Skip to main content

GPT-5 mini vs Qwen3 235B-A22B Instruct 2507

SpecGPT-5 miniQwen3 235B-A22B Instruct 2507
Respan Index20.0 (#129)20.2 (#127)
Blended price per 1M$0.688$0.205
Context window400K262K
Input / output per 1M$0.25 / $2$0.09 / $0.55
Max output128K-
Inputtext, visiontext
Released2025-08-072025-07-21

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.

CategoryGPT-5 miniQwen3 235B-A22B Instruct 2507
Coding9.1 GPT-5 mini4.7 Qwen3 235B-A22B Instruct 2507
Agents4.3 GPT-5 mini17.9* Qwen3 235B-A22B Instruct 2507
Reasoning31.5 GPT-5 mini22.6* Qwen3 235B-A22B Instruct 2507
Knowledge & language21.6 GPT-5 mini16.3 Qwen3 235B-A22B Instruct 2507
Human preference43.9 GPT-5 mini48.5 Qwen3 235B-A22B Instruct 2507

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

Benchmarks both report

They split the 2 benchmarks both report evenly. Higher is better. Each score links to where it was published.

BenchmarkGPT-5 miniQwen3 235B-A22B Instruct 2507
LMArena Elo13901422
WeirdML (Håvard Tveit Ihle)52.7%38.7%

FAQ

Is GPT-5 mini better than Qwen3 235B-A22B Instruct 2507?

Qwen3 235B-A22B Instruct 2507 scores 20.2 on the Respan Index (#127), ahead of GPT-5 mini at 20.0 (#129). They split the 2 benchmarks both report evenly.

Which is cheaper, GPT-5 mini or Qwen3 235B-A22B Instruct 2507?

GPT-5 mini lists at $0.25 input and $2 output per 1M tokens; Qwen3 235B-A22B Instruct 2507 at $0.09 and $0.55. Qwen3 235B-A22B Instruct 2507 is 3.4x cheaper per token at list price.

Which has the larger context window?

GPT-5 mini accepts 400K tokens and Qwen3 235B-A22B Instruct 2507 262K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.