Models / internlm2_5-20b-chat

Shanghai Ai Lab

internlm2_5-20b-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
Shanghai Ai Lab
Sources
1
Our benchmarks
0
Price
Not yet published

Reported by others

1,167
Business, management and finance · rank 335 of 402
Unit
Arena rating, higher is better
Range
1,150 to 1,184
Sample
1289 votes
Configuration
internlm2_5-20b-chat
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,130
Creative writing · rank 341 of 407
Unit
Arena rating, higher is better
Range
1,114 to 1,146
Sample
1432 votes
Configuration
internlm2_5-20b-chat
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,220
Expert prompts · rank 290 of 359
Unit
Arena rating, higher is better
Range
1,198 to 1,242
Sample
604 votes
Configuration
internlm2_5-20b-chat
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,178
Instruction following · rank 332 of 409
Unit
Arena rating, higher is better
Range
1,168 to 1,188
Sample
4092 votes
Configuration
internlm2_5-20b-chat
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,191
Overall · rank 337 of 409
Unit
Arena rating, higher is better
Range
1,184 to 1,198
Sample
9901 votes
Configuration
internlm2_5-20b-chat
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,152
Writing, literature and language · rank 341 of 408
Unit
Arena rating, higher is better
Range
1,139 to 1,164
Sample
2757 votes
Configuration
internlm2_5-20b-chat
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.