Benchmark Almanac

3D Worlds Arena

World Labs Marble 1.1 Plus · SPZ 1,283 tops its leaderboard
Not in model cards

Models generate explorable 3D scenes from an image and caption. Voters inspect two anonymous scenes from the same input and choose a favorite.

The published protocol describes four initial systems. The live leaderboard returned three system entries.

Made by
3d-arena
Kind
Interactive world models
Level
Everyday
Scored
Ranked by votes
Answers
Open-ended
Tasks
All public
Measures
Preference
Language
English
In and out
Images, Text → 3D
Interaction
Single turn
Items from
Live play or votes
Refresh
Live
Run by
A host
3
Entries on its own leaderboard, 0 models we track

World Labs Marble 1.1 Plus · SPZ tops the leaderboard with 1,283

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

Bars start at 600.

  1. 1 World Labs Marble 1.1 Plus · SPZ gaussian_splat/spz 1,283
  2. 2 Tencent HY-World 2.0 + WorldMirror gaussian_splat/ply 1,012
  3. 3 NVIDIA Lyra 2.0 gaussian_splat/ply 705

Source: Official 3D Worlds Arena leaderboard

#EntryScore ±SettingDateSource
1 World Labs Marble 1.1 Plus · SPZ closed weights 1,283 1250.9 to 1316.8 gaussian_splat/spz Nov 2026 Official leaderboard
2 Tencent HY-World 2.0 + WorldMirror open weights 1,012 992.8 to 1035.8 gaussian_splat/ply Nov 2026 Official leaderboard
3 NVIDIA Lyra 2.0 open weights 705 668.1 to 736.4 gaussian_splat/ply Nov 2026 Official leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in World models

All 53 in World models
  • AgentWorldBench In use Language world models predict the next environment observation after an agent action, in 7 domains from MCP and search to Android and desktop OS. A judge model scores each prediction against the real observation on five dimensions. GPT-5.4 58.3
  • IntPhys 2 In use Models watch simulated videos and judge whether each event is physically possible, testing object permanence, immutability, continuity and solidity. Scored by accuracy. Muse Spark Open 68.3%
  • QwenWorldBench Fading Models act as world models that simulate agent environments in 7 domains, such as terminal, web, and Android. A rubric judge scores five dimensions. Qwen3.7-Plus 62.1%
  • VPCT Fading Models view an image of a ball, ramps, and three buckets and predict which bucket the ball falls into. Scored by accuracy on 100 problems. Gemini 3 Pro 91%
  • ContPhy Fading Models infer physical properties such as mass and density of fluids and soft bodies from videos and predict their dynamics. Seed2.0 Pro 67.4%
  • RBench Only in system cards 650 image+text prompts for robot video generation (tasks and embodiments). MLLM judge scores task completion, physical plausibility, stability. Wan 2.6 60.7%

Data audit

All 7 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 pass 4 notes
  • Pass Independent runs Scores from the official leaderboard (3 entries).
  • Note Models scored 3 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom Scored as a rating, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on 3d-arena-3d-world-arena.hf.space: 3 entries at the last read, none a model we track.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check