Chaiverse calculates the ELO of LLMs via human feedback, obtained through blind selection testing using the Chai app. This involves gathering positive and negative upvotes from randomly selected models on our leaderboard, as experienced by end users. With over one million samples a day, we are able to build a ranking of LLMs - which for our use-case, seems to be the most accurate.

Submit your model now, and start collecting feedback on your model’s ranking in under five minutes! Feel free to join us on our Discord server to discuss the leaderboard and chat with other participants!

Submissions in the last 24 hours: 69
2 minutes ago by kaltcit πŸš€
Model: turboderp-llama3-turbcat_4336_v1
HuggingFace: N/A
Model Size: N/A
Elo: N/A
Human feedbacks: 0
1 hour ago by robert_irvine πŸš€
Model: blend_lugom_2024-06-25
HuggingFace: N/A
Model Size: n/a
Elo: 1197
Human feedbacks: 16663
1 hour ago by robert_irvine πŸš€
Model: blend_pemab_2024-06-25
HuggingFace: N/A
Model Size: n/a
Elo: 1196
Human feedbacks: 16583
1 hour ago by robert_irvine πŸš€
Model: blend_farof_2024-06-25
HuggingFace: N/A
Model Size: n/a
Elo: 1200
Human feedbacks: 16433
1 hour ago by robert_irvine πŸš€
Model: blend_tobef_2024-06-25
HuggingFace: N/A
Model Size: n/a
Elo: 1203
Human feedbacks: 16535
1 hour ago by robert_irvine πŸš€
Model: blend_fubot_2024-06-25
HuggingFace: N/A
Model Size: n/a
Elo: 1199
Human feedbacks: 16283
1 hour ago by robert_irvine πŸš€
Model: blend_pogem_2024-06-25
HuggingFace: N/A
Model Size: n/a
Elo: 1190
Human feedbacks: 16461
1 hour ago by robert_irvine πŸš€
Model: blend_sadel_2024-06-25
HuggingFace: N/A
Model Size: n/a
Elo: 1196
Human feedbacks: 16425
4 hours ago by chai_backend_admin πŸš€
Model: blend_lakem_2024-06-25
HuggingFace: N/A
Model Size: n/a
Elo: 1182
Human feedbacks: 106215
8 hours ago by c.gato πŸš€
Model: cgato-thesalt-rp-l3-8b-_8872_v12
HuggingFace: cgato/TheSalt-RP-L3-8b-v0.3.2
Model Size: 8B
Elo: 1204
Human feedbacks: 8777
Loading...