Skip to content

Benchmark

BlenderWorld · Nature & Landscapes

Higher scores are better.

Models and systems measured
13
Scores recorded
13
Sources
1
IQ weight
1.01

Score distribution

49.4
Mean
50.3
Median
14.9
Std dev
29.2
10th percentile
67.4
90th percentile
24.9
Min
24.978.4
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.01 for chat models, measured over 11 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#Model or systemScore
1GPT-6 Astrabenchmark-owner paper run · 21 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard· Reported by BlenderWorld authors / Alibaba Token Hub· via BenchBoard docs78.4
2Claude Opus 5benchmark-owner paper run · 21 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard· Reported by BlenderWorld authors / Alibaba Token Hub· via BenchBoard docs67.4
3GPT-5.6 Solbenchmark-owner paper run · 21 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard· Reported by BlenderWorld authors / Alibaba Token Hub· via BenchBoard docs63.6
4Qwen3.8 Maxbenchmark-owner paper run · 21 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard· Reported by BlenderWorld authors / Alibaba Token Hub· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.58.6
5DeepSeek V4.1 Flashbenchmark-owner paper run · 21 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard· Reported by BlenderWorld authors / Alibaba Token Hub· via BenchBoard docs54.9
6Claude Opus 4.8benchmark-owner paper run · 21 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard· Reported by BlenderWorld authors / Alibaba Token Hub· via BenchBoard docs51.8
7GLM 5.3 Flashbenchmark-owner paper run · 21 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard· Reported by BlenderWorld authors / Alibaba Token Hub· via BenchBoard docs50.3
8Qwen 3.8 27Bbenchmark-owner paper run · 21 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard· Reported by BlenderWorld authors / Alibaba Token Hub· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.41.3
9Kimi K3benchmark-owner paper run · 21 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard· Reported by BlenderWorld authors / Alibaba Token Hub· via BenchBoard docs34.8
10MiniMax M3benchmark-owner paper run · 21 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard· Reported by BlenderWorld authors / Alibaba Token Hub· via BenchBoard docs29.2
11Gemini 3.8 Flashbenchmark-owner paper run · 21 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard· Reported by BlenderWorld authors / Alibaba Token Hub· via BenchBoard docs24.9

Not ranked

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
Grok 4.6benchmark-owner paper run · 21 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard· Reported by BlenderWorld authors / Alibaba Token Hub· via BenchBoard docs47.1
Seed2.1 Pro 0915benchmark-owner paper run · 21 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard· Reported by BlenderWorld authors / Alibaba Token Hub· via BenchBoard docs39.3

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.