# Dolly 2.0-12b vs Qwen3.8 Max

> Qwen3.8 Max is the stronger model overall, scoring 56.8 to 25.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/dolly-2-0-12b-vs-qwen3-8-max
- 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 Qwen3.8 Max in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.8 Max leads 67.1 to 15.2.
- Dolly 2.0-12b has downloadable open weights; the other is API-only.

## Snapshot

| | Dolly 2.0-12b | Qwen3.8 Max |
|---|---|---|
| Provider | Databricks | Alibaba (Qwen) |
| Noometry Index | 25.5 | 56.8 |
| Rank | 342 | 22 |
| Context | — | 1M |
| Input $/M | — | $2 |
| Output $/M | — | $6 |
| Weights | Open | Proprietary |

## Coding

- Dolly 2.0-12b: 23.4 (#332)
- Qwen3.8 Max: 53.5 (#29)

| Benchmark | Dolly 2.0-12b | Qwen3.8 Max |
|---|---|---|
| LMArena Coding | 776 | 1502 |
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |

## Agentic & Tool Use

- Dolly 2.0-12b: —
- Qwen3.8 Max: 45.4 (#14)

| Benchmark | Dolly 2.0-12b | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |

## Reasoning

- Dolly 2.0-12b: 15.3 (#316)
- Qwen3.8 Max: 54.4 (#26)

| Benchmark | Dolly 2.0-12b | Qwen3.8 Max |
|---|---|---|
| LMArena Hard Prompts | 804 | 1496 |
| Epoch Capabilities Index | 89.67 | 156.41 |
| NYT Connections (extended) | — | 88.3% |
| CritPt | — | 20% |
| Chess Puzzles | — | 40% |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LMCA | — | 46.2% |
| HellaSwag | 70.8% | — |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |

## Math

- Dolly 2.0-12b: 27.3 (#251)
- Qwen3.8 Max: 73.2 (#20)

| Benchmark | Dolly 2.0-12b | Qwen3.8 Max |
|---|---|---|
| LMArena Math | 871 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 58% |

## Knowledge

- Dolly 2.0-12b: —
- Qwen3.8 Max: 61.7 (#27)

| Benchmark | Dolly 2.0-12b | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | — | 92.7% |
| SimpleQA Verified | — | 47.3% |
| LMArena Expert | — | 1507 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| MMLU | 26.2% | — |
| OpenBookQA | 39.2% | — |

## Multimodal

- Dolly 2.0-12b: —
- Qwen3.8 Max: 37.2 (#75)

| Benchmark | Dolly 2.0-12b | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |

## Multilingual

- Dolly 2.0-12b: 17.4 (#296)
- Qwen3.8 Max: 56.7 (#18)

| Benchmark | Dolly 2.0-12b | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 836 | 1472 |
| LMArena Chinese | 836 | 1538 |
| LMArena French | — | 1503 |
| LMArena German | — | 1483 |
| LMArena Japanese | — | 1467 |
| LMArena Korean | — | 1461 |
| LMArena Russian | — | 1481 |
| LMArena Spanish | — | 1492 |

## Instruction Following

- Dolly 2.0-12b: 38.7 (#304)
- Qwen3.8 Max: 77.6 (#17)

| Benchmark | Dolly 2.0-12b | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 814 | 1479 |

## Long Context

- Dolly 2.0-12b: —
- Qwen3.8 Max: 45.6 (#31)

| Benchmark | Dolly 2.0-12b | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | — | 1489 |

## Writing & Preference

- Dolly 2.0-12b: 15.2 (#311)
- Qwen3.8 Max: 67.1 (#30)

| Benchmark | Dolly 2.0-12b | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 851 | 1483 |
| LMArena Creative Writing | 864 | 1479 |
| LMArena Multi-Turn | 740 | 1489 |

## FAQ

### Is Dolly 2.0-12b better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 25.5 on the Noometry Index.

### Is Dolly 2.0-12b or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 23.4 in the Noometry coding category.

### How many benchmarks do Dolly 2.0-12b and Qwen3.8 Max share?

10 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Qwen3.8 Max has 39.