Get started

blender3d · Agents

Design Arena's Elo for blender3d · 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 capable1347Gemini 4 ArgonGoogle
Best value2030MiniMax M31066 at $0.525 blended per M
Newest ranked1347Gemini 4 Argonlisted 13 Oct 2026

5 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$10.0080710771347Blended list price per M tokens, log scaleEloGemini 4 Argon: 1347 · $4.00 blended · Google$4.00134705 Gemini 4 Argon1347 · $4.00 blended · GoogleGPT-6.1 Sol: 1244 · $4.00 blended · OpenAI$4.001244GPT-6.1 Sol1244 · $4.00 blended · OpenAIClaude Sonnet 5.5: 1237 · $4.00 blended · Anthropic$4.001237Claude Sonnet 5.51237 · $4.00 blended · AnthropicClaude Opus 5.5: 1225 · $8.00 blended · Anthropic$8.001225Claude Opus 5.51225 · $8.00 blended · AnthropicClaude Opus 5: 1201 · $10.00 blended · Anthropic$10.001201Claude Opus 51201 · $10.00 blended · AnthropicGrok 4.7: 1163 · $3.00 blended · SpaceXAI$3.00116304 Grok 4.71163 · $3.00 blended · SpaceXAIGemini 3.8 Flash: 1158 · $1.65 blended · Google$1.65115803 Gemini 3.8 Flash1158 · $1.65 blended · GoogleMuse Spark 1.3: 1145 · $2.00 blended · Meta$2.001145Muse Spark 1.31145 · $2.00 blended · MetaKimi K3: 1124 · $4.144 blended · MoonshotAI$4.1441124Kimi K31124 · $4.144 blended · MoonshotAIMuse Wonder: 1124 · $8.00 blended · Meta$8.001124Muse Wonder1124 · $8.00 blended · MetaGrok 4.6: 1121 · $3.00 blended · SpaceXAI$3.001121Grok 4.61121 · $3.00 blended · SpaceXAIGemini 3.7 Flash: 1112 · $1.50 blended · Google$1.50111202 Gemini 3.7 Flash1112 · $1.50 blended · GoogleClaude Opus 4.8: 1096 · $10.00 blended · Anthropic$10.001096Claude Opus 4.81096 · $10.00 blended · AnthropicMiniMax M3: 1066 · $0.525 blended · MiniMax$0.525106601 MiniMax M31066 · $0.525 blended · MiniMaxGemini 3.6 Flash: 1055 · $1.50 blended · Google$1.501055Gemini 3.6 Flash1055 · $1.50 blended · GoogleMuse Spark 1.2: 1053 · $2.00 blended · Meta$2.001053Muse Spark 1.21053 · $2.00 blended · MetaGrok 4.5: 1053 · $3.00 blended · SpaceXAI$3.001053Grok 4.51053 · $3.00 blended · SpaceXAIGemini 3.1 Pro Preview: 1037 · $4.50 blended · Google$4.501037Gemini 3.1 Pro Preview1037 · $4.50 blended · GoogleMuse Spark 1.1: 1009 · $2.00 blended · Meta$2.001009Muse Spark 1.11009 · $2.00 blended · MetaClaude Opus 4.6: 1008 · $10.00 blended · Anthropic$10.001008Claude Opus 4.61008 · $10.00 blended · AnthropicGLM 5.2: 983 · $1.705 blended · Z.ai$1.705983GLM 5.2983 · $1.705 blended · Z.aiQwen3.7 Max: 980 · $2.213 blended · Qwen$2.213980Qwen3.7 Max980 · $2.213 blended · QwenClaude Sonnet 5: 956 · $4.00 blended · Anthropic$4.00956Claude Sonnet 5956 · $4.00 blended · AnthropicGemini 3.5 Flash: 904 · $3.375 blended · Google$3.375904Gemini 3.5 Flash904 · $3.375 blended · GoogleGrok 4.3: 807 · $1.563 blended · SpaceXAI$1.563807Grok 4.3807 · $1.563 blended · SpaceXAI
  1. 01MiniMax M31066 · $0.525 blended
  2. 02Gemini 3.7 Flash1112 · $1.50 blended · +46 at 2.9x
  3. 03Gemini 3.8 Flash1158 · $1.65 blended · +46 at 1.1x
  4. 04Grok 4.71163 · $3.00 blended · +5 at 1.8x
  5. 05Gemini 4 Argon1347 · $4.00 blended · +184 at 1.3x

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 1096 and at or below the median blended price of $3.00. The tinted corner is that quadrant. 4 of the 25 crosses match the selection below and are drawn white.

4 of 25.

Design Arena · Elo
PositionModelAuthorEloWin rateSource rankIn / out per MContextListed
08Muse Spark 1.3Meta114556.3%8$1.25 / $4.251.05M
10Muse WonderMeta112435.9%10$4.00 / $20.001.05M
16Muse Spark 1.2Meta105342.9%16$1.25 / $4.251.05M
19Muse Spark 1.1Meta100935.9%19$1.25 / $4.251.05M

The field and the frontier above are the whole board and do not narrow with this table: a frontier drawn through 4 of 25 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.