Get started

HTML slides · Agents

Design Arena's Elo for html slides · agents, from pairwise human preference votes, as OpenRouter carries it. 25 models ranked, as carried in OpenRouter's catalog.

retrieved sha256 · 0bb53a77713fwww.designarena.ai ↗

Most capable1391Claude Fable 5.1Anthropic
Best value2955GLM 5.31189 at $0.402 blended per M
Newest ranked1126Muse Wonderlisted 12 Oct 2026

2 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$10.0090611491391Blended list price per M tokens, log scaleEloClaude Fable 5.1: 1391 · $20.00 blended · Anthropic$20.00139102 Claude Fable 5.11391 · $20.00 blended · AnthropicGLM 5.3: 1189 · $0.402 blended · Z.ai$0.402118901 GLM 5.31189 · $0.402 blended · Z.aiGrok 4.20: 1180 · $1.563 blended · SpaceXAI$1.5631180Grok 4.201180 · $1.563 blended · SpaceXAIClaude Fable 5: 1174 · $20.00 blended · Anthropic$20.001174Claude Fable 51174 · $20.00 blended · AnthropicKimi K3: 1152 · $4.144 blended · MoonshotAI$4.1441152Kimi K31152 · $4.144 blended · MoonshotAIGrok 4.6: 1146 · $3.00 blended · SpaceXAI$3.001146Grok 4.61146 · $3.00 blended · SpaceXAIMuse Wonder: 1126 · $8.00 blended · Meta$8.001126Muse Wonder1126 · $8.00 blended · MetaClaude Opus 4.8: 1118 · $10.00 blended · Anthropic$10.001118Claude Opus 4.81118 · $10.00 blended · AnthropicClaude Sonnet 5: 1113 · $4.00 blended · Anthropic$4.001113Claude Sonnet 51113 · $4.00 blended · AnthropicGrok 4.5: 1101 · $3.00 blended · SpaceXAI$3.001101Grok 4.51101 · $3.00 blended · SpaceXAIKimi K2.7 Code: 1099 · $1.463 blended · MoonshotAI$1.4631099Kimi K2.7 Code1099 · $1.463 blended · MoonshotAIMuse Spark 1.1: 1092 · $2.00 blended · Meta$2.001092Muse Spark 1.11092 · $2.00 blended · MetaKimi K2.6: 1081 · $1.34 blended · MoonshotAI$1.341081Kimi K2.61081 · $1.34 blended · MoonshotAIMiniMax M3: 1077 · $0.525 blended · MiniMax$0.5251077MiniMax M31077 · $0.525 blended · MiniMaxGLM 5.2: 1072 · $1.705 blended · Z.ai$1.7051072GLM 5.21072 · $1.705 blended · Z.aiGLM 5.1: 1067 · $2.15 blended · Z.ai$2.151067GLM 5.11067 · $2.15 blended · Z.aiQwen3.7 Max: 1054 · $2.213 blended · Qwen$2.2131054Qwen3.7 Max1054 · $2.213 blended · QwenGemini 3.1 Pro Preview: 1050 · $4.50 blended · Google$4.501050Gemini 3.1 Pro Preview1050 · $4.50 blended · GoogleGemini 3.6 Flash: 1045 · $1.50 blended · Google$1.501045Gemini 3.6 Flash1045 · $1.50 blended · GoogleGLM 5: 1044 · $1.55 blended · Z.ai$1.551044GLM 51044 · $1.55 blended · Z.aiGemini 3.5 Flash: 1040 · $3.375 blended · Google$3.3751040Gemini 3.5 Flash1040 · $3.375 blended · GoogleMuse Spark 1.2: 1029 · $2.00 blended · Meta$2.001029Muse Spark 1.21029 · $2.00 blended · MetaGLM 5V Turbo: 1017 · $1.90 blended · Z.ai$1.901017GLM 5V Turbo1017 · $1.90 blended · Z.aiGPT-5.5: 964 · $11.25 blended · OpenAI$11.25964GPT-5.5964 · $11.25 blended · OpenAIGrok 4.3: 906 · $1.563 blended · SpaceXAI$1.563906Grok 4.3906 · $1.563 blended · SpaceXAI
  1. 01GLM 5.31189 · $0.402 blended
  2. 02Claude Fable 5.11391 · $20.00 blended · +202 at 50x

25 of 25 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. 5 of 25 priced models sit in the attractive quadrant: at or above the median Elo of 1081 and at or below the median blended price of $2.15. The tinted corner is that quadrant.

All 25, best first.

Design Arena · Elo
PositionModelAuthorEloWin rateSource rankIn / out per MContextListed
01Claude Fable 5.1Anthropic139156.5%1$10.00 / $50.001M
02GLM 5.3Z.ai118939.1%2$0.0699 / $1.401.05M
03Grok 4.20SpaceXAI118045.7%3$1.25 / $2.502M
04Claude Fable 5Anthropic117463.2%4$10.00 / $50.001M
05Kimi K3MoonshotAI115255.6%5$0.192 / $16.001.05M
06Grok 4.6SpaceXAI114660.5%6$2.00 / $6.00500k
07Muse WonderMeta112614.1%7$4.00 / $20.001.05M
08Claude Opus 4.8Anthropic111858.1%8$5.00 / $25.001M
09Claude Sonnet 5Anthropic111353.7%9$2.00 / $10.001M
10Grok 4.5SpaceXAI110152.5%10$2.00 / $6.00500k
11Kimi K2.7 CodeMoonshotAI109953.9%11$0.70 / $3.75262k
12Muse Spark 1.1Meta109251.9%12$1.25 / $4.251.05M
13Kimi K2.6MoonshotAI108152.3%13$0.65 / $3.41262k
14MiniMax M3MiniMax107746.9%14$0.30 / $1.201.05M
15GLM 5.2Z.ai107249.6%15$0.007 / $6.801.05M
16GLM 5.1Z.ai106748.8%16$1.40 / $4.40205k
17Qwen3.7 MaxQwen105443.4%17$1.48 / $4.421M
18Gemini 3.1 Pro PreviewGoogle105048.4%18$2.00 / $12.001.05M
19Gemini 3.6 FlashGoogle104542.0%19$0.75 / $3.751.05M
20GLM 5Z.ai104445.1%20$1.00 / $3.20205k
21Gemini 3.5 FlashGoogle104046.6%21$1.50 / $9.001.05M
22Muse Spark 1.2Meta102939.9%22$1.25 / $4.251.05M
23GLM 5V TurboZ.ai101744.6%23$1.20 / $4.00203k
24GPT-5.5OpenAI96435.6%24$5.00 / $30.001.05M
25Grok 4.3SpaceXAI90628.6%25$1.25 / $2.501M
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.