Get started

Godot game development · Agents

Design Arena's Elo for godot game development · agents, from pairwise human preference votes, as OpenRouter carries it. 34 models ranked, as carried in OpenRouter's catalog.

retrieved sha256 · 0bb53a77713fwww.designarena.ai ↗

Most capable1296Claude Fable 5.1Anthropic
Best value1435GLM 4.71058 at $0.738 blended per M
Newest ranked1242Gemini 3.8 Flashlisted 2 Sep 2026

8 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
The attractive quadrant$1.00$10.0092411101296Blended list price per M tokens, log scaleEloClaude Fable 5.1: 1296 · $20.00 blended · Anthropic$20.00129608 Claude Fable 5.11296 · $20.00 blended · AnthropicClaude Fable 5: 1261 · $20.00 blended · Anthropic$20.001261Claude Fable 51261 · $20.00 blended · AnthropicClaude Opus 5: 1250 · $10.00 blended · Anthropic$10.00125007 Claude Opus 51250 · $10.00 blended · AnthropicGrok 4.6: 1247 · $3.00 blended · SpaceXAI$3.00124706 Grok 4.61247 · $3.00 blended · SpaceXAIGemini 3.8 Flash: 1242 · $1.65 blended · Google$1.65124205 Gemini 3.8 Flash1242 · $1.65 blended · GoogleGemini 3.7 Flash: 1230 · $1.50 blended · Google$1.50123004 Gemini 3.7 Flash1230 · $1.50 blended · GoogleClaude Sonnet 4.6: 1226 · $6.00 blended · Anthropic$6.001226Claude Sonnet 4.61226 · $6.00 blended · AnthropicKimi K2.5: 1219 · $1.00 blended · MoonshotAI$1.00121903 Kimi K2.51219 · $1.00 blended · MoonshotAIMuse Spark 1.3: 1210 · $2.00 blended · Meta$2.001210Muse Spark 1.31210 · $2.00 blended · MetaClaude Opus 4.8: 1202 · $10.00 blended · Anthropic$10.001202Claude Opus 4.81202 · $10.00 blended · AnthropicGrok 4.5: 1196 · $3.00 blended · SpaceXAI$3.001196Grok 4.51196 · $3.00 blended · SpaceXAIKimi K3: 1193 · $4.144 blended · MoonshotAI$4.1441193Kimi K31193 · $4.144 blended · MoonshotAIClaude Sonnet 5: 1191 · $4.00 blended · Anthropic$4.001191Claude Sonnet 51191 · $4.00 blended · AnthropicGLM 4.6: 1180 · $0.875 blended · Z.ai$0.875118002 GLM 4.61180 · $0.875 blended · Z.aiGemini 3 Flash Preview: 1161 · $1.125 blended · Google$1.1251161Gemini 3 Flash Preview1161 · $1.125 blended · GoogleQwen3.7 Max: 1157 · $2.213 blended · Qwen$2.2131157Qwen3.7 Max1157 · $2.213 blended · QwenGLM 5: 1144 · $1.55 blended · Z.ai$1.551144GLM 51144 · $1.55 blended · Z.aiGLM 5.2: 1142 · $1.705 blended · Z.ai$1.7051142GLM 5.21142 · $1.705 blended · Z.aiGPT-5.2: 1142 · $4.813 blended · OpenAI$4.8131142GPT-5.21142 · $4.813 blended · OpenAIGPT-5.2-Codex: 1142 · $4.813 blended · OpenAI$4.8131142GPT-5.2-Codex1142 · $4.813 blended · OpenAIGPT-5.5: 1142 · $11.25 blended · OpenAI$11.251142GPT-5.51142 · $11.25 blended · OpenAIGPT-5.4: 1135 · $5.625 blended · OpenAI$5.6251135GPT-5.41135 · $5.625 blended · OpenAIGemini 3.1 Pro Preview: 1131 · $4.50 blended · Google$4.501131Gemini 3.1 Pro Preview1131 · $4.50 blended · GoogleGPT-5.3-Codex: 1124 · $4.813 blended · OpenAI$4.8131124GPT-5.3-Codex1124 · $4.813 blended · OpenAIKimi K2.7 Code: 1115 · $1.463 blended · MoonshotAI$1.4631115Kimi K2.7 Code1115 · $1.463 blended · MoonshotAIKimi K2.6: 1090 · $1.34 blended · MoonshotAI$1.341090Kimi K2.61090 · $1.34 blended · MoonshotAIGrok 4.20: 1089 · $1.563 blended · SpaceXAI$1.5631089Grok 4.201089 · $1.563 blended · SpaceXAIMuse Spark 1.1: 1073 · $2.00 blended · Meta$2.001073Muse Spark 1.11073 · $2.00 blended · MetaGemini 3.5 Flash: 1069 · $3.375 blended · Google$3.3751069Gemini 3.5 Flash1069 · $3.375 blended · GoogleDeepSeek V4 Pro 0423: 1059 · $1.05 blended · DeepSeek$1.051059DeepSeek V4 Pro 04231059 · $1.05 blended · DeepSeekGLM 4.7: 1058 · $0.738 blended · Z.ai$0.738105801 GLM 4.71058 · $0.738 blended · Z.aiGLM 5.1: 1027 · $2.15 blended · Z.ai$2.151027GLM 5.11027 · $2.15 blended · Z.aiGLM 5V Turbo: 928 · $1.90 blended · Z.ai$1.90928GLM 5V Turbo928 · $1.90 blended · Z.aiGrok 4.3: 924 · $1.563 blended · SpaceXAI$1.563924Grok 4.3924 · $1.563 blended · SpaceXAI
  1. 01GLM 4.71058 · $0.738 blended
  2. 02GLM 4.61180 · $0.875 blended · +122 at 1.2x
  3. 03Kimi K2.51219 · $1.00 blended · +39 at 1.1x
  4. 04Gemini 3.7 Flash1230 · $1.50 blended · +11 at 1.5x
  5. 05Gemini 3.8 Flash1242 · $1.65 blended · +12 at 1.1x
  6. 06Grok 4.61247 · $3.00 blended · +5 at 1.8x
  7. 07Claude Opus 51250 · $10.00 blended · +3 at 3.3x
  8. 08Claude Fable 5.11296 · $20.00 blended · +46 at 2.0x

34 of 34 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. 7 of 34 priced models sit in the attractive quadrant: at or above the median Elo of 1143 and at or below the median blended price of $2.181. The tinted corner is that quadrant. 1 of the 34 crosses matches the selection below and is drawn white.

1 of 34.

Design Arena · Elo

The field and the frontier above are the whole board and do not narrow with this table: a frontier drawn through 1 of 34 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.

What the score tells you

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.

Sources

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.