BenchLeader

Qwen2.5 72B

Quality#230 of 333
43.1Index
Below the median
−6.9 on the median
Price#81 of 249
$0.485per 1M tokens
Cheaper than most
0.6× the median
Speed#208 of 215
23tokens/s
Bottom quarter
0.3× the median

44 cheaper ranked models score higher: GPT-5.6 Luna (58.5, $0.450), Inkling 2 Small (58.4, $0.475), Claude Haiku 5.5 (57.3, $0.200) and 41 more.

As of 8 Nov 2026, Qwen2.5 72B by Alibaba scores 43.1 on the BenchLeader Index (593 ranked configurations), with its best results in instruction following (46) and weakest in coding (37). API pricing: $0.480 per 1M input tokens and $0.500 per 1M output tokens ($0.485 blended at 3:1), list price on 8 Nov 2026. It streams about 23 tokens/s (Artificial Analysis). Released 19 Sep 2024.

Key facts (as of 8 Nov 2026)

  • Qwen2.5 72B API pricing: $0.480 per 1M input tokens and $0.500 per 1M output tokens ($0.485 blended at 3:1) (list price, 8 Nov 2026).
  • Qwen2.5 72B streams about 23 tokens/s (Artificial Analysis, 8 Nov 2026).
  • Qwen2.5 72B was released on 19 Sep 2024 (Alibaba).

In detail. Qwen2.5 72B is an Alibaba open-weights model, released 19 Sep 2024. Its best configuration ranks #473 of 593 on the BenchLeader Index at 43.1 ±4.5, in the lower half. The ± is the point: 205 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in instruction following (46) and lowest in coding (37). At $0.485 per million tokens blended it is cheaper than most ranked models. Output speed of 23 tokens per second puts it in the slowest quarter, with a first answer in 4.7 s. Last measured 6 Nov 2026.

Blended price
$0.485/M
$0.480 in · $0.500 out
via Artificial Analysis
Output speed
23 tok/s
measured by Artificial Analysis
First answer
4.65 s
first token 3.49 s
Context
33k
via models.dev
Full answer
–
Cost per task
–
Tokens per task
–
Released
19 Sep 2024
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index43
  2. Reasoning40
  3. Coding37
  4. Agents & tools38
  5. Maths44
  6. Instruction following46
  7. Human preference45

Get an email when Alibaba ships a new model

And once when it gets ranked, plus the weekly review on Mondays.

Choose providers and emails

How its index has moved

8 Sep 2026 to 8 Nov 2026
384348

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Coding

Benchmarknot statedSourceTrend
WeirdML16.0%#148WeirdML
Arena Coding1355#248Arena (LMArena)
LiveCodeBench (AA)not in index27.6%#215Artificial Analysis

Agents & tools

Benchmarknot statedSourceTrend
Terminal-Bench Hard4.5%#289Artificial Analysis
τ²-Bench Telecom (AA)not in index34.5%#243Artificial Analysis
BALROGnot in index16.2%#29BALROG
TheAgentCompanynot in index5.7%#11TheAgentCompany
METR Time Horizonsnot in index35.8%#34METR

Knowledge

Benchmarknot statedSourceTrend
MMLU-Pro (HELM)not in index63.1%#44HELM Capabilities
MMLUnot in index85.3%#8Epoch AI Benchmarking Hub
TriviaQAnot in index71.9%#27Epoch AI Benchmarking Hub

Instruction following

Human preference

Benchmarknot statedSourceTrend
Arena Text1303#263Arena (LMArena)
Arena Creative Writingnot in index1254#272Arena (LMArena)
Arena Multi-turnnot in index1299#250Arena (LMArena)
Arena Longer Queriesnot in index1317#253Arena (LMArena)

Composite

Safety & honesty

Benchmarknot statedSourceTrend
FORTRESSnot in index56.4%#8Scale AI SEAL

API pricing: where to run it

Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.

ProviderSpeedFirst tokenInput $/MOutput $/MContextQuantisation
DeepInfra13 tok/s3.49 s$0.360$0.40033kfp8

Price history

The price above, per 1M tokens, every day it changed.

$0.00$0.473$0.947$1.42$1.89Sep 26Oct 26Nov 26
input outputnow $0.480 in · $0.500 out

What a task costs

Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.

WorkloadTokens in / outCostWith cachingTime
Chat reply400 / 300$0.0003–17.7 s
Summarize a 30-page report12,000 / 600$0.0061–30.8 s
Code edit6,000 / 1,500$0.0036–1.2 min
Agentic coding session60,000 / 4,000$0.031–3.0 min
Structured extraction2,000 / 200$0.0011–13.4 s

More from Alibaba

New this month

See also

Embed or cite

Show where Qwen2.5 72B ranks on a model card or README. The badge redraws itself with every daily update, carries the data date and links back to this page. To see ranks like this on OpenRouter and Hugging Face model pages, get the Chrome extension.

[![Qwen2.5 72B on BenchLeader: #224 overall](https://www.benchleader.com/badge/qwen2-5-72b.svg)](https://www.benchleader.com/models/qwen2-5-72b)

Cite this

The ranking changes daily, so a reference carries the data date. APA style:

BenchLeader. (2026, November 8). Qwen2.5 72B on the BenchLeader Index (method v1.4) [Data set]. Retrieved November 8, 2026, from https://www.benchleader.com/models/qwen2-5-72b

BibTeX:

@misc{benchleader_qwen2_5_72b_20261108,
  author       = {{BenchLeader}},
  title        = {{Qwen2.5 72B on the BenchLeader Index (method v1.4)}},
  year         = {2026},
  month        = nov,
  howpublished = {\url{https://www.benchleader.com/models/qwen2-5-72b}},
  note         = {Data as of 2026-11-08}
}

Every badge style, the embeddable top-10 widget and how to cite the Index

Questions people ask

What are Qwen2.5 72B's benchmark scores?
As of 8 Nov 2026, Qwen2.5 72B scores 43.1 ±4.5 on the BenchLeader Index, strongest in instruction following (46) and weakest in coding (37). That rests on independent benchmark results only, and every score on this page links to its publisher.
How does Qwen2.5 72B rank?
Qwen2.5 72B is #473 of 593 ranked configurations on 8 Nov 2026. 205 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 69.4.
How much does Qwen2.5 72B cost per 1M tokens?
As of 8 Nov 2026, Qwen2.5 72B costs $0.480 per 1M input tokens and $0.500 per 1M output tokens, $0.485 blended (three input tokens per output token). The list price last changed on 9 Sep 2026.
When was Qwen2.5 72B released?
Alibaba released Qwen2.5 72B on 19 Sep 2024.

Data as of 8 Nov 2026. Compare with another model.

Cite as: BenchLeader, “Qwen2.5 72B: benchmarks, pricing, speed and rank”, data as of 8 Nov 2026, https://www.benchleader.com/models/qwen2-5-72b.