Compare AI models

Specifications
Parameters
1.5B/7B/72B397B
Context window
4k1M
API pricing
Input price
—$0.40International (Singapore)
Output price
—$2.40
Cheapest input
—$0.26Alibaba
Cheapest output
—$1.56Alibaba
—$130Alibaba
These models have no shared benchmark scores.
Overview
CompanyQwenQwen
Release dateSep 19 2024Feb 16 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Math and Qwen3.5-Plus don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only Qwen3.5-Plus has a verified first-party price for an available API: $0.40 per million input tokens and $2.40 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen2.5-Math. The listed Qwen3.5-Plus rates use the “International (Singapore)” pricing scope. Qwen2.5-Math shipped 515 days before Qwen3.5-Plus, so benchmark comparisons should account for the intervening progress.

Qwen2.5-Math has 1.5B/7B/72B parameters, while Qwen3.5-Plus has 397B. Context windows are 4k (Qwen2.5-Math) vs 1M (Qwen3.5-Plus). Qwen2.5-Math is open weight, while Qwen3.5-Plus is closed.

Direct benchmark comparisons are unavailable — Qwen2.5-Math and Qwen3.5-Plus don't publish scores on any of the same benchmarks.