Alibaba Cloud / Qwen Team model product
Qwen2.5-7B-Instruct is an instruction-tuned 7B parameter language model that excels at following instructions, generating long texts (over 8K tokens), understanding structured data, and generating structured outputs like JSON. The model features enhanced capabilities in mathematics, coding, and multilingual support across 29+ languages including Chinese, English, French, Spanish, and more.
Updated Aug 10, 2026. Default version: Qwen2.5 7B Instruct
Structured fields from the published default version.
This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.
Published benchmark records for the scored version Qwen2.5 7B Instruct.
| AlignBench | 0.7 | 3 | 4 | 33.3% | C | |
| MT-Bench | 0.9 | 5 | 12 | 63.6% | C | |
| MultiPL-E | 0.7 | 9 | 13 | 33.3% | C | |
| MBPP | 0.8 | 14 | 37 | 63.9% | C | |
| Arena Hard | 0.5 | 18 | 26 | 32.0% | C | |
| GSM8k | 0.9 | 22 | 48 | 55.3% | C | |
| MATH | 0.8 | 28 | 71 | 61.4% | C | |
| LiveBench | 0.4 | 37 | 38 | 2.7% | C | |
| HumanEval | 0.8 | 42 | 76 | 45.3% | C | |
| MMLU-Redux | 0.8 | 43 | 48 | 10.6% | C | |
| IFEval | 0.7 | 61 | 65 | 6.3% | C | |
| LiveCodeBench | 0.3 | 63 | 73 | 13.9% | C | |
| MMLU-Pro | 0.6 | 107 | 129 | 17.2% | C | |
| GPQA | 0.4 | 211 | 233 | 9.5% | C |
Preference and agent-evaluation signals from published Arena datasets.
The default version has no published Arena rows, or its source alias has not been resolved.
Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.
| NovitaAI | qwen/qwen2.5-7b-instruct | global | $0.07 | $0.07 | 32K | |
| Alibaba (China) | qwen2-5-7b-instruct | global | $0.072 | $0.144 | 131.1K | |
| OpenRouter | qwen/qwen-2.5-7b-instruct | global | $0.10 | $0.20 | 32.8K | |
| Alibaba | qwen2-5-7b-instruct | global | $0.175 | $0.70 | 131.1K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.
| Qwen2.5 7B Instruct | 32.4 | 7.6B | 131.1K | 8.2K | No | Apache 2.0 |
A concise description based on the published model registry.
Qwen2.5-7B-Instruct is an instruction-tuned 7B parameter language model that excels at following instructions, generating long texts (over 8K tokens), understanding structured data, and generating structured outputs like JSON. The model features enhanced capabilities in mathematics, coding, and multilingual support across 29+ languages including Chinese, English, French, Spanish, and more.
Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.
Data snapshot: 2026-08-07. Editorial model content is not available in the backend.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest published LLMBoard score.
Common questions about Qwen2.5 7B.
Qwen2.5 7B's default version was released on Sep 19, 2024.
Qwen2.5 7B's official API price is $0.175 per million input tokens and $0.70 per million output tokens via Alibaba. The lowest tracked third-party offer starts at $0.07 input and $0.07 output via NovitaAI.
Qwen2.5 7B is published under Alibaba Cloud / Qwen Team in the model registry.
The default version has a 131.1K token context window.
No. The default version is not marked as having publicly available weights.
4 published provider offerings are linked to the default version.
Nearby ranked alternatives include Claude Haiku 3, Qwen3 VL 8B Thinking, QwQ 32B.