Preview: 44.4 (#67)
| Benchmark | Dolly 2.0-12b | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Longer Query | — | 1452 |
Writing & Preference Gemini 3 Flash Preview leads
Dolly 2.0-12b: 15.2 (#311), Gemini 3 Flash Preview: 65.5 (#45)
| Benchmark | Dolly 2.0-12b | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Text | 851 | 1466 |
| LMArena Creative Writing | 864 | 1457 |
| LMArena Multi-Turn | 740 | 1471 |
Frequently asked questions
Is Dolly 2.0-12b better than Gemini 3 Flash Preview?
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 25.5 on the Noometry Index.
Is Dolly 2.0-12b or Gemini 3 Flash Preview better for coding?
Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 23.4 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Gemini 3 Flash Preview share?
10 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Gemini 3 Flash Preview has 59.