LLM Leaderboard - Best Text & Chat AI Models Compared

Text Arena🏆Overall

View overall rankings across various AI models in text-to-text tasks across math, coding, creative writing, and other open-ended domains.

Sep 2, 2026

7,999,020 votes

28 labs

Lab Rank		Model Score		Rank Spread
1	Anthropic claude-fable-5.1-max · Proprietary	1514±11	1	15
2	Google gemini-3.8-flash-high · Proprietary	1495±9	6	112
3	Meta muse-spark-1.2 (xHigh) · Proprietary	1489±10	10	423
4	Alibaba qwen3.8-max · Proprietary	1480±6	14	925
5	Moonshot kimi-k3-max · Kimi K3 license	1476±5	19	1029
6	Z.ai glm-5.3-max · MIT	1474±7	21	1032
7	OpenAI gpt-5.5-high · Proprietary	1471±4	24	1531
8	Baidu ernie-5.1 · Proprietary	1468±5	27	1733
9	Xiaomi mimo-v2.5-pro · MIT	1465±4	31	2034
10	SpaceXAI grok-4.5 · Proprietary	1453±5	39	3359
11	DeepSeek deepseek-v4-pro · MIT	1451±4	42	3562
12	Bytedance dola-seed-2.0-pro · Proprietary	1448±3	46	3665
13	Amazon amazon-nova-experimental-chat-26-02-10 · Proprietary	1448±10	47	3381
14	Nvidia nvidia-nemotron-3-ultra-550b-a55b-nvfp4 · OpenMDW-1.1	1445±7	54	3681
15	Tencent hy3 · Apache 2.0	1440±8	64	4286
16	Thinky inkling · Apache 2.0	1438±5	68	4785
17	MiniMax minimax-m3 · MiniMax Community License	1435±4	79	5489
18	Mistral mistral-large-3 · Apache 2.0	1428±3	87	78107
19	Meituan longcat-flash-chat-2602-exp · Proprietary	1426±5	90	78114
20	StepFun step-3.5-flash · Apache 2.0	1404±4	137	126147
21	Upstage solar-pro4 · Proprietary	1378±12	159	146182
22	IBM granite-4.2-30b · Apache 2.0	1363±11	179	157193
23	Ant Group ling-flash-2.0 · MIT	1362±7	181	163192
24	Inception AI mercury-2 · Proprietary	1358±11	183	164196
25	intellect-3 · MIT	1356±8	186	170196
26	Cohere command-a-03-2025 · CC-BY-NC-4.0	1331±3	210	199218
27	Ai2 olmo-3.1-32b-instruct · Apache 2.0	1312±6	225	214233
28	Microsoft phi-4 · MIT	1216±5	298	289300