Game development · Models
Design Arena's Elo for game development · models, from pairwise human preference votes, as OpenRouter carries it. 120 models ranked, as carried in OpenRouter's catalog.
retrieved sha256 · 0bb53a77713fwww.designarena.ai ↗
7 models sit on the frontier: nothing scores higher for less.
- the attractive quadrant
- the frontier
- a priced model, in its maker's tone
- on the frontier, named
- 01Hy4 flash1225 · $0.061 blended
- 02DeepSeek V4.1 Flash 10171253 · $0.152 blended · +28 at 2.5x
- 03Claude Haiku 5.51313 · $0.20 blended · +60 at 1.3x
- 04Muse Spark 1.31344 · $2.00 blended · +31 at 10x
- 05Kimi K3.1 Pro1402 · $2.281 blended · +58 at 1.1x
- 06GPT-6.1 Sol1406 · $4.00 blended · +4 at 1.8x
- 07Claude Opus 5.51427 · $8.00 blended · +21 at 2.0x
120 of 120 ranked models carry a list price; 0 are free or unlisted and not in the field. Price is the blended OpenRouter rate, three input tokens to one output, on a logarithmic axis. Each dot is filled in its maker's tone, as the columns above are. The numbered and named dots are the frontier, cheapest first; each step after the first names what it adds over the step before, and at what multiple of the blended price. A hover over any dot names it and its two figures, a click opens the model, and a model named in the picker above keeps its label on. 17 of 120 priced models sit in the attractive quadrant: at or above the median Elo of 1183 and at or below the median blended price of $1.026. The tinted corner is that quadrant. 120 of the 120 crosses match the selection below and are drawn white.
120 of 120.
Design Arena · Elo7 more authors are on this board, the largest with 3 models. Search a name to reach one.
| Position | Model | Author | Elo | Win rate | Source rank | In / out per M | Context | Listed |
|---|---|---|---|---|---|---|---|---|
| 01 | Claude Opus 5.5 | Anthropic | 1427 | 63.9% | 1 | $4.00 / $20.00 | 1M | |
| 02 | Muse Wonder | Meta | 1414 | 62.0% | 2 | $4.00 / $20.00 | 1.05M | |
| 03 | GPT-6.1 Sol | OpenAI | 1406 | 59.9% | 3 | $2.00 / $10.00 | 1.05M | |
| 04 | Kimi K3.1 Pro | MoonshotAI | 1402 | 65.6% | 4 | $0.24 / $8.40 | 1.05M | |
| 05 | Claude Fable 5.2 | Anthropic | 1401 | 64.7% | 5 | $8.00 / $40.00 | 1M | |
| 06 | Claude Sonnet 5.5 | Anthropic | 1383 | 58.4% | 6 | $2.00 / $10.00 | 1M | |
| 07 | Claude Fable 5.1 | Anthropic | 1364 | 59.5% | 7 | $10.00 / $50.00 | 1M | |
| 08 | Gemini 4 Argon | 1361 | 53.8% | 8 | $2.00 / $10.00 | 1.05M | ||
