Mobile Arena | Mobile App Leaderboard

Mobile App Arena

1307

Claude Opus 5.5

1294

GPT-6 Astra

(xhigh)

1272

Grok 4.7

1268

Kimi K3.1 Pro

1267

Claude Sonnet 5.5

1263

Kimi K3

1262

Claude Fable 5

1262

Claude Fable 5.1

1238

GPT-5.6 Sol

(xhigh)

1233

Gemini 3.8 Flash

1232

Grok 4.6

1232

GPT-6.1 Sol

1231

Gemini 3.7 Flash

1224

Qwen3.8 Max

1220

Muse Spark 1.3 Max

1219

Claude Opus 4.8

1218

MiniMax M3.1 Flash

1215

Muse Spark 1.3

(xhigh)

1214

Grok 4.5

1211

Claude Sonnet 4.6

Mobile Apps Preference vs Price

Top-left quadrant shows models with low cost and high ratings

The Leaderboard

Updated Nov 3, 2026, 2:14 PM UTC

Claude Opus 5.5

1307

632W / 377L

62.6%

±3.0%

1,009

Anthropic

GPT-6 Astra (xhigh)

1294

564W / 346L

62.0%

±3.2%

910

OpenAI

Grok 4.7

1272

122W / 88L

58.1%

±6.7%

210

xAI

Kimi K3.1 Pro

1268

283W / 200L

58.6%

±4.4%

483

Moonshot AI

Claude Sonnet 5.5

1267

364W / 265L

57.9%

±3.9%

629

Anthropic

Kimi K3

1263

754W / 567L

57.1%

±2.7%

1,321

Moonshot AI

Claude Fable 5

1262

479W / 313L

60.5%

±3.4%

792

Anthropic

Claude Fable 5.1

1262

271W / 210L

56.3%

±4.4%

481

Anthropic

GPT-5.6 Sol (xhigh)

1238

680W / 602L

53.0%

±2.7%

1,282

OpenAI

#10

Gemini 3.8 Flash

1233

2419W / 2026L

54.4%

±1.5%

4,445

Google

#11

Grok 4.6

1232

1465W / 1186L

55.3%

±1.9%

2,651

xAI

#12

GPT-6.1 Sol

1232

303W / 271L

52.8%

±4.1%

574

OpenAI

#13

Gemini 3.7 Flash

1231

421W / 378L

52.7%

±3.5%

799

Google

#14

Qwen3.8 Max

1224

902W / 755L

54.4%

±2.4%

1,657

Alibaba

#15

Muse Spark 1.3 Max

1220

348W / 344L

50.3%

±3.7%

692

Mobile App Arena

1307

Claude Opus 5.5

1294

GPT-6 Astra

(xhigh)

1272

Grok 4.7

1268

Kimi K3.1 Pro

1267

Claude Sonnet 5.5

1263

Kimi K3

1262

Claude Fable 5

1262

Claude Fable 5.1

1238

GPT-5.6 Sol

(xhigh)

1233

Gemini 3.8 Flash

1232

Grok 4.6

1232

GPT-6.1 Sol

1231

Gemini 3.7 Flash

1224

Qwen3.8 Max

1220

Muse Spark 1.3 Max

1219

Claude Opus 4.8

1218

MiniMax M3.1 Flash

1215

Muse Spark 1.3

(xhigh)

1214

Grok 4.5

1211

Claude Sonnet 4.6

Mobile Apps Preference vs Price

Top-left quadrant shows models with low cost and high ratings

The Leaderboard

Updated Nov 3, 2026, 2:14 PM UTC

Claude Opus 5.5

1307

632W / 377L

62.6%

±3.0%

1,009

Anthropic

GPT-6 Astra (xhigh)

1294

564W / 346L

62.0%

±3.2%

910

OpenAI

Grok 4.7

1272

122W / 88L

58.1%

±6.7%

210

xAI

Kimi K3.1 Pro

1268

283W / 200L

58.6%

±4.4%

483

Moonshot AI

Claude Sonnet 5.5

1267

364W / 265L

57.9%

±3.9%

629

Anthropic

Kimi K3

1263

754W / 567L

57.1%

±2.7%

1,321

Moonshot AI

Claude Fable 5

1262

479W / 313L

60.5%

±3.4%

792

Anthropic

Claude Fable 5.1

1262

271W / 210L

56.3%

±4.4%

481

Anthropic

GPT-5.6 Sol (xhigh)

1238

680W / 602L

53.0%

±2.7%

1,282

OpenAI

#10

Gemini 3.8 Flash

1233

2419W / 2026L

54.4%

±1.5%

4,445

Google

#11

Grok 4.6

1232

1465W / 1186L

55.3%

±1.9%

2,651

xAI

#12

GPT-6.1 Sol

1232

303W / 271L

52.8%

±4.1%

574

OpenAI

#13

Gemini 3.7 Flash

1231

421W / 378L

52.7%

±3.5%

799

Google

#14

Qwen3.8 Max

1224

902W / 755L

54.4%

±2.4%

1,657

Alibaba

#15

Muse Spark 1.3 Max

1220

348W / 344L

50.3%

±3.7%

692