Qwen2.5-Max
Qwen2.5-Max is an API-only (closed weights) language model from Qwen, released January 25, 2025. On the Epoch Capabilities Index it scores 131.2, rank 155 of 256 rated models.
Check it against your own PC →
Lab
Qwen
Released
January 25, 2025
Weights
API-only (closed weights)
Parameters
–
Context
–
Price / M tokens
–
Epoch ECI
131.2 #155
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Math | 16.5 | MATH level 5, OTIS Mock AIME 2024-2025, FrontierMath-2025-02-28-Private |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| MATH level 5 | 67.2% |
| GPQA Diamond | 43.2% |
| Aider Polyglot | 21.8% |
| OTIS Mock AIME | 16.0% |
| FrontierMath-2025-02-28-Private | 1.8% |
Links
Models with a similar score
Qwen3-30B-A3B-Instruct (Jul 2025) · gpt-oss-20b · GPT-4.1 mini · Qwen3-30B-A3B · Gemini 2.0 Flash (Feb 2025) · o1-preview · Gemini 2.0 Flash Thinking (Jan 2025) · Claude 3.5 Sonnet (October 2024)
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