Get started

spreadsheet · Agents

Design Arena's Elo for spreadsheet · agents, from pairwise human preference votes, as OpenRouter carries it. 32 models ranked, as carried in OpenRouter's catalog.

retrieved sha256 · 0bb53a77713fwww.designarena.ai ↗

Most capable1429Claude Fable 5.2Anthropic
Best value8322DeepSeek V4.1 Flash 10171265 at $0.152 blended per M
Newest ranked1220Gemini 4 Carbonlisted 10 Nov 2026

6 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$10.0091811741429Blended list price per M tokens, log scaleEloClaude Fable 5.2: 1429 · $16.00 blended · Anthropic$16.00142906 Claude Fable 5.21429 · $16.00 blended · AnthropicGrok 4.7: 1420 · $3.00 blended · SpaceXAI$3.00142005 Grok 4.71420 · $3.00 blended · SpaceXAIClaude Fable 5.1: 1344 · $20.00 blended · Anthropic$20.001344Claude Fable 5.11344 · $20.00 blended · AnthropicKimi K3.1 Pro: 1318 · $2.281 blended · MoonshotAI$2.281131804 Kimi K3.1 Pro1318 · $2.281 blended · MoonshotAIGLM 5.1: 1315 · $2.15 blended · Z.ai$2.15131503 GLM 5.11315 · $2.15 blended · Z.aiClaude Opus 5.5: 1291 · $8.00 blended · Anthropic$8.001291Claude Opus 5.51291 · $8.00 blended · AnthropicGrok 4.6: 1277 · $3.00 blended · SpaceXAI$3.001277Grok 4.61277 · $3.00 blended · SpaceXAIKimi K2.6: 1276 · $1.34 blended · MoonshotAI$1.34127602 Kimi K2.61276 · $1.34 blended · MoonshotAIDeepSeek V4.1 Flash 1017: 1265 · $0.152 blended · DeepSeek$0.152126501 DeepSeek V4.1 Flash 10171265 · $0.152 blended · DeepSeekClaude Sonnet 5.5: 1253 · $4.00 blended · Anthropic$4.001253Claude Sonnet 5.51253 · $4.00 blended · AnthropicClaude Opus 5: 1242 · $10.00 blended · Anthropic$10.001242Claude Opus 51242 · $10.00 blended · AnthropicMuse Wonder: 1232 · $8.00 blended · Meta$8.001232Muse Wonder1232 · $8.00 blended · MetaGemini 4 Carbon: 1220 · $4.00 blended · Google$4.001220Gemini 4 Carbon1220 · $4.00 blended · GoogleGPT-6.1 Sol: 1209 · $4.00 blended · OpenAI$4.001209GPT-6.1 Sol1209 · $4.00 blended · OpenAIMiniMax M3: 1167 · $0.525 blended · MiniMax$0.5251167MiniMax M31167 · $0.525 blended · MiniMaxGemini 4 Argon: 1146 · $4.00 blended · Google$4.001146Gemini 4 Argon1146 · $4.00 blended · GoogleMuse Spark 1.3: 1124 · $2.00 blended · Meta$2.001124Muse Spark 1.31124 · $2.00 blended · MetaGrok 4.5: 1058 · $3.00 blended · SpaceXAI$3.001058Grok 4.51058 · $3.00 blended · SpaceXAIKimi K3: 1052 · $4.144 blended · MoonshotAI$4.1441052Kimi K31052 · $4.144 blended · MoonshotAIGemini 3.6 Flash: 1045 · $1.50 blended · Google$1.501045Gemini 3.6 Flash1045 · $1.50 blended · GoogleClaude Opus 4.8: 1039 · $10.00 blended · Anthropic$10.001039Claude Opus 4.81039 · $10.00 blended · AnthropicClaude Sonnet 5: 1033 · $4.00 blended · Anthropic$4.001033Claude Sonnet 51033 · $4.00 blended · AnthropicGemini 3.8 Flash: 1028 · $1.65 blended · Google$1.651028Gemini 3.8 Flash1028 · $1.65 blended · GoogleGemini 3.7 Flash: 1018 · $1.50 blended · Google$1.501018Gemini 3.7 Flash1018 · $1.50 blended · GoogleGLM 5.2: 1013 · $1.705 blended · Z.ai$1.7051013GLM 5.21013 · $1.705 blended · Z.aiMuse Spark 1.1: 1003 · $2.00 blended · Meta$2.001003Muse Spark 1.11003 · $2.00 blended · MetaClaude Opus 4.6: 995 · $10.00 blended · Anthropic$10.00995Claude Opus 4.6995 · $10.00 blended · AnthropicQwen3.7 Max: 993 · $2.213 blended · Qwen$2.213993Qwen3.7 Max993 · $2.213 blended · QwenMuse Spark 1.2: 992 · $2.00 blended · Meta$2.00992Muse Spark 1.2992 · $2.00 blended · MetaGemini 3.5 Flash: 985 · $3.375 blended · Google$3.375985Gemini 3.5 Flash985 · $3.375 blended · GoogleGrok 4.3: 932 · $1.563 blended · SpaceXAI$1.563932Grok 4.3932 · $1.563 blended · SpaceXAIGemini 3.1 Pro Preview: 918 · $4.50 blended · Google$4.50918Gemini 3.1 Pro Preview918 · $4.50 blended · Google
  1. 01DeepSeek V4.1 Flash 10171265 · $0.152 blended
  2. 02Kimi K2.61276 · $1.34 blended · +11 at 8.8x
  3. 03GLM 5.11315 · $2.15 blended · +39 at 1.6x
  4. 04Kimi K3.1 Pro1318 · $2.281 blended · +3 at 1.1x
  5. 05Grok 4.71420 · $3.00 blended · +102 at 1.3x
  6. 06Claude Fable 5.21429 · $16.00 blended · +9 at 5.3x

32 of 32 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 32 priced models sit in the attractive quadrant: at or above the median Elo of 1135 and at or below the median blended price of $3.00. The tinted corner is that quadrant. 8 of the 32 crosses match the selection below and are drawn white.

8 of 32.

Design Arena · Elo
PositionModelAuthorEloWin rateSource rankIn / out per MContextListed
01Claude Fable 5.2Anthropic142974.9%1$8.00 / $40.001M
03Claude Fable 5.1Anthropic134458.8%3$10.00 / $50.001M
06Claude Opus 5.5Anthropic129153.1%6$4.00 / $20.001M
10Claude Sonnet 5.5Anthropic125346.3%10$2.00 / $10.001M
11Claude Opus 5Anthropic124243.4%11$5.00 / $25.001M
21Claude Opus 4.8Anthropic103923.0%21$5.00 / $25.001M
22Claude Sonnet 5Anthropic103325.6%22$2.00 / $10.001M
27Claude Opus 4.6Anthropic99522.5%28$5.00 / $25.001M

The field and the frontier above are the whole board and do not narrow with this table: a frontier drawn through 8 of 32 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.