# Pixtral Large vs Qwen3-1.7B

> Pixtral Large is the stronger model overall, scoring 31.7 to 26.2 on the Noometry Index.

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

## Snapshot

| | Pixtral Large | Qwen3-1.7B |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.7 | 26.2 |
| Rank | 257 | 331 |
| Context | 128K | — |
| Input $/M | $2 | — |
| Output $/M | $6 | — |
| Weights | Open | Open |

## Agentic & Tool Use

- Pixtral Large: —
- Qwen3-1.7B: 24.5 (#108)

| Benchmark | Pixtral Large | Qwen3-1.7B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.4% |

## Reasoning

- Pixtral Large: 20.9 (#208)
- Qwen3-1.7B: 18.5 (#263)

| Benchmark | Pixtral Large | Qwen3-1.7B |
|---|---|---|
| Chess Puzzles | — | 0% |
| EnigmaEval | 0.8% | — |

## Math

- Pixtral Large: —
- Qwen3-1.7B: 15.4 (#288)

| Benchmark | Pixtral Large | Qwen3-1.7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 8.1% |

## Knowledge

- Pixtral Large: —
- Qwen3-1.7B: 19.6 (#273)

| Benchmark | Pixtral Large | Qwen3-1.7B |
|---|---|---|
| GPQA Diamond | — | 38% |

## Multimodal

- Pixtral Large: 30.0 (#105)
- Qwen3-1.7B: —

| Benchmark | Pixtral Large | Qwen3-1.7B |
|---|---|---|
| LMArena Vision | 1089 | — |

## Writing & Preference

- Pixtral Large: 32.9 (#273)
- Qwen3-1.7B: —

| Benchmark | Pixtral Large | Qwen3-1.7B |
|---|---|---|
| EQ-Bench Creative Writing | 988 | — |

## FAQ

### Is Pixtral Large better than Qwen3-1.7B?

Pixtral Large is the stronger model overall, scoring 31.7 to 26.2 on the Noometry Index.

### How many benchmarks do Pixtral Large and Qwen3-1.7B share?

0 benchmarks have published results for both models. Pixtral Large has 3 scored results on Noometry and Qwen3-1.7B has 4.