ModelChorusModelChorus
ChallengeChatLeaderboardSwipeBenchmarksStore
OverviewVotersHead-to-HeadTextImageTTSSTTModels
How it worksAPITerms of ServicePrivacy Policy

Copyright 2026 MeetKai Inc.

Leaderboard Overview

Rankings are powered by the Elo rating system — the same method used in competitive chess. Every time you vote in a head-to-head challenge, the winning model gains points and the losing model drops. The more challenges a model wins, the higher it climbs. Scores update in real time so you're always seeing the latest community consensus.

Text

#
Model(18/18)
Elo
Votes
Benchmark
1
Functionary Swahili Mini
12565762.2
2
Claude Sonnet 4.6
1254154-
3
GLM 5
125317357.0
4
GPT-5.2
1252147-
5
GPT-oss-120B
118614159.1
6
Functionary Swahili Large
118113667.7
7
Claude Sonnet 4.5
1167138-
8
Claude Haiku 4.5
1157158-
9
GPT-5 Nano
113915268.4
10Provisional rank
Step 3.7 Flash
12395-

Provisional — fewer than 30 votes. These models are ranked below every established model, so rank and Elo can disagree.

View all 18 models

Image

#
Model(10/10)
Elo
Votes
1
Riverflow V2.5 Fast
132451
2
MAI-Image-2.5
132356
3
Nano Banana Pro (Gemini 3 Pro Image)
121074
4
Seedream 4.5
1210646
5
GPT Image 2
119866
6
Gemini 2.5 Flash Image (Nano Banana)
1198688
7
Riverflow V2 Fast
1191703
8
Nano Banana 2 (Gemini 3.1 Flash Image)
115863
9
FLUX.2 Max
114453
10
FLUX.2 Klein 4B
1137634
View all

TTS

#
Model(4/4)
Elo
Votes
1
MKA1 Speech TTS v1
1217254
2
MKA1 Speech TTS v1.1
1183254
3Provisional rank
Grok Voice TTS 1.0
12091
4Provisional rank
MAI-Voice-2
11911

Provisional — fewer than 30 votes. These models are ranked below every established model, so rank and Elo can disagree.

View all

STT

#
Model(2/2)
Elo
Votes
1Provisional rank
MKA1 Speech Transcription v1
122913
2Provisional rank
MKA1 Speech Transcription v1.1
117113

Provisional — fewer than 30 votes. An Elo from this few votes is still noisy.

View all