Alibaba Cloud / Qwen Team model product
Qwen2 72B
Qwen2 72B is an instruction-tuned language model with 72 billion parameters and a context length of up to 131,072 tokens.
Updated Sep 8, 2026. Default version: Qwen2 72B Instruct
LLMBoard Score8.3Qwen2 72B Instruct
Coverage60%17 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
Qwen2 72B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Qwen2 72B Benchmark Results
Benchmark scores for Qwen2 72B Instruct.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkTheoremQA | Score44.40% | Rank01 | Participants6 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkCMMLU | Score90.10% | Rank02 | Participants6 | Percentile80.00% | EvidenceC | Evaluated |
| BenchmarkEvalPlus | Score0.79 points | Rank02 | Participants4 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkWinogrande | Score85.10% | Rank04 | Participants22 | Percentile85.71% | EvidenceC | Evaluated |
| BenchmarkBBH | Score82.40% | Rank07 | Participants12 | Percentile45.45% | EvidenceC | Evaluated |
| BenchmarkHellaSwag | Score87.60% | Rank08 | Participants27 | Percentile73.08% | EvidenceC | Evaluated |
| BenchmarkMultiPL-E | Score69.20% | Rank10 | Participants13 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkMBPP | Score80.20% | Rank13 | Participants33 | Percentile62.50% | EvidenceC | Evaluated |
| BenchmarkTruthfulQA | Score54.80% | Rank13 | Participants18 | Percentile29.41% | EvidenceC | Evaluated |
| BenchmarkC-Eval | Score83.80% | Rank14 | Participants18 | Percentile23.53% | EvidenceC | Evaluated |
| BenchmarkARC-C | Score68.90% | Rank24 | Participants34 | Percentile30.30% | EvidenceC | Evaluated |
| BenchmarkGSM8k | Score91.10% | Rank25 | Participants48 | Percentile48.94% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score86.00% | Rank32 | Participants66 | Percentile52.31% | EvidenceC | Evaluated |
| BenchmarkMATH | Score59.70% | Rank48 | Participants71 | Percentile32.86% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score82.30% | Rank49 | Participants101 | Percentile52.00% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score64.40% | Rank109 | Participants138 | Percentile21.17% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,261.27 rating | Rank194 | Participants210 | Percentile7.66% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,203.05 rating | Rank199 | Participants210 | Percentile5.26% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score42.40% | Rank212 | Participants247 | Percentile14.23% | EvidenceC | Evaluated |
Qwen2 72B Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext style control | Categoryjapanese | Rank162 | Rating / score1,175.15 | Votes901 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank166 | Rating / score1,110.98 | Votes901 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank169 | Rating / score1,171.25 | Votes1,167 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank170 | Rating / score1,082.38 | Votes1,167 | ObservationsN/A | Result date |
| Arenatext style control | Categoryfrench | Rank173 | Rating / score1,251.26 | Votes596 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank173 | Rating / score1,247.40 | Votes596 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank174 | Rating / score1,170.03 | Votes596 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank175 | Rating / score1,239.81 | Votes4,078 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank175 | Rating / score1,168.05 | Votes596 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank175 | Rating / score1,220.42 | Votes1,340 | ObservationsN/A | Result date |
| Arenatext style control | Categorymath | Rank175 | Rating / score1,273.19 | Votes4,835 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank176 | Rating / score1,298.97 | Votes4,078 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank177 | Rating / score1,150.54 | Votes1,340 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry mathematical | Rank178 | Rating / score1,275.26 | Votes4,235 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank182 | Rating / score1,234.79 | Votes4,835 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry mathematical | Rank183 | Rating / score1,230.64 | Votes4,235 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexpert | Rank190 | Rating / score1,260.33 | Votes1,763 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank192 | Rating / score1,274.83 | Votes2,067 | ObservationsN/A | Result date |
| Arenatext style control | Categoryenglish | Rank193 | Rating / score1,275.52 | Votes19,928 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts | Rank193 | Rating / score1,272.89 | Votes10,780 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts english | Rank193 | Rating / score1,283.35 | Votes6,483 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank193 | Rating / score1,221.06 | Votes5,791 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank194 | Rating / score1,297.00 | Votes6,249 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank194 | Rating / score1,222.24 | Votes5,504 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexclude ties | Rank194 | Rating / score1,170.71 | Votes23,757 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank194 | Rating / score1,243.65 | Votes6,698 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank194 | Rating / score1,261.27 | Votes37,325 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank195 | Rating / score1,171.26 | Votes1,763 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts english | Rank195 | Rating / score1,205.91 | Votes6,483 | ObservationsN/A | Result date |
| Arenatext | Categorymulti turn | Rank195 | Rating / score1,195.69 | Votes6,698 | ObservationsN/A | Result date |
Qwen2 72B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 0
No provider prices
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Qwen2 72B Runtime Performance
Provider-specific output speed and catalog latency for Qwen2 72B Instruct. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Qwen2 72B Specifications
Technical details for the model's default version.
- Version
- Qwen2 72B Instruct
- Released
- Jul 23, 2024
- Knowledge cutoff
- Unknown
- Parameters
- 72B
- Context window
- N/A
- Max output
- N/A
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- tongyi-qianwen
Qwen2 72B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionQwen2 72B Instruct | Released | LLMBoard8.33 | Parameters72B | ContextN/A | Max outputN/A | Open weightsYes | Licensetongyi-qianwen |
Models similar to Qwen2 72B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
Qwen2.5 Omni 7B
Alibaba Cloud / Qwen Team
AC
Qwen2.5 14B
Alibaba Cloud / Qwen Team
AC
Qwen2.5 VL 7B
Alibaba Cloud / Qwen Team
AC
Qwen2.5 7B
Alibaba Cloud / Qwen Team
AC
Qwen2.5 32B
Alibaba Cloud / Qwen Team
AC
Qwen2.5 Coder 32B
Alibaba Cloud / Qwen Team
What is Qwen2 72B?
Key information about Qwen2 72B and its available data.
Qwen2 72B is part of the Qwen2 series and is based on Qwen2-72B-Instruct, an instruction-tuned language model with 72 billion parameters. It supports context lengths of up to 131,072 tokens.
Data as of 2026-09-08.
FAQ
Common questions about Qwen2 72B.
When was Qwen2 72B released?
Qwen2 72B's default version was released on Jul 23, 2024.
How much does Qwen2 72B cost?
No official standard PAYG price is currently available for Qwen2 72B.
Who created Qwen2 72B?
Qwen2 72B was created by Alibaba Cloud / Qwen Team.
What is the context window for Qwen2 72B?
A context window is not available for the default version.
Is Qwen2 72B open weight?
Yes. The default version is marked as open weight under tongyi-qianwen.
How many API providers offer Qwen2 72B?
No provider offering is currently linked to the default version.