# Dolly 2.0-12b vs Gemini 3.7 Flash

> Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 24.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/dolly-2-0-12b-vs-gemini-3-7-flash
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. Dolly 2.0-12b scores higher in 0 categories and Gemini 3.7 Flash in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 3.7 Flash leads 71.4 to 15.3.
- Dolly 2.0-12b has downloadable open weights; the other is API-only.

## Snapshot

| | Dolly 2.0-12b | Gemini 3.7 Flash |
|---|---|---|
| Provider | Databricks | Google |
| Noometry Index | 24.9 | 59.8 |
| Rank | 339 | 11 |
| Context | — | 1.05M |
| Input $/M | — | $0.75 |
| Output $/M | — | $3.75 |
| Weights | Open | Proprietary |

## Coding

- Dolly 2.0-12b: 23.0 (#327)
- Gemini 3.7 Flash: 55.7 (#19)

| Benchmark | Dolly 2.0-12b | Gemini 3.7 Flash |
|---|---|---|
| LMArena Coding | 776 | 1499 |
| DeepSWE | — | 65.5% |
| FrontierCode | — | 43.6% |
| LMArena WebDev | — | 1593 |
| FrontierSWE | — | 20.3% |
| SciCode | — | 59.8% |
| ALE-Bench | — | 904.3 |

## Agentic & Tool Use

- Dolly 2.0-12b: —
- Gemini 3.7 Flash: 42.2 (#18)

| Benchmark | Dolly 2.0-12b | Gemini 3.7 Flash |
|---|---|---|
| APEX-Agents | — | 67.8% |
| Remote Labor Index | — | 5% |
| GDP.pdf | — | 23.8% |

## Reasoning

- Dolly 2.0-12b: 14.6 (#315)
- Gemini 3.7 Flash: 70.1 (#12)

| Benchmark | Dolly 2.0-12b | Gemini 3.7 Flash |
|---|---|---|
| LMArena Hard Prompts | 804 | 1497 |
| Epoch Capabilities Index | 88.94 | 157.72 |
| ARC-AGI-2 | — | 84.6% |
| NYT Connections (extended) | — | 94% |
| ARC-AGI-1 | — | 95.5% |
| CritPt | — | 14.3% |
| Chess Puzzles | — | 47% |
| Mystery Game Puzzles | — | 37% |
| DTBench | — | 96.8% |
| LMCA | — | 50.4% |
| HellaSwag | 70.8% | — |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |

## Math

- Dolly 2.0-12b: 25.0 (#250)
- Gemini 3.7 Flash: 69.5 (#18)

| Benchmark | Dolly 2.0-12b | Gemini 3.7 Flash |
|---|---|---|
| LMArena Math | 871 | 1511 |
| FrontierMath (Tiers 1-3) | — | 71.6% |
| FrontierMath Tier 4 | — | 36.6% |
| OTIS Mock AIME 2024-2025 | — | 97.2% |
| ProofBench | — | 58% |

## Knowledge

- Dolly 2.0-12b: —
- Gemini 3.7 Flash: 69.8 (#4)

| Benchmark | Dolly 2.0-12b | Gemini 3.7 Flash |
|---|---|---|
| GPQA Diamond | — | 94.8% |
| SimpleQA Verified | — | 69.2% |
| LMArena Expert | — | 1508 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| MMLU | 26.2% | — |
| OpenBookQA | 39.2% | — |

## Multimodal

- Dolly 2.0-12b: —
- Gemini 3.7 Flash: 36.9 (#69)

| Benchmark | Dolly 2.0-12b | Gemini 3.7 Flash |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 26.7% |

## Multilingual

- Dolly 2.0-12b: 17.4 (#291)
- Gemini 3.7 Flash: 57.8 (#7)

| Benchmark | Dolly 2.0-12b | Gemini 3.7 Flash |
|---|---|---|
| LMArena Non-English | 836 | 1485 |
| LMArena Chinese | 836 | 1553 |
| LMArena French | — | 1512 |
| LMArena German | — | 1485 |
| LMArena Japanese | — | 1506 |
| LMArena Korean | — | 1486 |
| LMArena Russian | — | 1519 |
| LMArena Spanish | — | 1507 |

## Instruction Following

- Dolly 2.0-12b: 38.9 (#299)
- Gemini 3.7 Flash: 78.0 (#12)

| Benchmark | Dolly 2.0-12b | Gemini 3.7 Flash |
|---|---|---|
| LMArena Instruction Following | 814 | 1486 |

## Long Context

- Dolly 2.0-12b: —
- Gemini 3.7 Flash: 45.8 (#28)

| Benchmark | Dolly 2.0-12b | Gemini 3.7 Flash |
|---|---|---|
| LMArena Longer Query | — | 1493 |

## Writing & Preference

- Dolly 2.0-12b: 15.3 (#306)
- Gemini 3.7 Flash: 71.4 (#19)

| Benchmark | Dolly 2.0-12b | Gemini 3.7 Flash |
|---|---|---|
| LMArena Text | 851 | 1487 |
| LMArena Creative Writing | 864 | 1490 |
| LMArena Multi-Turn | 740 | 1495 |
| EQ-Bench Creative Writing | — | 1723 |

## FAQ

### Is Dolly 2.0-12b better than Gemini 3.7 Flash?

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 24.9 on the Noometry Index.

### Is Dolly 2.0-12b or Gemini 3.7 Flash better for coding?

Gemini 3.7 Flash scores higher on coding benchmarks: 55.7 versus 23.0 in the Noometry coding category.

### How many benchmarks do Dolly 2.0-12b and Gemini 3.7 Flash share?

10 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Gemini 3.7 Flash has 44.