| 09 | Gemini 4 Hydrogen | 1354 | 54.5% | 9 | $1.50 / $7.50 | 1.05M | ||
| 10 | Kimi K3 | MoonshotAI | 1354 | 55.2% | 10 | $0.192 / $16.00 | 1.05M | |
| 11 | Muse Spark 1.3 | Meta | 1344 | 56.9% | 11 | $1.25 / $4.25 | 1.05M | |
| 12 | Gemini 4 Carbon | 1332 | 57.5% | 12 | $2.00 / $10.00 | 1.05M | ||
| 13 | Claude Opus 5 | Anthropic | 1329 | 57.8% | 13 | $5.00 / $25.00 | 1M | |
| 14 | Claude Fable 5 | Anthropic | 1324 | 60.8% | 14 | $10.00 / $50.00 | 1M | |
| 15 | Claude Haiku 5.5 | Anthropic | 1313 | 51.2% | 15 | $0.10 / $0.50 | 1M | |
| 16 | MiMo-V2.6-Pro | Xiaomi | 1312 | 53.5% | 16 | $0.435 / $0.87 | 1.05M | |
| 17 | Gemini 3.7 Flash | 1311 | 53.2% | 17 | $0.75 / $3.75 | 1.05M | ||
| 18 | Grok 4.7 | SpaceXAI | 1305 | 50.4% | 19 | $2.00 / $6.00 | 500k | |
| 19 | Gemini 3.8 Flash | 1296 | 50.8% | 20 | $0.825 / $4.13 | 1.05M | ||
| 20 | Muse Spark 1.2 | Meta | 1293 | 50.4% | 21 | $1.25 / $4.25 | 1.05M | |
| 21 | GLM 5.3 | Z.ai | 1287 | 50.4% | 22 | $0.0699 / $1.40 | 1.05M | |
| 22 | GPT-5.5 | OpenAI | 1281 | 56.1% | 23 | $5.00 / $30.00 | 1.05M | |
| 23 | Grok 4.6 | SpaceXAI | 1280 | 52.9% | 24 | $2.00 / $6.00 | 500k | |
| 24 | Hy4 | Tencent | 1278 | 50.4% | 25 | $0.417 / $1.25 | 1.05M | |
| 25 | Claude Sonnet 5 | Anthropic | 1272 | 51.4% | 26 | $2.00 / $10.00 | 1M | |
| 26 | Claude Opus 4.6 | Anthropic | 1267 | 61.0% | 27 | $5.00 / $25.00 | 1M | |
| 27 | GLM 5.3 Flash | Z.ai | 1266 | 46.4% | 28 | $0.15 / $0.50 | 1.05M | |
| 28 | MiMo-V2.5-Pro | Xiaomi | 1265 | 54.1% | 29 | $0.435 / $0.87 | 1.02M | |
| 29 | Muse Spark Open | Meta | 1260 | 47.4% | 30 | $1.25 / $4.25 | 1.05M | |
| 30 | Muse Spark 1.1 | Meta | 1257 | 47.5% | 31 | $1.25 / $4.25 | 1.05M | |
| 31 | GLM 5.2 | Z.ai | 1255 | 49.0% | 32 | $0.007 / $6.80 | 1.05M | |
| 32 | GLM 5.1 | Z.ai | 1254 | 54.5% | 33 | $1.40 / $4.40 | 205k | |
| 33 | Qwen3.7 Max | Qwen | 1254 | 52.2% | 34 | $1.48 / $4.42 | 1M | |
| 34 | DeepSeek V4.1 Flash 1017 | DeepSeek | 1253 | 43.2% | 35 | $0.036 / $0.50 | 1.05M | |
| 35 | Gemini 3.5 Flash | 1253 | 52.3% | 36 | $1.50 / $9.00 | 1.05M | ||
| 36 | Gemini 3.6 Flash | 1252 | 50.4% | 37 | $0.75 / $3.75 | 1.05M | ||
| 37 | Claude Opus 4.8 | Anthropic | 1250 | 51.8% | 38 | $5.00 / $25.00 | 1M | |
| 38 | Qwen3.7 Plus | Qwen | 1250 | 48.7% | 39 | $0.32 / $1.28 | 1M | |
| 39 | Grok 4.5 | SpaceXAI | 1250 | 48.4% | 40 | $2.00 / $6.00 | 500k | |
| 40 | Claude Sonnet 4.6 | Anthropic | 1248 | 58.8% | 41 | $3.00 / $15.00 | 1M | |
