Get started

Full stack · Agents

Design Arena's Elo for full stack · agents, from pairwise human preference votes, as OpenRouter carries it. 44 models ranked, as carried in OpenRouter's catalog.

retrieved sha256 · 0bb53a77713fwww.designarena.ai ↗

Most capable1397Claude Fable 5.2Anthropic
Best value2238MiniMax M31175 at $0.525 blended per M
Newest ranked1397Claude Fable 5.2listed 9 Nov 2026

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
The attractive quadrant$1.00$10.0094811731397Blended list price per M tokens, log scaleEloClaude Fable 5.2: 1397 · $16.00 blended · Anthropic$16.00139707 Claude Fable 5.21397 · $16.00 blended · AnthropicClaude Opus 5.5: 1391 · $8.00 blended · Anthropic$8.00139106 Claude Opus 5.51391 · $8.00 blended · AnthropicKimi K3.1 Pro: 1321 · $2.281 blended · MoonshotAI$2.281132105 Kimi K3.1 Pro1321 · $2.281 blended · MoonshotAIClaude Fable 5.1: 1300 · $20.00 blended · Anthropic$20.001300Claude Fable 5.11300 · $20.00 blended · AnthropicKimi K3: 1289 · $4.144 blended · MoonshotAI$4.1441289Kimi K31289 · $4.144 blended · MoonshotAIMuse Spark 1.3: 1287 · $2.00 blended · Meta$2.00128704 Muse Spark 1.31287 · $2.00 blended · MetaClaude Opus 5: 1280 · $10.00 blended · Anthropic$10.001280Claude Opus 51280 · $10.00 blended · AnthropicClaude Fable 5: 1254 · $20.00 blended · Anthropic$20.001254Claude Fable 51254 · $20.00 blended · AnthropicGrok 4.6: 1237 · $3.00 blended · SpaceXAI$3.001237Grok 4.61237 · $3.00 blended · SpaceXAIClaude Opus 4.8: 1224 · $10.00 blended · Anthropic$10.001224Claude Opus 4.81224 · $10.00 blended · AnthropicClaude Sonnet 5: 1224 · $4.00 blended · Anthropic$4.001224Claude Sonnet 51224 · $4.00 blended · AnthropicGrok 4.5: 1223 · $3.00 blended · SpaceXAI$3.001223Grok 4.51223 · $3.00 blended · SpaceXAIGemini 3.8 Flash: 1216 · $1.65 blended · Google$1.65121603 Gemini 3.8 Flash1216 · $1.65 blended · GoogleGLM 5.2: 1215 · $1.705 blended · Z.ai$1.7051215GLM 5.21215 · $1.705 blended · Z.aiClaude Opus 4.6: 1194 · $10.00 blended · Anthropic$10.001194Claude Opus 4.61194 · $10.00 blended · AnthropicClaude Sonnet 4.6: 1186 · $6.00 blended · Anthropic$6.001186Claude Sonnet 4.61186 · $6.00 blended · AnthropicMuse Spark 1.2: 1183 · $2.00 blended · Meta$2.001183Muse Spark 1.21183 · $2.00 blended · MetaGemini 3.7 Flash: 1182 · $1.50 blended · Google$1.50118202 Gemini 3.7 Flash1182 · $1.50 blended · GoogleMiniMax M3: 1175 · $0.525 blended · MiniMax$0.525117501 MiniMax M31175 · $0.525 blended · MiniMaxMuse Spark 1.1: 1170 · $2.00 blended · Meta$2.001170Muse Spark 1.11170 · $2.00 blended · MetaGemini 3.5 Flash: 1170 · $3.375 blended · Google$3.3751170Gemini 3.5 Flash1170 · $3.375 blended · GoogleQwen3.7 Max: 1167 · $2.213 blended · Qwen$2.2131167Qwen3.7 Max1167 · $2.213 blended · QwenGemini 3.6 Flash: 1153 · $1.50 blended · Google$1.501153Gemini 3.6 Flash1153 · $1.50 blended · GoogleKimi K2.7 Code: 1150 · $1.463 blended · MoonshotAI$1.4631150Kimi K2.7 Code1150 · $1.463 blended · MoonshotAIGLM 5.1: 1141 · $2.15 blended · Z.ai$2.151141GLM 5.11141 · $2.15 