Skip to main content

Qwen2.5 72B Instruct vs Qwen3.8-Max

SpecQwen2.5 72B InstructQwen3.8-Max
Respan Index10.0 (#173)52.8 (#35)
Blended price per 1M$0.37$2.48
Context window131K1M
Input / output per 1M$0.36 / $0.4$1.65 / $4.95
Max output8K131K
Inputtexttext, vision
Released2024-09-192026-08-02

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryQwen2.5 72B InstructQwen3.8-Max
Coding0.9 Qwen2.5 72B Instruct39.3 Qwen3.8-Max
Agents2.0 Qwen2.5 72B Instruct68.6 Qwen3.8-Max
Reasoning16.6 Qwen2.5 72B Instruct49.4 Qwen3.8-Max
Knowledge & language3.1* Qwen2.5 72B Instruct48.1 Qwen3.8-Max
Human preference32.2 Qwen2.5 72B Instruct58.0 Qwen3.8-Max

* Estimated: no published scores in that category. How the Respan Index works

Benchmarks both report

Qwen3.8-Max leads on 3 of the 3 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkQwen2.5 72B InstructQwen3.8-Max
LMArena Elo13031484
GPQA Diamond49.1%92.6%
OTIS Mock AIME 2024-2025 (Epoch AI)8.1%100%

FAQ

Is Qwen2.5 72B Instruct better than Qwen3.8-Max?

Qwen3.8-Max scores 52.8 on the Respan Index (#35), ahead of Qwen2.5 72B Instruct at 10.0 (#173). Qwen3.8-Max leads on 3 of the 3 benchmarks both report.

Which is cheaper, Qwen2.5 72B Instruct or Qwen3.8-Max?

Qwen2.5 72B Instruct lists at $0.36 input and $0.4 output per 1M tokens; Qwen3.8-Max at $1.65 and $4.95. Qwen2.5 72B Instruct is 6.7x cheaper per token at list price.

Which has the larger context window?

Qwen2.5 72B Instruct accepts 131K tokens and Qwen3.8-Max 1M tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.