| 41 | MiMo-V2.5 | Xiaomi | 1242 | 52.6% | 42 | $0.40 / $2.00 | 1M | |
| 42 | Kimi K2.6 | MoonshotAI | 1239 | 54.8% | 43 | $0.65 / $3.41 | 262k | |
| 43 | GLM 5 Turbo | Z.ai | 1237 | 52.2% | 44 | $1.20 / $4.00 | 203k | |
| 44 | GPT-5.4 | OpenAI | 1228 | 57.6% | 45 | $2.50 / $15.00 | 1.05M | |
| 45 | Hy4 flash | Tencent | 1225 | 45.0% | 46 | $0.035 / $0.141 | 1.05M | |
| 46 | GLM 5 | Z.ai | 1223 | 57.4% | 47 | $1.00 / $3.20 | 205k | |
| 47 | DeepSeek V4 Pro 0423 | DeepSeek | 1221 | 53.0% | 48 | $0.90 / $1.50 | 1.05M | |
| 48 | Claude Opus 4.5 | Anthropic | 1218 | 59.3% | 49 | $5.00 / $25.00 | 200k | |
| 49 | Kimi K2.7 Code | MoonshotAI | 1210 | 46.4% | 51 | $0.70 / $3.75 | 262k | |
| 50 | GLM 5V Turbo | Z.ai | 1206 | 49.3% | 52 | $1.20 / $4.00 | 203k | |
| 51 | Mistral Large 4 | Mistral | 1204 | 40.2% | 54 | $0.70 / $2.10 | 1.05M | |
| 52 | Qwen3.6 Plus | Qwen | 1201 | 48.2% | 56 | $0.325 / $1.95 | 1M | |
| 53 | MiniMax M3 | MiniMax | 1199 | 45.1% | 57 | $0.30 / $1.20 | 1.05M | |
| 54 | MiniMax M2.7 | MiniMax | 1198 | 49.0% | 58 | $0.21 / $0.84 | 197k | |
| 55 | DeepSeek V4 Flash 0731 | DeepSeek | 1197 | 44.8% | 59 | $0.06 / $0.18 | 1.05M | |
| 56 | Kimi K2.5 | MoonshotAI | 1195 | 53.4% | 61 | $0.50 / $2.50 | 262k | |
| 57 | Gemini 3.1 Pro Preview | 1191 | 52.4% | 62 | $2.00 / $12.00 | 1.05M | ||
| 58 | Beam 1.0 501B A23B | Reflection | 1187 | 40.0% | 63 | $0.30 / $1.00 | 1.05M | |
| 59 | DeepSeek V4 Flash 0423 | DeepSeek | 1186 | 50.2% | 64 | $0.09 / $0.18 | 1.05M | |
| 60 | GPT-5.2 | OpenAI | 1184 | 56.0% | 65 | $1.75 / $14.00 | 400k | |
| 61 | Grok 4.20 | SpaceXAI | 1182 | 50.4% | 66 | $1.25 / $2.50 | 2M | |
| 62 | GLM 4.7 | Z.ai | 1177 | 55.2% | 67 | $0.40 / $1.75 | 205k | |
| 63 | GPT-5 | OpenAI | 1174 | 59.3% | 68 | $1.25 / $10.00 | 400k | |
| 64 | GPT-5.1 | OpenAI | 1168 | 55.9% | 69 | $1.25 / $10.00 | 400k | |
| 65 | Solar Pro 4 | Upstage | 1167 | 40.9% | 70 | $0.15 / $0.60 | 524k | |
| 66 | MiniMax M2.5 | MiniMax | 1165 | 55.5% | 71 | $0.295 / $1.20 | 198k | |
| 67 | Claude Opus 4.1 | Anthropic | 1160 | 58.4% | 72 | $15.00 / $75.00 | 200k | |
| 68 | Grok 4.3 | SpaceXAI | 1160 | 42.5% | 73 | $1.25 / $2.50 | 1M | |
| 69 | Claude Sonnet 4.5 | Anthropic | 1155 | 51.1% | 75 | $3.00 / $15.00 | 1M | |
| 70 | Gemini 3 Flash Preview | 1155 | 58.3% | 76 | $0.50 / $3.00 | 1.05M | ||
| 71 | Inkling | Thinking Machines | 1151 | 37.2% | 77 | $1.00 / $4.05 | 524k | |
