Benchmark Almanac

EmbodiedCLUE-World 2.0

PF-Cosmos 52.4 tops its leaderboard LingBot-Video-MoE 41.8 leads the models we track
Not in model cards
Version 2.0

World models predict outcomes in embodied settings under the second evaluation protocol.

SuperCLUE reports scores in a public workbook.

Made by
SuperCLUE
Released
July 2026
Kind
Interactive world models
Level
Everyday
Scored
Checked automatically
Answers
Prediction
Measures
Capability
In and out
Images, Video → Video
Interaction
Single turn
Run by
A host
Last model added
July 2026
Scores refreshed
November 20th, 2026
6
Entries on its own leaderboard, 1 model we track

PF-Cosmos tops the leaderboard with 52.4 LingBot-Video-MoE leads with 41.8

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. The best model we track is LingBot-Video-MoE, at 41.8. This view shows only models we track, each at its best.

  1. 1 PF-Cosmos 本地部署 52.4
  2. 2 WoW-1-Wan-14B-2M 本地部署 48.9
  3. 3 Abot-PhysWorld 本地部署 45.4
  4. 4 LingBot-Video-MoE 本地部署 41.8
  5. 5 Cosmos-Predict2.5-14B 本地部署 38.1
  6. 6 GigaWorld-0-Video-GR1-2b 本地部署 19.7

Source: Official EmbodiedCLUE-World 2.0 leaderboard

  1. 1 LingBot-Video-MoE 本地部署 41.8

Source: Official EmbodiedCLUE-World 2.0 leaderboard

#EntryScoreSettingDateSource
1 PF-Cosmos 52.4 本地部署 Official leaderboard
2 WoW-1-Wan-14B-2M 48.9 本地部署 Official leaderboard
3 Abot-PhysWorld 45.4 本地部署 Official leaderboard
4 LingBot-Video-MoE 41.8 本地部署 Jul 2026 Official leaderboard
5 Cosmos-Predict2.5-14B 38.1 本地部署 Official leaderboard
6 GigaWorld-0-Video-GR1-2b 19.7 本地部署 Official leaderboard
#ModelScoreSettingDateSource
1 LingBot-Video-MoE 41.8 本地部署 Jul 2026 Official leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard
41.8 41.8

Source: Official EmbodiedCLUE-World 2.0 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.

Versions

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

8 of 9 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (6 entries).
  • Pass Models scored 1 model we track, plus 5 other entries on its leaderboard.
  • Pass Newest score The newest is from July 2026, for LingBot-Video-MoE.
  • Note Frontier models None of its models are on the capabilities index.
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on superclueai.com: 1 row for models we track and 5 other entries at the last read.
  • 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