AA / RENDER #—
2D / RGBBENCHMARK 002MATCH / 0001
TASK
Loading comparison…
Loading benchmark brief…
Evaluation Blind pairwise
Order Randomized
Progress001 / —
Benchmark detailsBlind · randomized · Match 1+
ProgressMatch 1 / —
MethodBlind pairwise comparison
RandomizationSides randomized
Identities and configuration details stay hidden until you vote.
How should I judge?
Judge prompt adherence and overall result quality. Model, harness, and effort stay hidden until you vote.
Brief adherenceRequested elements are present and convincingly combined.
CompositionThe scene is clear, intentional, and readable at a glance.
Finish qualityMaterials, lighting, detail, and completeness feel resolved.
Filters All configurations+
BLIND PAIRWISE COMPARISON
Which result better satisfies the brief?
Compare only what is visible. Select the stronger render, or record that both or neither satisfy the brief. Identities hidden
BB / RENDER #—
2D / RGBVote recorded · Identities revealedNext comparison in 6s
LIVE STANDINGS02
Rankings
Each row represents one model × effort group pooled across harnesses and profiles. Ratings are updated from blind pairwise votes.
—configurations
—total votes
Liveupdates
Ranking view
CONFIGURATION EFFICIENCYHigher is better
Efficiency
Why this is not pooled: each model, harness, effort, and profile combination stays separate. Repeated runs of the same configuration are averaged; settings are never averaged together, making tradeoffs between configurations visible.
Show
Advanced filtersAny configuration+
| Efficiency | Confidence | Votes | |||||
|---|---|---|---|---|---|---|---|
| Loading standings… | |||||||
Ratings begin at 1500. Model × Effort pools across harnesses and profiles; Harness uses direct same-model, same-effort comparisons. Configurations with fewer than five votes are marked provisional.
RUN EXPLORER03
Runs
Search and filter imported runs, then open one to inspect its render, interactive 3D model, and recorded metrics.
| Run | Run date | Model | Harness | Effort | Prompt | Runtime / cost | Agent activity | Geometry |
|---|---|---|---|---|---|---|---|---|
| Loading run history… | ||||||||
← Back to history![]()
Preview unavailable
RUN DETAILRUN / —
Loading run…
RENDER PREVIEWRun image
Open image ↗SCENE MODELInteractive 3D model
Download GLB ↓RESEARCH METHOD04
How the benchmark works
The evaluation isolates the full tool-using stack while keeping the voting experience simple and blind.
Every run begins with the same natural-language Blender task.
CONTROLLEDModels work through their assigned harness and reasoning setting.
VARIESIdentities and configuration details remain hidden during voting.
HIDDEN UNTIL VOTEPairwise outcomes update ratings for each configuration.
CALCULATEDCONTROLLED
Prompt, benchmark scene, comparison protocol, and vote outcomes.
WHAT VARIES
Model, reasoning effort, harness, and the resulting Blender scene.
AFTER VOTING
Identities and technical run metrics are revealed without moving the renders.
LOW SAMPLES
New configurations remain marked Provisional until enough votes accumulate.
CONTRIBUTE A RUN05
Run the benchmark locally
Use the submission script to run Pi with a selected model, reasoning effort, and canonical prompt. Uploads enter a private staging queue and are published only after administrator review.
QUICK START
Download submission script chmod +x submit-run.sh
./submit-run.sh --server https://arena.example \
--model PROVIDER/MODEL --effort high --prompt worldtreeThe script does not assume CPU or GPU rendering. It records the actual Blender environment with the session, preview, GLB, and Blend file. Session logs can contain prompts, tool output, and local paths; inspect them before confirming upload.
ABOUT THE LAB06
Preference data for a more open 3D future.
Render Arena is an open benchmark for comparing real Blender runs across the complete agent stack. Votes are stored against an anonymous browser token so one voter cannot submit the same comparison twice.