Skip to main content

GPT-4o mini vs Qwen2.5 72B Instruct

SpecGPT-4o miniQwen2.5 72B Instruct
Respan Index10.7 (#171)10.0 (#173)
Blended price per 1M$0.262$0.37
Context window128K131K
Input / output per 1M$0.15 / $0.6$0.36 / $0.4
Max output16K8K
Inputtext, visiontext
Released2024-07-182024-09-19

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-4o miniQwen2.5 72B Instruct
Coding0.5 GPT-4o mini0.9 Qwen2.5 72B Instruct
Agents2.3 GPT-4o mini2.0 Qwen2.5 72B Instruct
Reasoning17.4 GPT-4o mini16.6 Qwen2.5 72B Instruct
Knowledge & language8.2 GPT-4o mini3.1* Qwen2.5 72B Instruct
Human preference32.5 GPT-4o mini32.2 Qwen2.5 72B Instruct

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

Benchmarks both report

Qwen2.5 72B Instruct leads on 4 of the 6 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkGPT-4o miniQwen2.5 72B Instruct
LMArena Elo13181303
GPQA Diamond40.2%49.1%
MATH Level 5 (Epoch AI)52.6%63.2%
OTIS Mock AIME 2024-2025 (Epoch AI)6.9%8.1%
WeirdML (Håvard Tveit Ihle)11.8%16%
BALROG (BALROG)17.4%16.2%

FAQ

Is GPT-4o mini better than Qwen2.5 72B Instruct?

GPT-4o mini scores 10.7 on the Respan Index (#171), ahead of Qwen2.5 72B Instruct at 10.0 (#173). Qwen2.5 72B Instruct leads on 4 of the 6 benchmarks both report.

Which is cheaper, GPT-4o mini or Qwen2.5 72B Instruct?

GPT-4o mini lists at $0.15 input and $0.6 output per 1M tokens; Qwen2.5 72B Instruct at $0.36 and $0.4. GPT-4o mini is 1.4x cheaper per token at list price.

Which has the larger context window?

GPT-4o mini accepts 128K tokens and Qwen2.5 72B Instruct 131K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.