Qwen3-Max
Qwen3-Max is an API-only (closed weights) language model from Qwen, released September 5, 2025. Its makers disclosed about 1T parameters. The context window is 256K tokens. On the Epoch Capabilities Index it scores 142.6, rank 110 of 256 rated models. API price: $1.2 input / $6 output per million tokens.
Following the release of the Qwen3-2507 series, we are thrilled to introduce Qwen3-Max — our largest and most capable model to date. The preview version of Qwen3-Max-Instruct currently ranks third on the Text Arena leaderboard, surpassing GPT-5-Chat.
Check it against your own PC →
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Math | 33.5 | MATH level 5, OTIS Mock AIME 2024-2025, FrontierMath-Tiers-1-3-v2-Private |
| Knowledge | 64.6 | GPQA diamond, SimpleQA Verified |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| MATH level 5 | 97.1% |
| OTIS Mock AIME | 73.3% |
| GPQA Diamond | 66.1% |
| SimpleQA Verified | 48.7% |
| FrontierMath (Tiers 1–3) | 19.9% |
| Mystery Game Puzzles | 0.0% |
Links
Announcement · Epoch AI benchmarks
Models with a similar score
GLM-5 · GPT-5.4 Nano · DeepSeek-V3.2 · GPT-5 mini · Gemini 3.5 Flash-Lite · Kimi K2 Thinking · o4-mini · Gemini 3.1 Flash-Lite
More from Qwen
Qwen3.8 Omni Flash · Qwen3.8 Max (0902) · Qwen3.8 Flash · Qwen3.8 Flash Next · Qwen 3.8 27B · Qwen3.8-2.4T-A95B · Qwen 3.8 Max · Qwen3.7 Flash