Qwen3 Max (Preview)
Qwen3 Max (Preview) is an AI model published by Alibaba, released on 2025-09-05, for Chat model, and 256K context length, with a 84.20 score on τ²-Bench - Telecom.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Model basics
Open source & experience
Official resources
API details
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | - | ¥0.0032/ 1K tokens | ¥0.013/ 1K tokens |
| Text | Context > 32768 | ¥0.0064/ 1K tokens | ¥0.026/ 1K tokens |
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | - | ¥0.0016/ 1K tokens | ¥0.0064/ 1K tokens |
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | Context <= 32000 | $1.20/ 1M tokens | $6.00/ 1M tokens |
| Text | Context > 32000, Context <= 128000 | $2.40/ 1M tokens | $12.00/ 1M tokens |
| Text | Context > 128000, Context <= 256000 | $3.00/ 1M tokens | $15.00/ 1M tokens |
“—” means the modality is not billed in that direction, or the vendor has not published a price for it.
Benchmark Results
Qwen3 Max (Preview) currently shows benchmark results led by MMLU Pro (40 / 176, score 84), τ²-Bench - Telecom (96 / 264, score 84.20), AIME2025 (97 / 215, score 80.60). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.
Coding and Software Engineer
2 evaluationsAgent Level Benchmark
3 evaluationsPublisher
Model Overview
Qwen3 Max (Preview) is an AI model published by Alibaba, released on 2025-09-05, for Chat model, and 256K context length, with a 84.20 score on τ²-Bench - Telecom.
DataLearner on WeChat
Follow DataLearner on WeChat for AI model updates and research notes.