| 72 | GPT-5.3-Codex | OpenAI | 1150 | 51.2% | 78 | $1.75 / $14.00 | 400k | |
| 73 | Step 3.7 Flash | StepFun | 1143 | 37.1% | 79 | $0.20 / $1.15 | 262k | |
| 74 | GLM 4.6 | Z.ai | 1140 | 54.8% | 81 | $0.50 / $2.00 | 205k | |
| 75 | GLM 4.5 | Z.ai | 1134 | 54.4% | 82 | $0.60 / $2.20 | 131k | |
| 76 | DeepSeek V3.2 Exp | DeepSeek | 1133 | 53.0% | 83 | $0.27 / $0.41 | 164k | |
| 77 | Qwen3.5 397B A17B | Qwen | 1129 | 50.2% | 86 | $0.45 / $3.00 | 262k | |
| 78 | GPT-5.1-Codex | OpenAI | 1127 | 50.5% | 88 | $1.25 / $10.00 | 400k | |
| 79 | Nemotron 3 Ultra | NVIDIA | 1126 | 35.3% | 89 | $0.50 / $2.20 | 262k | |
| 80 | Hy3 | Tencent | 1125 | 38.6% | 90 | $0.0825 / $0.33 | 262k | |
| 81 | GLM 4.7 Flash | Z.ai | 1124 | 49.7% | 91 | $0.0605 / $0.40 | 200k | |
| 82 | DeepSeek V3.1 Terminus | DeepSeek | 1120 | 52.5% | 93 | $0.27 / $1.00 | 164k | |
| 83 | DeepSeek V3.2 | DeepSeek | 1120 | 46.5% | 94 | $0.26 / $0.38 | 164k | |
| 84 | GPT-5 Mini | OpenAI | 1118 | 46.5% | 95 | $0.25 / $2.00 | 400k | |
| 85 | Muse Glimmer 30B | Meta | 1109 | 29.8% | 96 | $0.35 / $1.50 | 131k | |
| 86 | Gemini 2.5 Pro | 1100 | 54.2% | 98 | $1.25 / $10.00 | 1.05M | ||
| 87 | Solar Mini 4 | Upstage | 1095 | 27.7% | 99 | $0.05 / $0.20 | 524k | |
| 88 | Qwen3.5 Plus 2026-02-15 | Qwen | 1094 | 42.6% | 100 | $0.26 / $1.56 | 1M | |
| 89 | Qwen3 Coder 480B A35B | Qwen | 1088 | 58.7% | 102 | $0.30 / $1.00 | 262k | |
| 90 | Claude Haiku 4.5 | Anthropic | 1086 | 44.7% | 103 | $1.00 / $5.00 | 200k | |
| 91 | R1 0528 | DeepSeek | 1086 | 49.3% | 104 | $0.50 / $2.15 | 164k | |
| 92 | GLM 4.5 Air | Z.ai | 1083 | 48.4% | 105 | $0.13 / $0.85 | 131k | |
| 93 | Nemotron 3.5 Super VL | NVIDIA | 1082 | 27.5% | 107 | $0.15 / $0.50 | 1.05M | |
| 94 | GPT-5.1-Codex-Mini | OpenAI | 1081 | 43.4% | 108 | $0.25 / $2.00 | 400k | |
| 95 | DeepSeek V3.1 | DeepSeek | 1073 | 47.1% | 109 | $0.25 / $0.95 | 164k | |
| 96 | Mistral Large 3 2512 | Mistral | 1069 | 41.5% | 110 | $0.50 / $1.50 | 262k | |
| 97 | GPT-4.1 | OpenAI | 1068 | 59.1% | 111 | $2.00 / $8.00 | 1.05M | |
| 98 | Mistral Medium 3.1 | Mistral | 1063 | 40.8% | 114 | $0.44 / $2.20 | 131k | |
| 99 | GPT-4.1 Mini | OpenAI | 1060 | 58.5% | 115 | $0.40 / $1.60 | 1.05M | |
| 100 | Gemini 2.5 Flash | 1055 | 44.3% | 116 | $0.30 / $2.50 | 1.05M | ||
| 101 | DeepSeek V3 | DeepSeek | 1042 | 43.7% | 119 | $0.257 / $1.03 | 164k | |
| 102 | GPT-5 Nano | OpenAI | 1034 | 46.5% | 121 | $0.05 / $0.40 | 400k | |
