whatmodel.sh / Qwen2.5-Max (2025-01-25)
Qwen2.5-Max (2025-01-25)
↗ share
+ contribute
Qwen2.5-Max (2025-01-25) is a closed-weights language model from Alibaba, released January 2025. Licence: proprietary.
Catalogue identity notes
Comparison model from the Epoch AI internal-evaluation CSVs (Epoch release date 2025-01-25). Dated API snapshot qwen-max-2025-01-25 (Epoch display 'Qwen2.5-Max'). Not listed on Model Studio's text-generation or pricing pages (observed 2026-09-28), so api is null. Distinct from arena's 'qwen-max-0919'.
$ how it compares
The LLMs ranked either side of Qwen2.5-Max (2025-01-25), out of 828 with a score, then more from Alibaba.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 278 |  GPT-4o (2024-11-20) | 57±1 | api $4.38/M | ||
| 279 |  Gemini 2.5 Flash-Lite | 57±2 | api $0.17/M | ||
| 280 | Qwen2.5-Max (2025-01-25) | 57±1 | comparison only | ||
| 281 | Qwen2.5-Omni 7B | 57±2 | local | ||
| 282 | GPT-4o (2024-05-13) | 57±0 | api $7.50/M | ||
| more from Alibaba | |||||
| 18 | Qwen3.8 Max (2.4T-A95B) | 78±1 | api $3.00/M +local | ||
| 34 | Qwen3.8 Max (0902) | 76±1 | api $3.00/M | ||
| 37 | Qwen3.8-Flash-Next | 75±1 | local | ||
$ what it's good at
coding▁▁▁▃▅▇█▇▅▄▃▁ #249 of 524 * · 31% of its score · 2 tests
Beats Qwen3.5 4B, Qwen3-VL 32B Instruct, Solar Open 100B (102B-A12B) here, though they rank higher overall. Trails QwQ-32B-Preview, Ministral 3 3B Reasoning 2512, DeepSeek-Coder-V2 Instruct (0724) here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Aider polyglot (225 exercises, two attempts) | 21.8% ✎ | ▂·▂▃▅▂▃█▆▄▂▂ beats 12/49 | 27% |
| WebApp1K-React pass@1 (onekq-ai) | 57.6% ✎ | ▃▁▁█▁▄▅▃▄▇▁▄ beats 14/31 | 4.7% |
chat & writing▁▁▁▃▅▄▆█▇▇▇▃ #158 of 463 * · 12% of its score · 1 test
Beats o3-mini, EXAONE 4.5 33B, INTELLECT-3 here, though they rank higher overall. Trails LFM2.5 8B-A1B, LFM2.5 2.6B, Spark-X2.5 1.7B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena (text) | 1373.8 ✎ | ▁▁▁▂▃▃▃▆▆▇█▃ beats 214/379 | 12% |
math▁▂▃▅▇▅▅█▄▁▁▁ #241 of 462 * · 36% of its score · 2 tests
Beats DeepSeek V3 (Dec '24), GPT-4o (2024-08-06), Command A (03-2025) here, though they rank higher overall. Trails Olmo 3 7B Instruct, DeepSeek R1 Distill Llama 8B, Phi-4-mini-reasoning 3.8B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| MATH level 5 | 67.2% ✎ | ▂▂▅▆▄█▆▃▅▂▃▄ beats 58/92 | 26% |
| OTIS mock AIME 2024–2025 | 16.1% ✎ | ▃▃▄▃▃▃▇▇█▃▂▅ beats 54/193 | 10% |
other tests1 not in a task · 20% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| GPQA Diamond | 56.1% ✎ | ▁▁▁▁▂▄▆▄▅▇█▅ beats 82/208 | 20% |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · Epoch AI — internal evaluatio… 57%, Aider polyglot benchmark runs 27%, LMArena leaderboard dataset 12% and 1 more
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 Epoch AI — internal evaluations | 3 | 57% |
 Aider polyglot benchmark runs | 1 | 27% |
 LMArena leaderboard dataset | 1 | 12% |
| WebApp1K models leaderboard (onekq-ai) | 1 | 5% |
| prior · pull toward the middle | 1% | |
| weighted average | = 57.1 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json