Skip to main content

Phi-4 vs Qwen2.5 72B Instruct

SpecPhi-4Qwen2.5 72B Instruct
Respan Index9.2 (#174)10.0 (#173)
Blended price per 1M$0.088$0.37
Context window16K131K
Input / output per 1M$0.07 / $0.14$0.36 / $0.4
Max output16K8K
Inputtexttext
Released2024-12-122024-09-19

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.

CategoryPhi-4Qwen2.5 72B Instruct
Coding0.6* Phi-40.9 Qwen2.5 72B Instruct
Agents0.9 Phi-42.0 Qwen2.5 72B Instruct
Reasoning17.2 Phi-416.6 Qwen2.5 72B Instruct
Knowledge & language4.9 Phi-43.1* Qwen2.5 72B Instruct
Human preference27.1 Phi-432.2 Qwen2.5 72B Instruct

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

Benchmarks both report

Phi-4 leads on 3 of the 5 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkPhi-4Qwen2.5 72B Instruct
LMArena Elo12561303
GPQA Diamond56.1%49.1%
MATH Level 5 (Epoch AI)64.9%63.2%
OTIS Mock AIME 2024-2025 (Epoch AI)13.8%8.1%
BALROG (BALROG)11.6%16.2%

FAQ

Is Phi-4 better than Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct scores 10.0 on the Respan Index (#173), ahead of Phi-4 at 9.2 (#174). Phi-4 leads on 3 of the 5 benchmarks both report.

Which is cheaper, Phi-4 or Qwen2.5 72B Instruct?

Phi-4 lists at $0.07 input and $0.14 output per 1M tokens; Qwen2.5 72B Instruct at $0.36 and $0.4. Phi-4 is 4.2x cheaper per token at list price.

Which has the larger context window?

Phi-4 accepts 16K tokens and Qwen2.5 72B Instruct 131K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.