# Molmo 2 8b vs Qwen3-1.7B

> Molmo 2 8b is the stronger model overall, scoring 38.7 to 26.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/molmo-2-8b-vs-qwen3-1-7b
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where Molmo 2 8b leads 24.5 to 18.5.

## Snapshot

| | Molmo 2 8b | Qwen3-1.7B |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Alibaba (Qwen) |
| Noometry Index | 38.7 | 26.2 |
| Rank | 170 | 331 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Agentic & Tool Use

- Molmo 2 8b: —
- Qwen3-1.7B: 24.5 (#108)

| Benchmark | Molmo 2 8b | Qwen3-1.7B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.4% |

## Reasoning

- Molmo 2 8b: 24.5 (#146)
- Qwen3-1.7B: 18.5 (#263)

| Benchmark | Molmo 2 8b | Qwen3-1.7B |
|---|---|---|
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1288 | — |

## Math

- Molmo 2 8b: —
- Qwen3-1.7B: 15.4 (#288)

| Benchmark | Molmo 2 8b | Qwen3-1.7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 8.1% |

## Knowledge

- Molmo 2 8b: —
- Qwen3-1.7B: 19.6 (#273)

| Benchmark | Molmo 2 8b | Qwen3-1.7B |
|---|---|---|
| GPQA Diamond | — | 38% |

## Multimodal

- Molmo 2 8b: 29.5 (#106)
- Qwen3-1.7B: —

| Benchmark | Molmo 2 8b | Qwen3-1.7B |
|---|---|---|
| LMArena Vision | 1081 | — |

## Multilingual

- Molmo 2 8b: 42.8 (#186)
- Qwen3-1.7B: —

| Benchmark | Molmo 2 8b | Qwen3-1.7B |
|---|---|---|
| LMArena Non-English | 1275 | — |

## Instruction Following

- Molmo 2 8b: 67.2 (#196)
- Qwen3-1.7B: —

| Benchmark | Molmo 2 8b | Qwen3-1.7B |
|---|---|---|
| LMArena Instruction Following | 1270 | — |

## Writing & Preference

- Molmo 2 8b: 49.5 (#187)
- Qwen3-1.7B: —

| Benchmark | Molmo 2 8b | Qwen3-1.7B |
|---|---|---|
| LMArena Text | 1288 | — |

## FAQ

### Is Molmo 2 8b better than Qwen3-1.7B?

Molmo 2 8b is the stronger model overall, scoring 38.7 to 26.2 on the Noometry Index.

### How many benchmarks do Molmo 2 8b and Qwen3-1.7B share?

0 benchmarks have published results for both models. Molmo 2 8b has 5 scored results on Noometry and Qwen3-1.7B has 4.