~ same prompt, different LLM — every model gets the same brief in Blender, you judge the render ~
OpenAI / GPT 6 Astra / thinking:max has entered the arena NEW!
ARCHIVEDRetired from the leaderboard and voting — smoke-test scene — capability sanity check, not part of the benchmark · 2026-07-20. Preserved here for reference only.
Render Window — hero
hero render
camera + framing set up by the AI contestant
3D Viewport — red-ball User Persp
LOADING 3D VIEW
$0.00Cost
65sDuration
8Tool calls
9Turns
Blender 5.1.0MCP 1.22026-07-15
Tokens: 55465/3604Vision: Votes W-L-T: 0-0-0NO DONE
B-BENCH — TRANSCRIPT DeepSeek / Deepseek V4 Flash · r1 · 2026-07-15
RUN LOG — red-ball · DeepSeek / Deepseek V4 Flash · r1 · ok
SYSTEM PROMPTthe control — every model on this task got these instructions
PROMPTblender-bench v6HARNESSraw-v1
SHOW FULL PROMPT · 1104 chars
You are participating in Blender-Bench, a public benchmark where AI models complete the same Blender task.

Your result will be compared head-to-head with another model. Anyone on the internet can vote, based only on the published visual outputs they can inspect: the interactive 3D scene and rendered presentation.

Complete the request as well as you can. The benchmark does not prescribe a workflow or visual style; use whichever Blender techniques you consider appropriate. Make the important requirements evident in the published result, save a complete scene, and present the work clearly in every requested output.

## Harness Instructions

You are operating Blender through the provided tools. The scene starts empty. Build what the user's prompt asks for in the current scene. Work step by step and verify your own work. Before you finish, set up a camera and lighting to frame a single, well-composed presentation image of your result — position and aim the camera, and add or adjust lights so the subject reads clearly. When you are finished, reply with the single word DONE and no tool calls.
--TASK red-ball: ## Task Complete the following Blender task: <task> A red sphere of 1 meter diameter resting on a white ground plane — touching it exactly, neither floating nor sunk. Smooth shading, a plain red material on the ball, plain white on the floor. The floor is the sphere, the color, and the contact. The ceiling is presentation: a soft believable shadow under the ball, a hint of glossiness that catc…
51:36>>get_scene_info({"user_prompt":"A red sphere of 1 meter diameter resting on a white ground plane"})
51:36<<{ "name": "Scene", "object_count": 0, "objects": [], "materials_count": 2 }
51:44>>execute_blender_code({"code":"# Clear the scene\nimport bpy\nbpy.ops.object.select_all(action='SELECT')\nbpy.ops.object.delete(use_global=False)\n\n# Add a ground plane\nbpy.ops.mesh.primitive_plane_add(size=10, location=(0, 0, 0))\nground = bpy.context.active_object\nground.name = \"Ground\"\n\n# Add a sphere - radius 0.5m, positioned so it touches the ground at z=0\n# Center of sphere at z=0.5 so bottom touches z=0\…)
51:44<<Code executed successfully: Created sphere and ground plane
51:52>>execute_blender_code({"code":"import bpy\n\n# Get objects\nsphere = bpy.data.objects[\"RedBall_Sphere\"]\nground = bpy.data.objects[\"Ground\"]\n\n# Apply smooth shading to sphere\nbpy.context.view_layer.objects.active = sphere\nbpy.ops.object.shade_smooth()\n\n# Also smooth the ground (it's flat so doesn't matter, but for consistency)\nbpy.context.view_layer.objects.active = ground\nbpy.ops.object.shade_smooth()\n\n#…)
51:52<<Error executing code: Communication error with Blender: Code execution error: 'bpy_prop_collection[key]: key "Specular" not found'
52:00>>execute_blender_code({"code":"import bpy\n\n# Get objects\nsphere = bpy.data.objects[\"RedBall_Sphere\"]\nground = bpy.data.objects[\"Ground\"]\n\n# Apply smooth shading to sphere\nbpy.context.view_layer.objects.active = sphere\nbpy.ops.object.shade_smooth()\n\n# Create red material for sphere\nred_mat = bpy.data.materials.new(name=\"Red_Material\")\nred_mat.use_nodes = True\nnodes = red_mat.node_tree.nodes\nlinks = r…)
52:00<<Code executed successfully: Materials created and assigned
52:04>>get_polyhaven_status({})
52:04<<PolyHaven integration is currently disabled. To enable it: 1. In the 3D Viewport, find the BlenderMCP panel in the sidebar (press N if hidden) 2. Check the 'Use assets from Poly Haven' checkbox 3. Restart the connection to Claude
52:09>>execute_blender_code({"code":"import bpy\n\n# Set up world background to dark/neutral\nworld = bpy.data.worlds['World']\nworld.use_nodes = True\nnodes = world.node_tree.nodes\nlinks = world.node_tree.links\n\n# Clear world nodes\nfor node in nodes:\n nodes.remove(node)\n\n# Add a simple background color node\nbg = nodes.new(type='ShaderNodeBackground')\nbg.location = (0, 0)\nbg.inputs['Color'].default_value = (0.1,…)
52:09<<Code executed successfully: World background set to dark gray
52:17>>execute_blender_code({"code":"import bpy\n\n# Set render engine to Cycles for better shadows and reflections\nbpy.context.scene.render.engine = 'CYCLES'\nbpy.context.scene.cycles.samples = 128\n\n# Enable shadow catcher? No, we just need lights to cast shadows naturally.\n\n# Delete default lights if any\nfor obj in bpy.data.objects:\n if obj.type == 'LIGHT':\n bpy.data.objects.remove(obj)\n\n# Add key light…)
52:17<<Code executed successfully: Lights added
52:21>>execute_blender_code({"code":"import bpy\nimport math\n\n# Delete any existing cameras\nfor obj in bpy.data.objects:\n if obj.type == 'CAMERA':\n bpy.data.objects.remove(obj)\n\n# Add a camera\nbpy.ops.object.camera_add(location=(3, -3, 2))\ncam = bpy.context.active_object\ncam.name = \"Camera\"\n\n# Point camera at the sphere (origin at 0,0,0.5)\ncam.rotation_euler = (math.radians(60), 0, math.radians(45))\…)
52:21<<Code executed successfully: Camera set up
52:27--status: budget_exhausted
>
FULL CALL INSPECTOR
OPEN RAW JSONL ↗
0 SHOWN
LOADING COMPLETE TRANSCRIPT…
Votes cast on this bench: 000482 · 157 runs · 25 contestants
Best viewed with Netscape Navigator 4.07 at 800×600 · real runs, live ratings