Benchmark Almanac

HandWorldBench

JointControlVideo 55.5 tops its leaderboard HunyuanVideo 1.5 52.2 leads the models we track
Not in model cards

Models generate videos of human or robotic hands moving objects. The benchmark combines 17 measures of hand motion, object state, and video quality.

The authors compare 11 models on 500 clips.

Released
November 2026
Kind
Video world models
Level
Everyday
Scored
Graded by a model
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Images → Video
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Scores refreshed
November 20th, 2026
11
Entries on its own leaderboard, 1 model we track

JointControlVideo tops the leaderboard with 55.5 HunyuanVideo 1.5 leads with 52.2

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 HunyuanVideo 1.5, at 52.2. This view shows only models we track, each at its best.

  1. 1 JointControlVideo 55.5
  2. 2 HunyuanVideo 1.5 52.2
  3. 3 Wan2.2 51.6
  4. 4 Wan2.1 50.3
  5. 5 EgoHOI 48.9
  6. 6 DWM 47.3
  7. 7 PAM 46.1
  8. 8 CogVideoX1.5 45.9
  9. 9 EgoSim 45.4
  10. 10 RynnWorld-Teleop 42.6
  11. 11 Hand2World 34.1

Source: Official HandWorldBench leaderboard

Source: Official HandWorldBench leaderboard

#EntryScoreSettingDateSource
1 JointControlVideo 55.5 Official leaderboard
2 HunyuanVideo 1.5 52.2 Official leaderboard
3 Wan2.2 51.6 Official leaderboard
4 Wan2.1 50.3 Official leaderboard
5 EgoHOI 48.9 Official leaderboard
6 DWM 47.3 Official leaderboard
7 PAM 46.1 Official leaderboard
8 CogVideoX1.5 45.9 Official leaderboard
9 EgoSim 45.4 Official leaderboard
10 RynnWorld-Teleop 42.6 Official leaderboard
11 Hand2World 34.1 Official leaderboard
#ModelScoreSettingDateSource
1 HunyuanVideo 1.5 52.2 Official leaderboard

Scores over time

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

No dated values yet.

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 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (11 entries).
  • Pass Models scored 1 model we track, plus 10 other entries on its leaderboard.
  • Note Newest score No scores yet.
  • 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 embodiedcity.github.io: 1 row for models we track and 10 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