Skip to content
llmwaves

Qwen2.5 72B Instruct

Qwen · released Sep 19, 2024

Open weightsTool useStructured output

Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...

Specification

Context window
33K
Max output
16K
Knowledge cutoff
Jun 30, 2024
Parameters
72.7B
Licence
other
Serving providers
2
Moderated
No
Uptime
99.6%

Intelligence

9.4

34th percentile

Coding

Coding Index

Agentic

Agentic Index

Output speed

30 t/s

Median across providers

Latency

285ms

Time to first token

Cost per task

$0.03

Estimated

Benchmarks

Where the score comes from

The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.

Evaluation scores

Percentage correct · higher is better

  • MMLU-Pro
    72.0%
  • GPQA Diamond
    49.1%
  • IFBench
    36.9%
  • τ²-bench (Telecom)
    34.5%
  • LiveCodeBench
    27.6%
  • SciCode
    26.7%
  • AA-LCR (long context)
    20.0%
  • AIME 2025
    14.0%
  • Terminal-Bench Hard
    4.5%
  • Humanity's Last Exam
    3.6%

An evaluation missing from this list was not run for this model — it is not a zero.

View as table
EvaluationScore
MMLU-Pro72.0%
GPQA Diamond49.1%
IFBench36.9%
τ²-bench (Telecom)34.5%
LiveCodeBench27.6%
SciCode26.7%
AA-LCR (long context)20.0%
AIME 202514.0%
Terminal-Bench Hard4.5%
Humanity's Last Exam3.6%

Against its peers

Intelligence Index · this model highlighted, nearest peers in grey

Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.

View as table
ModelIntelligence
Llama 4 Scout10.3
Qwen3 VL 30B A3B Instruct9.9
R1 Distill Llama 70B9.8
GPT-4.1 Nano9.6
Qwen2.5 72B Instruct9.4
Sonar9.4
GPT-4o (2024-08-06)9.4
Sonar Pro9.1

Percentile among all indexed models

Intelligence34th
Mathematics17th
Terminal work28th

Pricing

What it costs to run

List prices per million tokens, plus what one representative task works out to.

List price

Input / 1M tokens
$0.36
Output / 1M tokens
$0.4
Cached input / 1M
Not offered
Blended 3:1
$0.37

One task, estimated

$0.03

Input tokens
50,000
Output tokens
25,000
Profile
Standard

Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).

Serving providers

Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.