blended · Z.aiClaude Opus 4.5: 1130 · $10.00 blended · Anthropic$10.001130Claude Opus 4.51130 · $10.00 blended · AnthropicKimi K2.6: 1129 · $1.34 blended · MoonshotAI$1.341129Kimi K2.61129 · $1.34 blended · MoonshotAIGLM 5V Turbo: 1123 · $1.90 blended · Z.ai$1.901123GLM 5V Turbo1123 · $1.90 blended · Z.aiGLM 5: 1096 · $1.55 blended · Z.ai$1.551096GLM 51096 · $1.55 blended · Z.aiKimi K2.5: 1087 · $1.00 blended · MoonshotAI$1.001087Kimi K2.51087 · $1.00 blended · MoonshotAIGPT-5.1-Codex: 1086 · $3.438 blended · OpenAI$3.4381086GPT-5.1-Codex1086 · $3.438 blended · OpenAIGPT-5.5: 1063 · $11.25 blended · OpenAI$11.251063GPT-5.51063 · $11.25 blended · OpenAIGemini 3.1 Pro Preview: 1041 · $4.50 blended · Google$4.501041Gemini 3.1 Pro Preview1041 · $4.50 blended · GoogleGemini 3 Flash Preview: 1037 · $1.125 blended · Google$1.1251037Gemini 3 Flash Preview1037 · $1.125 blended · GoogleGrok 4.20: 1028 · $1.563 blended · SpaceXAI$1.5631028Grok 4.201028 · $1.563 blended · SpaceXAIClaude Sonnet 4.5: 1024 · $6.00 blended · Anthropic$6.001024Claude Sonnet 4.51024 · $6.00 blended · AnthropicGLM 4.7: 1023 · $0.738 blended · Z.ai$0.7381023GLM 4.71023 · $0.738 blended · Z.aiGPT-5.2: 1016 · $4.813 blended · OpenAI$4.8131016GPT-5.21016 · $4.813 blended · OpenAIGLM 4.6: 1003 · $0.875 blended · Z.ai$0.8751003GLM 4.61003 · $0.875 blended · Z.aiGPT-5.4: 991 · $5.625 blended · OpenAI$5.625991GPT-5.4991 · $5.625 blended · OpenAIGrok 4.3: 981 · $1.563 blended · SpaceXAI$1.563981Grok 4.3981 · $1.563 blended · SpaceXAIGPT-5.2-Codex: 966 · $4.813 blended · OpenAI$4.813966GPT-5.2-Codex966 · $4.813 blended · OpenAIGPT-5.3-Codex: 957 · $4.813 blended · OpenAI$4.813957GPT-5.3-Codex957 · $4.813 blended · OpenAIDeepSeek V4 Pro 0423: 948 · $1.05 blended · DeepSeek$1.05948DeepSeek V4 Pro 0423948 · $1.05 blended · DeepSeek
  1. 01MiniMax M31175 · $0.525 blended
  2. 02Gemini 3.7 Flash1182 · $1.50 blended · +7 at 2.9x
  3. 03Gemini 3.8 Flash1216 · $1.65 blended · +34 at 1.1x
  4. 04Muse Spark 1.31287 · $2.00 blended · +71 at 1.2x
  5. 05Kimi K3.1 Pro1321 · $2.281 blended · +34 at 1.1x
  6. 06Claude Opus 5.51391 · $8.00 blended · +70 at 3.5x
  7. 07Claude Fable 5.21397 · $16.00 blended · +6 at 2.0x

44 of 44 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. 9 of 44 priced models sit in the attractive quadrant: at or above the median Elo of 1160 and at or below the median blended price of $2.64. The tinted corner is that quadrant. 6 of the 44 crosses match the selection below and are drawn white.

6 of 44.

Design Arena · Elo
PositionModelAuthorEloWin rateSource rankIn / out per MContextListed
14GLM 5.2Z.ai121560.0%15$0.007 / $6.801.05M
25GLM 5.1Z.ai114153.0%26$1.40 / $4.40205k
28GLM 5V TurboZ.ai112352.1%29$1.20 / $4.00203k
29GLM 5Z.ai109651.7%30$1.00 / $3.20205k
37GLM 4.7Z.ai102345.1%39$0.40 / $1.75205k
39GLM 4.6Z.ai100342.3%41$0.50 / $2.00205k

The field and the frontier above are the whole board and do not narrow with this table: a frontier drawn through 6 of 44 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.