| 103 | Ministral 3 14B 2512 | Mistral | 1027 | 43.6% | 123 | $0.20 / $0.20 | 262k | |
| 104 | o3 | OpenAI | 1023 | 56.9% | 124 | $2.00 / $8.00 | 200k | |
| 105 | Gemini 3.1 Flash Lite Preview | 1018 | 33.7% | 125 | $0.25 / $1.50 | 1.05M | ||
| 106 | Mistral Medium 3 | Mistral | 1007 | 45.2% | 127 | $0.44 / $2.20 | 131k | |
| 107 | o4 Mini (batch) | OpenAI | 992 | 50.0% | 128 | $0.55 / $2.20 | 200k | |
| 108 | gpt-oss-120b | OpenAI | 981 | 40.5% | 129 | $0.15 / $0.60 | 131k | |
| 109 | Ministral 3 8B 2512 | Mistral | 979 | 38.7% | 130 | $0.15 / $0.15 | 262k | |
| 110 | Kimi K2 0711 | MoonshotAI | 963 | 46.4% | 131 | $0.57 / $2.30 | 131k | |
| 111 | GPT-4.1 Nano | OpenAI | 959 | 49.6% | 133 | $0.10 / $0.40 | 1.05M | |
| 112 | Codestral 2508 | Mistral | 957 | 36.3% | 134 | $0.30 / $0.90 | 256k | |
| 113 | Qwen3 235B A22B Thinking 2507 | Qwen | 946 | 34.2% | 136 | $0.45 / $3.50 | 128k | |
| 114 | Qwen3 235B A22B Instruct 2507 | Qwen | 940 | 35.0% | 137 | $0.14 / $0.80 | 262k | |
| 115 | Ministral 3 3B 2512 | Mistral | 937 | 33.0% | 138 | $0.10 / $0.10 | 131k | |
| 116 | GPT-4o | OpenAI | 895 | 42.3% | 141 | $2.50 / $10.00 | 128k | |
| 117 | Qwen3 30B A3B | Qwen | 887 | 33.9% | 142 | $0.12 / $0.50 | 41k | |
| 118 | Mistral Small 3.2 24B | Mistral | 877 | 39.4% | 143 | $0.10 / $0.30 | 256k | |
| 119 | Llama 4 Maverick | Meta Llama | 827 | 33.7% | 145 | $0.35 / $1.00 | 524k | |
| 120 | Llama 4 Scout | Meta Llama | 762 | 27.4% | 146 | $0.10 / $0.30 | 1.31M |
The field and the frontier above are the whole board and do not narrow with this table: a frontier drawn through 120 of 120 models would say nothing beats them on both while something in the same board does. The models this table holds are drawn white in the figures instead.
An Elo from pairwise human preference votes: a higher figure means the model's output was preferred more often against the field it was matched with. Win rate is the share of matchups won. Both shift as new models enter the arena, neither is a measure of correctness, and the source's own rank counts models this catalog does not carry.
Source: OpenRouter (openrouter.ai/models), as of 17 Nov 16:29 UTC. sha256 0bb53a77713f over 853,270 bytes.
Catalog: OpenRouter's public model list.
Intelligence, coding and agentic indexes: Artificial Analysis, as published by OpenRouter.
Elo, win rate and rank: Design Arena, as published by OpenRouter.
Vitna ran none of these evaluations and adjusted none of these figures.
