Models / qwen1.5-72b-chat

Alibaba

qwen1.5-72b-chat

6 published results from 1 source. Each card shows where the number comes from and what it does not measure. The overall leaderboard combines them; here each stands alone.

Provider
Alibaba
Sources
1
Our benchmarks
0
Price per million tokens
Not listed on OpenRouter

Reported by others

1,206
Business, management and finance · rank 313 of 402
Unit
Arena rating, higher is better
Range
1,194 to 1,217
Sample
3842 votes
Configuration
qwen1.5-72b-chat
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,188
Creative writing · rank 311 of 407
Unit
Arena rating, higher is better
Range
1,178 to 1,199
Sample
5888 votes
Configuration
qwen1.5-72b-chat
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,236
Expert prompts · rank 283 of 359
Unit
Arena rating, higher is better
Range
1,220 to 1,251
Sample
1846 votes
Configuration
qwen1.5-72b-chat
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,212
Instruction following · rank 317 of 409
Unit
Arena rating, higher is better
Range
1,205 to 1,219
Sample
13814 votes
Configuration
qwen1.5-72b-chat
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,234
Overall · rank 316 of 409
Unit
Arena rating, higher is better
Range
1,228 to 1,239
Sample
39302 votes
Configuration
qwen1.5-72b-chat
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,214
Writing, literature and language · rank 310 of 408
Unit
Arena rating, higher is better
Range
1,206 to 1,223
Sample
9492 votes
Configuration
qwen1.5-72b-chat
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.