Get started

Agentic slides · Agents

Design Arena's Elo for agentic 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 capable1294Claude Opus 4.8Anthropic
Best value954Gemini 3 Flash Preview1073 at $1.125 blended per M
Newest ranked1294Claude Opus 4.8listed 27 May 2026

4 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$10.00107211831294Blended list price per M tokens, log scaleEloClaude Opus 4.8: 1294 · $10.00 blended · Anthropic$10.00129404 Claude Opus 4.81294 · $10.00 blended · AnthropicGLM 5.1: 1245 · $2.15 blended · Z.ai$2.15124503 GLM 5.11245 · $2.15 blended · Z.aiGemini 3.5 Flash: 1244 · $3.375 blended · Google$3.3751244Gemini 3.5 Flash1244 · $3.375 blended · GoogleKimi K2.6: 1187 · $1.34 blended · MoonshotAI$1.34118702 Kimi K2.61187 · $1.34 blended · MoonshotAIGLM 5V Turbo: 1171 · $1.90 blended · Z.ai$1.901171GLM 5V Turbo1171 · $1.90 blended · Z.aiGPT-5.5: 1150 · $11.25 blended · OpenAI$11.251150GPT-5.51150 · $11.25 blended · OpenAIGemini 3.1 Pro Preview: 1112 · $4.50 blended · Google$4.501112Gemini 3.1 Pro Preview1112 · $4.50 blended · GoogleGemini 3 Flash Preview: 1073 · $1.125 blended · Google$1.125107301 Gemini 3 Flash Preview1073 · $1.125 blended · GoogleGrok 4.3: 1072 · $1.563 blended · SpaceXAI$1.5631072Grok 4.31072 · $1.563 blended · SpaceXAI
  1. 01Gemini 3 Flash Preview1073 · $1.125 blended
  2. 02Kimi K2.61187 · $1.34 blended · +114 at 1.2x
  3. 03GLM 5.11245 · $2.15 blended · +58 at 1.6x
  4. 04Claude Opus 4.81294 · $10.00 blended · +49 at 4.7x

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. 3 of 9 priced models sit in the attractive quadrant: at or above the median Elo of 1171 and at or below the median blended price of $2.15. The tinted corner is that quadrant.

All 9, best first.

Design Arena · Elo
PositionModelAuthorEloWin rateSource rankIn / out per MContextListed
01Claude Opus 4.8Anthropic129464.8%1$5.00 / $25.001M
02GLM 5.1Z.ai124554.4%2$1.40 / $4.40205k
03Gemini 3.5 FlashGoogle124457.5%3$1.50 / $9.001.05M
04Kimi K2.6MoonshotAI118745.8%4$0.65 / $3.41262k
05GLM 5V TurboZ.ai117151.6%5$1.20 / $4.00203k
06GPT-5.5OpenAI115043.5%6$5.00 / $30.001.05M
07Gemini 3.1 Pro PreviewGoogle111233.8%7$2.00 / $12.001.05M
08Gemini 3 Flash PreviewGoogle107339.3%8$0.50 / $3.001.05M
09Grok 4.3SpaceXAI107231.9%9$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.