Alibaba (Qwen)

Qwen2.5 Max 2025-01-25

Type
language model
Context
128K tokens
Max output
4K
Released
5 August 2025
API string
qwen-max-2025-01-25

Prices by provider

Providers do have offers, but we have not collected a current price yet. That is a gap on our side, not a model missing from the market.

Measurement results

Task set Result Run conditions Measured by
MATH, difficulty level five 67.18 % · with a tuned harness Epoch evaluations
Fiction.LiveBench — holding a long context 66.7 % Fiction.live leaderboard
GPQA Diamond — graduate-level questions 41.5 % · with a tuned harness Epoch evaluations
Aider Polyglot — code edits in six languages 21.8 % · with a tuned harness Aider LLM Leaderboards
Mock AIME 2024–2025 — olympiad problems 16.03 % · with a tuned harness Epoch evaluations