# Dolly 2.0-12b vs MiniMax-M3

> MiniMax-M3 is the stronger model overall, scoring 43.8 to 25.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/dolly-2-0-12b-vs-minimax-m3
- Last updated: 2026-10-12
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. Dolly 2.0-12b scores higher in 0 categories and MiniMax-M3 in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M3 leads 62.1 to 15.2.

## Snapshot

| | Dolly 2.0-12b | MiniMax-M3 |
|---|---|---|
| Provider | Databricks | MiniMax |
| Noometry Index | 25.5 | 43.8 |
| Rank | 342 | 85 |
| Context | — | 1M |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Open | Open |

## Coding

- Dolly 2.0-12b: 23.4 (#332)
- MiniMax-M3: 41.8 (#118)

| Benchmark | Dolly 2.0-12b | MiniMax-M3 |
|---|---|---|
| LMArena Coding | 776 | 1469 |
| FrontierCode | — | 14.7% |
| LMArena WebDev | — | 1482 |
| SciCode | — | 47.1% |
| ALE-Bench | — | 640.02 |

## Agentic & Tool Use

- Dolly 2.0-12b: —
- MiniMax-M3: 22.6 (#130)

| Benchmark | Dolly 2.0-12b | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |

## Reasoning

- Dolly 2.0-12b: 15.3 (#316)
- MiniMax-M3: 30.1 (#87)

| Benchmark | Dolly 2.0-12b | MiniMax-M3 |
|---|---|---|
| LMArena Hard Prompts | 804 | 1447 |
| Epoch Capabilities Index | 89.67 | 146.95 |
| SimpleBench | — | 45.8% |
| NYT Connections (extended) | — | 65.1% |
| CritPt | — | 3.7% |
| Chess Puzzles | — | 14% |
| Mystery Game Puzzles | — | 8% |
| DTBench | — | 78.9% |
| LMCA | — | 33.7% |
| Surface Evolver Bench | — | 55% |
| ForecastBench | — | 61.4 |
| HellaSwag | 70.8% | — |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |

## Math

- Dolly 2.0-12b: 27.3 (#251)
- MiniMax-M3: 40.0 (#95)

| Benchmark | Dolly 2.0-12b | MiniMax-M3 |
|---|---|---|
| LMArena Math | 871 | 1429 |
| OTIS Mock AIME 2024-2025 | — | 71.1% |
| ProofBench | — | 18% |

## Knowledge

- Dolly 2.0-12b: —
- MiniMax-M3: 58.4 (#35)

| Benchmark | Dolly 2.0-12b | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | — | 90.9% |
| LMArena Expert | — | 1461 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| MMLU | 26.2% | — |
| OpenBookQA | 39.2% | — |

## Multimodal

- Dolly 2.0-12b: —
- MiniMax-M3: 40.2 (#51)

| Benchmark | Dolly 2.0-12b | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1253 |
| LMArena Document | — | 1435 |

## Multilingual

- Dolly 2.0-12b: 17.4 (#296)
- MiniMax-M3: 53.0 (#75)

| Benchmark | Dolly 2.0-12b | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 836 | 1420 |
| LMArena Chinese | 836 | 1463 |
| LMArena French | — | 1447 |
| LMArena German | — | 1426 |
| LMArena Japanese | — | 1381 |
| LMArena Korean | — | 1372 |
| LMArena Russian | — | 1428 |
| LMArena Spanish | — | 1432 |

## Instruction Following

- Dolly 2.0-12b: 38.7 (#304)
- MiniMax-M3: 75.5 (#62)

| Benchmark | Dolly 2.0-12b | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 814 | 1433 |

## Long Context

- Dolly 2.0-12b: —
- MiniMax-M3: 44.2 (#72)

| Benchmark | Dolly 2.0-12b | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | — | 1445 |

## Writing & Preference

- Dolly 2.0-12b: 15.2 (#311)
- MiniMax-M3: 62.1 (#83)

| Benchmark | Dolly 2.0-12b | MiniMax-M3 |
|---|---|---|
| LMArena Text | 851 | 1433 |
| LMArena Creative Writing | 864 | 1404 |
| LMArena Multi-Turn | 740 | 1442 |
| EQ-Bench 4 | — | 1150 |

## FAQ

### Is Dolly 2.0-12b better than MiniMax-M3?

MiniMax-M3 is the stronger model overall, scoring 43.8 to 25.5 on the Noometry Index.

### Is Dolly 2.0-12b or MiniMax-M3 better for coding?

MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 23.4 in the Noometry coding category.

### How many benchmarks do Dolly 2.0-12b and MiniMax-M3 share?

10 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and MiniMax-M3 has 41.