Agentic Game Dev Arena | DesignArena

Agentic Game Dev Arena | DesignArena

Agentic Game Dev

Agentic Game Dev

1265

Gemini 4 Argon

1233

Claude Fable 5

1213

GPT-5.6 Sol

(xhigh)

1204

Claude Opus 5

1203

Kimi K3

1184

Claude Opus 4.8

1184

Grok 4.5

1182

Gemini 3.7 Flash

1171

Claude Sonnet 5

1158

GLM 5.2

1158

Grok 4.6

1146

Claude Opus 4.6

1132

Muse Spark 1.1

1129

Gemini 3.5 Flash

1127

GPT-5.5

1127

Muse Spark 1.2

1126

Gemini 3.6 Flash

1119

Claude Sonnet 4.6

1115

MiniMax M3

1111

GLM 5.1

Agentic Game Dev Preference vs Price

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

Models

Gemini 4 Argon

Gemini 4 Argon

Grok 4.5

Grok 4.5

Gemini 3.7 Flash

Gemini 3.7 Flash

MiniMax M3

MiniMax M3

Claude Fable 5

Claude Fable 5

GPT-5.6 Sol (xhigh)

GPT-5.6 Sol (xhigh)

Claude Opus 5

Claude Opus 5

Kimi K3

Kimi K3

Claude Opus 4.8

Claude Opus 4.8

Claude Sonnet 5

Claude Sonnet 5

GLM 5.2

GLM 5.2

Grok 4.6

Grok 4.6

Claude Opus 4.6

Claude Opus 4.6

GPT-5.6 Sol (Medium)

GPT-5.6 Sol (Medium)

Muse Spark 1.1

Muse Spark 1.1

Gemini 3.5 Flash

Gemini 3.5 Flash

GPT-5.5

GPT-5.5

Muse Spark 1.2

Muse Spark 1.2

Gemini 3.6 Flash

Gemini 3.6 Flash

Claude Sonnet 4.6

Claude Sonnet 4.6

GLM 5.1

GLM 5.1

Qwen3.7 Max

Qwen3.7 Max

Kimi K2.6

Kimi K2.6

Kimi K2.7 Code

Kimi K2.7 Code

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

GLM 5V Turbo

GLM 5V Turbo

GPT-5.6 Terra

GPT-5.6 Terra

Grok 4.3

Grok 4.3

The Leaderboard

Updated Nov 13, 2026, 12:09 AM UTC

#1

Gemini 4 Argon

1265

203W / 194L

51.1%

±4.9%

397

Google

#2

Claude Fable 5

1233

888W / 544L

62.0%

±2.5%

1,432

Anthropic

#3

GPT-5.6 Sol (xhigh)

1213

627W / 487L

56.3%

±2.9%

1,114

OpenAI

#4

Claude Opus 5

1204

458W / 402L

53.3%

±3.3%

860

Anthropic

#5

Kimi K3

1203

441W / 376L

54.0%

±3.4%

817

Moonshot AI

#6

Claude Opus 4.8

1184

789W / 638L

55.3%

±2.6%

1,427

Anthropic

#7

Grok 4.5

1184

853W / 675L

55.8%

±2.5%

1,528

xAI

#8

Gemini 3.7 Flash

1182

2471W / 2278L

52.0%

±1.4%

4,749

Google

#9

Claude Sonnet 5

1171

787W / 739L

51.6%

±2.5%

1,526

Anthropic

#10

GLM 5.2

1158

446W / 451L

49.7%

±3.3%

897

Zhipu AI

#11

Grok 4.6

1158

363W / 406L

47.2%

±3.5%

769

xAI

#12

Claude Opus 4.6

1146

126W / 151L

45.5%

±5.9%

277

Anthropic

#13

Muse Spark 1.1

1132

1336W / 1421L

48.5%

±1.9%

2,757

Meta

#14

Gemini 3.5 Flash

1129

2003W / 1621L

55.3%

±1.6%

3,624

Google

#15

GPT-5.5

1127

1202W / 1098L

52.3%

±2.0%

2,300

OpenAI

Elo Rating: A skill-based rating system starting at 1200. Ratings are calculated using the standard Bradley-Terry model. See more in our Methodology page.Margin of Error: Shows ±standard error from the Bradley-Terry model for Elo rating confidence intervals.