Alibaba Cloud / Qwen Team model product
Qwen2.5 7B
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.
Updated Aug 17, 2026. Default version: Qwen2.5 7B Instruct
LLMBoard Score5.7Qwen2.5 7B Instruct
Coverage100%14 benchmark families
Context window131.1KTokens
Official input price$0.175Alibaba API
Qwen2.5 7B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Qwen2.5 7B Benchmark Results
Benchmark scores for Qwen2.5 7B Instruct.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAlignBench | Score73.3% | Rank03 | Participants4 | Percentile33.3% | EvidenceC | Evaluated |
| BenchmarkMT-Bench | Score87.5% | Rank05 | Participants12 | Percentile63.6% | EvidenceC | Evaluated |
| BenchmarkMultiPL-E | Score70.4% | Rank09 | Participants13 | Percentile33.3% | EvidenceC | Evaluated |
| BenchmarkMBPP | Score79.2% | Rank14 | Participants33 | Percentile59.4% | EvidenceC | Evaluated |
| BenchmarkArena Hard | Score52.0% | Rank18 | Participants26 | Percentile32.0% | EvidenceC | Evaluated |
| BenchmarkGSM8k | Score91.6% | Rank22 | Participants48 | Percentile55.3% | EvidenceC | Evaluated |
| BenchmarkMATH | Score75.5% | Rank28 | Participants71 | Percentile61.4% | EvidenceC | Evaluated |
| BenchmarkLiveBench | Score35.9% | Rank37 | Participants38 | Percentile2.7% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score84.8% | Rank38 | Participants66 | Percentile43.1% | EvidenceC | Evaluated |
| BenchmarkMMLU-Redux | Score75.4% | Rank43 | Participants48 | Percentile10.6% | EvidenceC | Evaluated |
| BenchmarkIFEval | Score71.2% | Rank63 | Participants67 | Percentile6.1% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score28.7% | Rank65 | Participants75 | Percentile13.5% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score56.3% | Rank111 | Participants134 | Percentile17.3% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score36.4% | Rank217 | Participants239 | Percentile9.2% | EvidenceC | Evaluated |
Qwen2.5 7B Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Qwen2.5 7B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.175 input, $0.70 output per 1M
- Official provider
- Alibaba
- Lowest third-party
- From $0.07 input, $0.07 output per 1M via NovitaAI
- Tracked offerings
- 4
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderNovitaAI | Provider model IDqwen/qwen2.5-7b-instruct | Regionglobal | Input / 1M$0.07 | Output / 1M$0.07 | Context32K | Updated |
| ProviderAlibaba (China) | Provider model IDqwen2-5-7b-instruct | Regionglobal | Input / 1M$0.072 | Output / 1M$0.144 | Context131.1K | Updated |
| ProviderOpenRouter | Provider model IDqwen/qwen-2.5-7b-instruct | Regionglobal | Input / 1M$0.10 | Output / 1M$0.20 | Context32.8K | Updated |
| ProviderAlibaba | Provider model IDqwen2-5-7b-instruct | Regionglobal | Input / 1M$0.175 | Output / 1M$0.70 | Context131.1K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Qwen2.5 7B Runtime Performance
Provider-specific output speed and catalog latency for Qwen2.5 7B Instruct. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderTogether | Output Speed138 tok/s | Catalog Latency0.5 s | Max Input131.1K | Max Output8.2K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Qwen2.5 7B Specifications
Technical details for the model's default version.
- Version
- Qwen2.5 7B Instruct
- Released
- Sep 19, 2024
- Knowledge cutoff
- Unknown
- Parameters
- 7.6B
- Context window
- 131.1K
- Max output
- 8.2K
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- Apache 2.0
Qwen2.5 7B 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 |
|---|
| VersionQwen2.5 7B Instruct | Released | LLMBoard5.7 | Parameters7.6B | Context131.1K | Max output8.2K | Open weightsNo | LicenseApache 2.0 |
Qwen2.5 7B vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Qwen2.5 7B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
Qwen2.5 Coder 32B
Alibaba Cloud / Qwen Team
AC
Qwen2.5 14B
Alibaba Cloud / Qwen Team
AC
Qwen3.5 2B
Alibaba Cloud / Qwen Team
AC
Qwen2 72B
Alibaba Cloud / Qwen Team
AC
Qwen2.5 Omni 7B
Alibaba Cloud / Qwen Team
AC
Qwen3.5 0.8B
Alibaba Cloud / Qwen Team
What is Qwen2.5 7B?
Key information about Qwen2.5 7B and its available data.
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.
Data as of 2026-08-17.
FAQ
Common questions about Qwen2.5 7B.
When was Qwen2.5 7B released?
Qwen2.5 7B's default version was released on Sep 19, 2024.
How much does Qwen2.5 7B cost?
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.
Who created Qwen2.5 7B?
Qwen2.5 7B was created by Alibaba Cloud / Qwen Team.
What is the context window for Qwen2.5 7B?
The default version has a 131.1K token context window.
Is Qwen2.5 7B open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Qwen2.5 7B?
4 provider offerings are linked to the default version.
What models should I compare Qwen2.5 7B with?
Nearby ranked alternatives include LFM2.5 VL 3B, Mistral Large 2, Phi 4 multimodal.