Text Leaderboard

Overall rankings for text generation models, powered by community votes and the Elo rating system.

Scroll horizontally to see all columns

Text

#	Model	Elo	Votes	Benchmark	$/1M In / Out	Value
1	Functionary Swahili Mini	1256	57	62.2	$0.10 / $0.90	2,512
2	Claude Sonnet 4.6	1254	154	-	$3.00 / $15.00	139
3	GLM 5	1253	173	57.0	$0.95 / $2.55	716
4	GPT-5.2	1252	147	-	$1.75 / $14.00	159
5	GPT-oss-120B	1186	141	59.1	$0.04 / $0.17	11,459
6	Functionary Swahili Large	1181	136	67.7	$0.20 / $1.50	1,389
7	Claude Sonnet 4.5	1167	138	-	$3.00 / $15.00	130
8	Claude Haiku 4.5	1157	158	-	$1.00 / $5.00	386
9	GPT-5 Nano	1139	152	68.4	$0.05 / $0.40	5,062
10Provisional rank	Step 3.7 Flash	1239	5	-	$0.20 / $1.15	1,836
11Provisional rank	GLM 5.2	1233	16	-	$0.76 / $2.42	775
12Provisional rank	DeepSeek V4 Pro	1229	10	-	$0.65 / $1.30	1,258
13Provisional rank	Mistral Medium 3.5	1228	7	-	$1.50 / $7.50	273
14Provisional rank	Kimi K2.6	1227	12	-	$0.95 / $4.00	496
15Provisional rank	MiniMax M3	1208	20	-	$0.30 / $1.20	1,611
16Provisional rank	Qwen3.7 Max	1203	11	-	$1.48 / $4.42	408
17Provisional rank	DeepSeek V4 Flash	1184	10	-	$0.14 / $0.28	5,638
18Provisional rank	GPT-5.6 Luna	1135	8	-	$0.10 / $0.60	3,243

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