Text Arena: LLM Rankings & AI Model Benchmarks

Lab Rank		Model Score		Rank Spread
1	Google Gemini 4 Argon (High) · Proprietary	1524±9	1	13
2	Meta Muse Wonder (Max) · Proprietary	1510±9	2	18
3	Anthropic Claude Opus 5.5 (High) · Proprietary	1509±7	3	17
4	Moonshot Kimi K3 (Max) · Kimi K3 license	1488±5	18	930
5	OpenAI GPT-5.6 Sol (xHigh) · Proprietary	1484±4	21	1234
6	Alibaba Qwen3.8-Max · Proprietary	1483±5	23	1242
7	Z.ai GLM-5.3 (Max) · MIT	1481±5	26	1544
8	Xiaomi MiMo-V2.6-Pro · MIT	1480±9	27	1251
9	DeepSeek DeepSeek-V4.1-Flash-20260910 (Max) · MIT	1475±6	36	2154
10	SpaceXAI Grok 4.20 Beta 1 · Proprietary	1475±5	39	2251
11	Baidu ERNIE 5.1 · Proprietary	1467±5	50	3261
12	Bytedance Dola Seed 2.0 Pro · Proprietary	1456±3	67	5782
13	Tencent Hy3 · Apache 2.0	1453±6	74	5790
14	StepFun Step 5 Preview · Proprietary	1446±7	85	64107
15	Thinky Inkling · Apache 2.0	1441±4	93	79111
16	MiniMax MiniMax-M3 · MiniMax Community License	1441±4	97	81112
17	Meituan LongCat-Flash-Chat Exp (2602) · Proprietary	1436±5	103	87121
18	Reflection Beam 1.0 501B A23B · Apache 2.0	1436±9	104	79130
19	Mistral Mistral Large 4 · Proprietary	1433±7	112	88131
20	Amazon amazon-nova-experimental-chat (26-02-10) · Proprietary	1426±10	118	97148
21	Nvidia NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4) · OpenMDW-1.1	1426±7	121	101143
22	Upstage Solar Pro 4 · Proprietary	1388±5	181	167192
23	Trinity Large Preview · Apache 2.0	1379±4	191	180199
24	Cohere Command A (03-2025) · CC-BY-NC-4.0	1354±3	213	207234
25	Ant Group Ling-flash-2.0 · MIT	1343±7	229	212248
26	Inception AI Mercury 2 · Proprietary	1342±11	233	209251
27	IBM Granite 4.2 30B · Apache 2.0	1340±10	236	212256
28	Ai2 Olmo 3.1 32B Instruct · Apache 2.0	1329±6	247	230265
29	Microsoft Phi-4 · MIT	1256±5	321	315323

Lab Rank

Model Score

Rank Spread

Google

Gemini 4 Argon (High) · Proprietary

1524±9

Meta

Muse Wonder (Max) · Proprietary

1510±9

Anthropic

Claude Opus 5.5 (High) · Proprietary

1509±7

Moonshot

Kimi K3 (Max) · Kimi K3 license

1488±5

930

OpenAI

GPT-5.6 Sol (xHigh) · Proprietary

1484±4

1234

Alibaba

Qwen3.8-Max · Proprietary

1483±5

1242

Z.ai

GLM-5.3 (Max) · MIT

1481±5

1544

Xiaomi

MiMo-V2.6-Pro · MIT

1480±9

1251

DeepSeek

DeepSeek-V4.1-Flash-20260910 (Max) · MIT

1475±6

2154

SpaceXAI

Grok 4.20 Beta 1 · Proprietary

1475±5

2251

Baidu

ERNIE 5.1 · Proprietary

1467±5

3261

Bytedance

Dola Seed 2.0 Pro · Proprietary

1456±3

5782

Tencent

Hy3 · Apache 2.0

1453±6

5790

StepFun

Step 5 Preview · Proprietary

1446±7

64107

Thinky

Inkling · Apache 2.0

1441±4

79111

MiniMax

MiniMax-M3 · MiniMax Community License

1441±4

81112

Meituan

LongCat-Flash-Chat Exp (2602) · Proprietary

1436±5

103

87121

Reflection

Beam 1.0 501B A23B · Apache 2.0

1436±9

104

79130

Mistral

Mistral Large 4 · Proprietary

1433±7

112

88131

Amazon

amazon-nova-experimental-chat (26-02-10) · Proprietary

1426±10

118

97148

Nvidia

NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4) · OpenMDW-1.1

1426±7

121

101143

Upstage

Solar Pro 4 · Proprietary

1388±5

181

167192

Trinity Large Preview · Apache 2.0

1379±4

191

180199

Cohere

Command A (03-2025) · CC-BY-NC-4.0

1354±3

213

207234

Ant Group

Ling-flash-2.0 · MIT

1343±7

229

212248

Inception AI

Mercury 2 · Proprietary

1342±11

233

209251

IBM

Granite 4.2 30B · Apache 2.0

1340±10

236

212256

Ai2

Olmo 3.1 32B Instruct · Apache 2.0

1329±6

247

230265

Microsoft

Phi-4 · MIT

1256±5

321

315323

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.

Default Leaderboard Plots

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.

Default Leaderboard Plots

Fraction of Model A Wins in A vs. B Battles (Ties Excluded)

Average Win Rate Against Each Opponent (Ties Excluded)

Battle Count for Each Pair of Models (Ties Excluded)

Confidence Intervals on Model Strength (via Bootstrapping)