Skip to content
OneAtlas

Design Arena · Game dev

Head-to-head Elo from Design Arena votes in the Game dev category.

Published by Design Arena
116
Models scored
1438
Top score
1176
Median

Distribution of scores

7731438

Leaderboard

116 models

#ModelScoreWin rateContextInput $Output $
1Claude Opus 5.5Anthropic143866.4%1M$4.00$20.00
2Claude Sonnet 5.5Anthropic141462.2%1M$2.00$10.00
3GPT-6.1 SolOpenAI140861.0%1.05M$2.00$10.00
4Kimi K3.1 ProMoonshot AI140766.5%1.05M$4.00$20.00
5Claude Fable 5.1Anthropic138165.6%1M$10.00$50.00
6Gemini 4 ArgonGoogle136957.9%1.05M$2.00$10.00
7Kimi K3Moonshot AI136260.2%1.05M$3.00$15.00
8Muse Spark 1.3Meta134356.0%1.05M$1.25$4.25
9Claude Opus 5Anthropic133858.3%1M$5.00$25.00
10Claude Fable 5Anthropic133560.8%1M$10.00$50.00
11Claude Haiku 5.5Anthropic132355.0%1M$0.10$0.50
12Gemini 3.7 FlashGoogle131853.5%1.05M$0.75$3.75
13MiMo-V2.6-ProXiaomi131553.5%1.05M$0.43$0.87
14Grok 4.7xAI131352.6%500K$2.00$6.00
15GLM-5.3Zhipu AI130752.1%1M$1.20$4.18
16Gemini 3.8 FlashGoogle130451.0%1.05M$0.75$3.75
17Muse Spark 1.2Meta130150.5%1.05M$1.25$4.25
18Grok 4.6xAI129454.0%500K$2.00$6.00
19GPT-5.5OpenAI129156.6%1.05M$5.00$30.00
20GLM-5.3-FlashZhipu AI127646.8%1M$0.30$1.05
21Claude Opus 4.6Anthropic127661.0%1M$5.00$25.00
22Claude Sonnet 5Anthropic127451.1%1M$2.00$10.00
23Muse Spark OpenMeta126949.8%1.05M$1.25$4.25
24Muse Spark 1.1Meta126948.1%1.05M$1.25$4.25
25GLM-5.2Zhipu AI126649.4%1M$1.20$4.18
26DeepSeek V4.1 Flash 1017DeepSeek126443.4%1.05M$0.15$0.60
27Qwen3.7 MaxAlibaba126452.6%1M$2.50$7.50
28MiMo-V2.5-ProXiaomi126453.3%1.05M$0.43$0.87
29GLM-5.1Zhipu AI126455.0%200K$0.90$3.59
30Claude Opus 4.8Anthropic126352.5%1M$5.00$25.00
31Gemini 3.6 FlashGoogle126250.8%1.05M$0.75$3.75
32Grok 4.5xAI126249.2%500K$2.00$6.00
33Gemini 3.5 FlashGoogle126252.5%1.05M$1.50$9.00
34Qwen3.7 PlusAlibaba126049.2%1M$0.40$1.60
35Claude Sonnet 4.6Anthropic125958.8%1M$3.00$15.00
36MiMo-V2.5Xiaomi124952.5%1.05M$0.14$0.28
37Kimi K2.6Moonshot AI124954.9%262K$0.95$4.00
38GLM-5-TurboZhipu AI124652.4%200K$0.72$3.20
39GPT-5.4OpenAI123757.6%1.05M$2.50$15.00
40GLM-5Zhipu AI123457.4%205K$0.60$2.69
41DeepSeek V4 ProDeepSeek122952.3%1.05M$1.00$2.50
42Claude Opus 4.5 (latest)Anthropic122959.3%200K$5.00$25.00
43Mistral Large 4Mistral122642.3%1.05M$1.36$4.18
44Mercury 3Inception122244.2%1M$0.10$0.35
45Kimi K2.7 CodeMoonshot AI122047.0%262K$1.90$8.00
46GLM-5V-TurboZhipu AI121749.7%200K$0.75$3.29
47Beam 1.0 501B A23BReflection121241.4%1.05MFreeFree
48MiniMax-M3MiniMax121145.7%1M$0.30$1.20
49Qwen3.6 PlusAlibaba121148.4%1M$0.50$3.00
50DeepSeek V4 Flash 0731DeepSeek120844.6%1.05M$0.13$0.26
51MiniMax-M2.7MiniMax120849.4%205K$0.30$1.20
52Kimi K2.5Moonshot AI120553.4%262K$0.63$3.30
53Gemini 3.1 Pro PreviewGoogle120252.2%1.05M$2.00$12.00
54DeepSeek V4 FlashDeepSeek119750.2%1M$0.45$1.35
55GPT-5.2OpenAI119556.0%400K$1.75$14.00
56GLM-4.7Zhipu AI118755.2%205K$0.45$2.09
