Get started

Agentic HTML slides · Agents

Design Arena's Elo for agentic html slides · agents, from pairwise human preference votes, as OpenRouter carries it. 9 models ranked, as carried in OpenRouter's catalog.

retrieved sha256 · 0bb53a77713fwww.designarena.ai ↗

Most capable1254Claude Fable 5Anthropic
Best value931Kimi K2.61248 at $1.34 blended per M
Newest ranked1254Claude Fable 5listed 9 Jun 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$10.00106611601254Blended list price per M tokens, log scaleEloClaude Fable 5: 1254 · $20.00 blended · Anthropic$20.00125402 Claude Fable 51254 · $20.00 blended · AnthropicKimi K2.6: 1248 · $1.34 blended · MoonshotAI$1.34124801 Kimi K2.61248 · $1.34 blended · MoonshotAIClaude Opus 4.8: 1227 · $10.00 blended · Anthropic$10.001227Claude Opus 4.81227 · $10.00 blended · AnthropicGemini 3.1 Pro Preview: 1226 · $4.50 blended · Google$4.501226Gemini 3.1 Pro Preview1226 · $4.50 blended · GoogleGLM 5.1: 1205 · $2.15 blended · Z.ai$2.151205GLM 5.11205 · $2.15 blended · Z.aiGemini 3.5 Flash: 1162 · $3.375 blended · Google$3.3751162Gemini 3.5 Flash1162 · $3.375 blended · GoogleGLM 5V Turbo: 1134 · $1.90 blended · Z.ai$1.901134GLM 5V Turbo1134 · $1.90 blended · Z.aiGPT-5.5: 1084 · $11.25 blended · OpenAI$11.251084GPT-5.51084 · $11.25 blended · OpenAIGrok 4.3: 1066 · $1.563 blended · SpaceXAI$1.5631066Grok 4.31066 · $1.563 blended · SpaceXAI
  1. 01Kimi K2.61248 · $1.34 blended
  2. 02Claude Fable 51254 · $20.00 blended · +6 at 15x

9 of 9 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. 2 of 9 priced models sit in the attractive quadrant: at or above the median Elo of 1205 and at or below the median blended price of $3.375. The tinted corner is that quadrant. 2 of the 9 crosses match the selection below and are drawn white.

2 of 9.

Design Arena · Elo
PositionModelAuthorEloWin rateSource rankIn / out per MContextListed
04Gemini 3.1 Pro PreviewGoogle122655.8%4$2.00 / $12.001.05M
06Gemini 3.5 FlashGoogle116245.8%6$1.50 / $9.001.05M

The field and the frontier above are the whole board and do not narrow with this table: a frontier drawn through 2 of 9 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.