# Qwen2.5 VL 72B Instruct

Qwen2.5 VL 72B Instruct costs $0.80 per million input tokens and $1.00 per million output tokens, as of October 21, 2026. None of the 6 coding benchmarks behind the index has measured it, so it has no coding index, but 5 benchmarks outside the index have a result below.

Page: https://llmbenchmark.ai/models/qwen2-5-vl-72b-instruct
Data from October 21, 2026. Every figure below names the board it was read from and the day.

- Maker: Qwen
- Released: February 1, 2025
- Price per million input tokens: $0.80
- Price per million output tokens: $1.00
- Context window: 128K tokens

Benchmark results (5 of 190):

- GeoBench: 62.0% (source: Epoch AI benchmarking hub, read October 21, 2026)
- OSWorld: 5.0% (source: Epoch AI benchmarking hub, read October 21, 2026)
- LMArena Vision: 1107 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Vision: English: 1115 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Vision: Chinese: 1107 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)