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	GPT-5.2	1267	172	-	$1.75 / $14.00	161
2	MiniMax M3	1265	53	-	$0.30 / $1.20	1,687
3	Kimi K2.6	1264	31	-	$0.65 / $3.41	623
4	GPT-5.6 Luna	1243	42	-	$0.20 / $1.20	1,776
5	Claude Haiku 4.5	1241	185	-	$1.00 / $5.00	414
6	Mistral Medium 3.5	1219	31	-	$1.50 / $7.50	271
7	Functionary Swahili Large	1216	157	67.7	$0.20 / $1.50	1,431
8	GLM 5.2	1208	49	-	$0.03 / $7.00	343
9	GLM 5	1195	199	57.0	$1.00 / $3.20	569
10	Functionary Swahili Mini	1191	77	62.2	$0.10 / $0.90	2,382
11	Claude Sonnet 4.6	1190	176	-	$3.00 / $15.00	132
12	Claude Sonnet 4.5	1190	168	-	$3.00 / $15.00	132
13	Qwen3.7 Max	1164	33	-	$1.48 / $4.42	395
14	GPT-5 Nano	1159	164	68.4	$0.05 / $0.40	5,151
15	GPT-oss-120B	1122	164	59.1	$0.15 / $0.60	2,992
16	DeepSeek V4 Flash	1118	44	-	$0.14 / $0.28	5,324
17Provisional rank	DeepSeek V4 Pro	1229	29	-	$0.96 / $1.91	858
18Provisional rank	Step 3.7 Flash	1192	18	-	$0.20 / $1.15	1,766

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