57GPT-5OpenAI118559.3%400K$1.25$10.00
58GPT-5.1OpenAI117755.9%400K$1.25$10.00
59MiniMax-M2.5MiniMax117655.5%205K$0.30$1.20
60Grok 4.3xAI117142.8%1M$1.25$2.50
61Claude Opus 4.1 (latest)Anthropic117158.4%200K$15.00$75.00
62Solar Pro 4Upstage117039.9%524K$0.30$1.20
63Gemini 3 Flash PreviewGoogle116658.3%1.05M$0.50$3.00
64Claude Sonnet 4.5 (latest)Anthropic116651.1%200K$3.00$15.00
65InklingThinking Machines116437.8%262K$1.00$4.05
66GPT-5.3 CodexOpenAI116151.3%400K$1.75$14.00
67Step 3.7 FlashStepFun (China)115637.8%256K$0.20$1.21
68GLM-4.6Zhipu AI115154.8%205K$0.60$2.20
69GLM-4.5Zhipu AI114554.4%131K$0.60$2.20
70DeepSeek V3.2 ExpDeepSeek114453.0%164K$0.27$0.41
71Nemotron 3 Ultra 550B A55BNVIDIA114036.1%1MFreeFree
72Qwen3.5 397B-A17BAlibaba114050.2%262K$0.60$3.60
73GPT-5.1 CodexOpenAI113850.5%400K$1.25$10.00
74Hy3Tencent113638.6%262K$0.14$0.58
75GLM-4.7-FlashZhipu AI113549.7%200KFreeFree
76MiniMax-M2.1MiniMax113450.4%205K$0.30$1.20
77DeepSeek V3.2DeepSeek113046.5%164K$0.60$0.90
78DeepSeek V3.1 TerminusDeepSeek112952.5%128K$0.27$1.00
79GPT-5 MiniOpenAI112846.5%400K$0.25$2.00
80Solar Mini 4Upstage112529.4%524K$0.10$0.40
81Muse Glimmer 30BMeta112231.2%131KFreeFree
82MiniMax-M2MiniMax111848.1%205K$0.30$1.20
83Gemini 2.5 ProGoogle111154.2%1.05M$1.25$10.00
84Nemotron 3.5 Super VL 120B A12BNVIDIA111029.4%1.05MFreeFree
85Qwen3 Coder 480B A35B InstructAlibaba109958.7%262K$1.50$7.50
86Claude Haiku 4.5 (latest)Anthropic109744.7%200K$1.00$5.00
87DeepSeek R1 0528DeepSeek109749.3%164K$0.50$2.15
88GLM-4.5-AirZhipu AI109448.4%131K$0.12$0.90
89GPT-5.1 Codex miniOpenAI109243.4%256K$0.25$2.00
90DeepSeek V3.1DeepSeek108447.1%164K$0.25$0.95
91Mistral Large 3Mistral108041.5%262K$0.50$1.50
92GPT-4.1OpenAI107859.1%1.05M$2.00$8.00
93Mistral Medium 3.1Mistral107440.8%262K$0.40$2.00
94GPT-4.1 miniOpenAI106958.5%1.05M$0.40$1.60
95Gemini 2.5 FlashGoogle106444.3%1.05M$0.30$2.50
96DeepSeek ChatDeepSeek105343.7%128K$0.26$1.03
97GPT-5 NanoOpenAI104546.5%400K$0.05$0.40
98Ministral 3 14B 2512Mistral103843.6%128K$0.33$0.33
99o3OpenAI103456.9%200K$2.00$8.00
100Gemini 3.1 Flash Lite PreviewGoogle102933.7%1.05M$0.25$1.50
101Mistral Medium 3Mistral101845.2%131K$0.40$2.00
102o4-miniOpenAI100350.0%200K$1.10$4.40
103GPT OSS 120BOpenAI99240.5%128K$0.10$0.50
104Ministral 3 8B 2512Mistral99038.7%262K$0.15$0.15
105Mercury 2Inception97918.3%128K$0.25$0.75
106Kimi K2Moonshot AI97446.4%131K$0.57$2.30
107GPT-4.1 nanoOpenAI96949.6%1.05M$0.10$0.40
108Codestral 25.08Mistral96636.3%256K$0.30$0.90
109Qwen3 235B A22B Thinking 2507Alibaba95734.2%262K$0.30$3.00
110Qwen3 235B A22B Instruct 2507Alibaba95035.0%262K$1.03$3.08
111Ministral 3BMistral94733.0%128K$0.04$0.04
112GPT-4oOpenAI90642.3%128K$2.50$10.00
113Qwen3 30B A3BAlibaba89733.9%128K$0.11$1.08
114Mistral Small 3.2 24B InstructMistral88739.4%256K$0.09$0.25
115Llama 4 Maverick 17B InstructMeta83633.7%128K$0.19$0.65
116Llama 4 Scout 17B InstructMeta77327.4%328K$0.08$0.24