grok-4.20-beta1

8 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: xAI
Sources: 1
Our benchmarks: 0
Price: Not yet published

Reported by others

Reported by Arena (formerly LMArena)

1,197

Overall · rank 6 of 34

Unit: Arena rating, higher is better
Range: 1,191 to 1,203
Sample: 53921 votes
Configuration: grok-4.20-beta1 (arena search)
Measured: 24 Aug 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,453

Overall · rank 44 of 177

Unit: Arena rating, higher is better
Range: 1,448 to 1,457
Sample: 27668 votes
Configuration: grok-4.20-beta1
Measured: 25 Sep 2026
Not shown: Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.

Reported by Arena (formerly LMArena)

1,470

Business, management and finance · rank 15 of 402

Unit: Arena rating, higher is better
Range: 1,461 to 1,478
Sample: 5365 votes
Configuration: grok-4.20-beta1
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,464

Creative writing · rank 9 of 407

Unit: Arena rating, higher is better
Range: 1,454 to 1,474
Sample: 4171 votes
Configuration: grok-4.20-beta1
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,476

Expert prompts · rank 37 of 359

Unit: Arena rating, higher is better
Range: 1,463 to 1,488
Sample: 2462 votes
Configuration: grok-4.20-beta1
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,450

Instruction following · rank 41 of 409

Unit: Arena rating, higher is better
Range: 1,443 to 1,457
Sample: 8832 votes
Configuration: grok-4.20-beta1
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,475

Overall · rank 19 of 409

Unit: Arena rating, higher is better
Range: 1,470 to 1,479
Sample: 27864 votes
Configuration: grok-4.20-beta1
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,453

Writing, literature and language · rank 25 of 408

Unit: Arena rating, higher is better
Range: 1,445 to 1,461
Sample: 6376 votes
Configuration: grok-4.20-beta1
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.