Qwen2.5 72B
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
- Overall index43
- Reasoning40
- Coding37
- Agents & tools38
- Maths44
- Instruction following46
- Human preference45
How its index has moved
8 Sep 2026 to 8 Nov 2026The 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.
Reasoning
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| GPQA Diamond | 49.1%#228 | Epoch AI Benchmarking Hub | |
| Arena Hard Prompts | 1317#255 | Arena (LMArena) | |
| GPQA Diamond (AA)not in index | 49.1%#440 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 3.6%#604 | Artificial Analysis | |
| GPQA Diamond (HELM)not in index | 42.6%#44 | HELM Capabilities | |
| CritPtnot in index | 0.0%#329 | Artificial Analysis | |
| LMCAnot in index | 13.4%#177 | Epoch AI Benchmarking Hub | |
| DTBenchnot in index | 62.9%#175 | Epoch AI Benchmarking Hub | |
| ForecastBenchnot in index | 61.6%#63 | ForecastBench | |
| HellaSwagnot in index | 84.8%#11 | Epoch AI Benchmarking Hub | |
| BIG-Bench Hardnot in index | 79.8%#6 | Epoch AI Benchmarking Hub | |
| WinoGrandenot in index | 82.3%#11 | Epoch AI Benchmarking Hub | |
| ARC (AI2 Challenge)not in index | 94.5%#3 | Epoch AI Benchmarking Hub | |
| PIQAnot in index | 82.6%#18 | Epoch AI Benchmarking Hub |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| WeirdML | 16.0%#148 | WeirdML | |
| Arena Coding | 1355#248 | Arena (LMArena) | |
| LiveCodeBench (AA)not in index | 27.6%#215 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Terminal-Bench Hard | 4.5%#289 | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 34.5%#243 | Artificial Analysis | |
| BALROGnot in index | 16.2%#29 | BALROG | |
| TheAgentCompanynot in index | 5.7%#11 | TheAgentCompany | |
| METR Time Horizonsnot in index | 35.8%#34 | METR |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| OTIS Mock AIME | 8.1%#243 | Epoch AI Benchmarking Hub | |
| MATH Level 5 | 63.2%#46 | Epoch AI Benchmarking Hub | |
| Omni-MATH (HELM) | 33.0%#38 | HELM Capabilities | |
| Arena Maths | 1296#236 | Arena (LMArena) |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| MMLU-Pro (HELM)not in index | 63.1%#44 | HELM Capabilities | |
| MMLUnot in index | 85.3%#8 | Epoch AI Benchmarking Hub | |
| TriviaQAnot in index | 71.9%#27 | Epoch AI Benchmarking Hub |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| IFBench | 36.9%#300 | Artificial Analysis | |
| IFEval (HELM) | 80.6%#46 | HELM Capabilities | |
| WildBench (HELM) | 80.2%#31 | HELM Capabilities | |
| Arena Instruction Followingnot in index | 1292#254 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 1303#263 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1254#272 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1299#250 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1317#253 | Arena (LMArena) |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Epoch Capabilities Indexnot in index | 127.3#148 | Epoch AI Benchmarking Hub | |
| AA Intelligence Index v4.3.2not in index | 7.7#470 | Artificial Analysis | |
| AA Progress Index v1not in index | 164.4#519 | Artificial Analysis | |
| HELM Capabilities meannot in index | 59.9%#44 | HELM Capabilities |
Safety & honesty
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| FORTRESSnot in index | 56.4%#8 | Scale 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.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| DeepInfra | 13 tok/s | 3.49 s | $0.360 | $0.400 | 33k | fp8 |
Price history
The price above, per 1M tokens, every day it changed.
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.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0003 | – | 17.7 s |
| Summarize a 30-page report | 12,000 / 600 | $0.0061 | – | 30.8 s |
| Code edit | 6,000 / 1,500 | $0.0036 | – | 1.2 min |
| Agentic coding session | 60,000 / 4,000 | $0.031 | – | 3.0 min |
| Structured extraction | 2,000 / 200 | $0.0011 | – | 13.4 s |
More from Alibaba
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.
[](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.