Skip to main content

Llama 3.2 1B Instruct vs Qwen2.5 72B Instruct

SpecLlama 3.2 1B InstructQwen2.5 72B Instruct
Respan Index5.3 (#176)10.0 (#173)
Blended price per 1M$0.02$0.37
Context window128K131K
Input / output per 1M$0.02 / $0.02$0.36 / $0.4
Max output-8K
Inputtexttext
Released2024-09-252024-09-19

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.

CategoryLlama 3.2 1B InstructQwen2.5 72B Instruct
Coding0.0* Llama 3.2 1B Instruct0.9 Qwen2.5 72B Instruct
Agents0.2 Llama 3.2 1B Instruct2.0 Qwen2.5 72B Instruct
Reasoning12.5 Llama 3.2 1B Instruct16.6 Qwen2.5 72B Instruct
Knowledge & language0.3* Llama 3.2 1B Instruct3.1* Qwen2.5 72B Instruct
Human preference13.8 Llama 3.2 1B Instruct32.2 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 4 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkLlama 3.2 1B InstructQwen2.5 72B Instruct
LMArena Elo11111303
GPQA Diamond23.9%49.1%
OTIS Mock AIME 2024-2025 (Epoch AI)0.6%8.1%
BALROG (BALROG)6.6%16.2%

FAQ

Is Llama 3.2 1B Instruct better than Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct scores 10.0 on the Respan Index (#173), ahead of Llama 3.2 1B Instruct at 5.3 (#176). Qwen2.5 72B Instruct leads on 4 of the 4 benchmarks both report.

Which is cheaper, Llama 3.2 1B Instruct or Qwen2.5 72B Instruct?

Llama 3.2 1B Instruct lists at $0.02 input and $0.02 output per 1M tokens; Qwen2.5 72B Instruct at $0.36 and $0.4. Llama 3.2 1B Instruct is 19x cheaper per token at list price.

Which has the larger context window?

Llama 3.2 1B Instruct accepts 128K tokens and Qwen2.5 72B Instruct 131K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.