# Qwen2.5-VL 72B Instruct vs Qwen3 Coder Next

> Qwen3 Coder Next is the stronger model overall, scoring 33.8 to 29.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen2-5-vl-72b-instruct-vs-qwen3-coder-next
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- Qwen3 Coder Next is cheaper at $0.12 / $0.80 per million input/output tokens, against $2.80 / $8.40 for Qwen2.5-VL 72B Instruct.
- Qwen3 Coder Next accepts more context: 262K tokens versus 131K.

## Snapshot

| | Qwen2.5-VL 72B Instruct | Qwen3 Coder Next |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 29.4 | 33.8 |
| Rank | 298 | 229 |
| Context | 131K | 262K |
| Input $/M | $2.80 | $0.12 |
| Output $/M | $8.40 | $0.80 |
| Weights | Open | Open |

## Coding

- Qwen2.5-VL 72B Instruct: —
- Qwen3 Coder Next: 35.8 (#206)

| Benchmark | Qwen2.5-VL 72B Instruct | Qwen3 Coder Next |
|---|---|---|
| SciCode | — | 32.3% |
| WeirdML | — | 34.4% |

## Agentic & Tool Use

- Qwen2.5-VL 72B Instruct: 18.4 (#136)
- Qwen3 Coder Next: —

| Benchmark | Qwen2.5-VL 72B Instruct | Qwen3 Coder Next |
|---|---|---|
| OSWorld | 5% | — |

## Reasoning

- Qwen2.5-VL 72B Instruct: 20.0 (#228)
- Qwen3 Coder Next: 21.7 (#191)

| Benchmark | Qwen2.5-VL 72B Instruct | Qwen3 Coder Next |
|---|---|---|
| Kagi LLM Benchmark | 36% | — |
| CritPt | — | 0% |

## Multimodal

- Qwen2.5-VL 72B Instruct: 32.9 (#92)
- Qwen3 Coder Next: —

| Benchmark | Qwen2.5-VL 72B Instruct | Qwen3 Coder Next |
|---|---|---|
| LMArena Vision | 1107 | — |
| Video-MME | 73.5% | — |
| GeoBench | 62% | — |
| SpatialViz-Bench | 33.3% | — |

## FAQ

### Is Qwen2.5-VL 72B Instruct better than Qwen3 Coder Next?

Qwen3 Coder Next is the stronger model overall, scoring 33.8 to 29.4 on the Noometry Index.

### Which is cheaper, Qwen2.5-VL 72B Instruct or Qwen3 Coder Next?

Qwen3 Coder Next is cheaper. It lists at $0.12 per million input tokens and $0.80 per million output tokens; Qwen2.5-VL 72B Instruct lists at $2.80 and $8.40.

### Which has the bigger context window?

Qwen3 Coder Next does, with 262K tokens against 131K.

### How many benchmarks do Qwen2.5-VL 72B Instruct and Qwen3 Coder Next share?

0 benchmarks have published results for both models. Qwen2.5-VL 72B Instruct has 6 scored results on Noometry and Qwen3 Coder Next has 3.