TriWorldBench
World models generate synchronized robot-view videos from head and wrist cameras. Nineteen signals measure cross-view agreement, task alignment, physical coherence, motion, temporal stability, and visual quality.
The public validation set has 100 RoboTwin 2.0 episodes. Scoring combines automatic measurements with semantic model judgments.
- Made by
- Peking University, Tsinghua University, Beihang University and others
- Released
- September 2026
- Kind
- Video world models
- Level
- Everyday
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Another benchmark
- Refresh
- One fixed set
- Run by
- Anyone
- Based on
- RoboTwin 2.0
- In views
- Vision, Image, video and 3D generation
In the authors’ words
Embodied world models predict the outcomes of robot actions to support learning and planning. For robots equipped with head and wrist cameras, this requires complementary views: the head view captures the overall task, while wrist views reveal local gripper-object interactions. However, evaluating these views independently cannot determine whether they describe the same action and object state. We introduce TRIWORLDBENCH, a benchmark for evaluating embodied world models through synchronized head, left-wrist, and right-wrist videos. It contains 500 episodes across 50 bimanual manipulation tasks and uses 19 metrics to assess tri-view consistency, task alignment, physical and 3D coherence, motion quality, temporal consistency, and visual quality. By combining cross-view checks with measurements tailored to each camera, the benchmark evaluates whether plausible individual videos also form a consistent prediction of the intended task. We summarize overall performance with TWB-Score and retain per-view results to identify where predictions fail. This extends world-model evaluation beyond single-view visual quality. Code, data, and metric definitions are available at https://github.com/TriWorldBench/TriWorldBench.
cogito tops the leaderboard with 72.9
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.
- 72.9 cogito
- 71.8 WorldIncept
- 71.5 Digger-v2
- 70.9 X-WM-Pro
- 70.5 salad
- 70.4 BWM-Pro
- 70.2 digger
- 70.2 Salad-0.4
- 68.3 Soil
- 67.9 X-Lab
- 67.6 LinearEWM
- 66.5 LeapBotWM
- 66.0 CasualWM
- 65.7 X-WM
- 65.7 dream4act
- 65.7 VisBot
- 65.5 BWM
- 65.4 WoVR_Plus
- 64.8 Sii
- 64.6 ZWM
- 64.4 WorldNative
- 64.3 HY_World
- 64.3 PhyxWM
- 64.0 t640_mix50
- 63.9 XiaomiAutoWM
- 63.8 xiao-world
- 63.6 BetaBWM
- 63.6 Fysiverse-Video
- 62.1 WMEpivoryn
- 62.1 CoWM
- 61.3 VWA-World
- 60.8 ROBOWM
- 60.8 TrivoryxWM
- 60.5 CogVerse
- 60.4 DynaWolrd-V2
- 59.8 Xi-WM-0.4
- 59.3 LibWM
- 58.8 ActoVision-X
- 58.6 TriCam-Dreamer
- 58.5 ViewWeaver
- 58.4 MirageFlow-V3
- 58.4 DynaWorld
- 58.2 VMA-World
- 57.7 RopeWM
- 57.3 Ra_1
- 56.4 KineWorld
- 56.4 SD2-WM
- 55.6 LightWM-Alpha
- 55.0 Kimo
- 55.0 KineJing-Pro
- 54.5 Flash-WM
- 54.4 CCoae
- 53.9 ArmW
- 53.8 WDK-XLAB
- 53.7 Ennerverse-AC
- 53.7 CWAM2
- 53.7 GentleWM
- 53.5 CWAM
- 53.4 CWAM0.5
- 51.7 DreamDojo
- 51.4 VMA_X-Era
- 49.9 Dream
- 49.6 WMxel
- 49.2 LatentGrip
- 48.9 Act-Cosmos
- 42.4 motus
- 41.2 KineJing
- 40.7 genie-envisioner
- 39.0 ctrl-world
- 1 cogito 72.9
- 2 WorldIncept 71.8
- 3 Digger-v2 71.5
- 4 X-WM-Pro 70.9
- 5 salad 70.5
- 6 BWM-Pro 70.4
- 7 digger 70.2
- 8 Salad-0.4 70.2
- 9 Soil 68.3
- 10 X-Lab 67.9
- 11 LinearEWM 67.6
- 12 LeapBotWM 66.5
- 13 CasualWM 66.0
- 14 X-WM 65.7
- 15 dream4act 65.7
- 16 VisBot 65.7
- 17 BWM 65.5
- 18 WoVR_Plus 65.4
- 19 Sii 64.8
- 20 ZWM 64.6
- 21 WorldNative 64.4
- 22 HY_World 64.3
- 23 PhyxWM 64.3
- 24 t640_mix50 64.0
- 25 XiaomiAutoWM 63.9
- 26 xiao-world 63.8
- 27 BetaBWM 63.6
- 28 Fysiverse-Video 63.6
- 29 WMEpivoryn 62.1
- 30 CoWM 62.1
- 31 VWA-World 61.3
- 32 ROBOWM 60.8
- 33 TrivoryxWM 60.8
- 34 CogVerse 60.5
- 35 DynaWolrd-V2 60.4
- 36 Xi-WM-0.4 59.8
- 37 LibWM 59.3
- 38 ActoVision-X 58.8
- 39 TriCam-Dreamer 58.6
- 40 ViewWeaver 58.5
- 41 MirageFlow-V3 58.4
- 42 DynaWorld 58.4
- 43 VMA-World 58.2
- 44 RopeWM 57.7
- 45 Ra_1 57.3
- 46 KineWorld 56.4
- 47 SD2-WM 56.4
- 48 LightWM-Alpha 55.6
- 49 Kimo 55.0
- 50 KineJing-Pro 55.0
- 51 Flash-WM 54.5
- 52 CCoae 54.4
- 53 ArmW 53.9
- 54 WDK-XLAB 53.8
- 55 Ennerverse-AC 53.7
- 56 CWAM2 53.7
- 57 GentleWM 53.7
- 58 CWAM 53.5
- 59 CWAM0.5 53.4
- 60 DreamDojo 51.7
- 61 VMA_X-Era 51.4
- 62 Dream 49.9
- 63 WMxel 49.6
- 64 LatentGrip 49.2
- 65 Act-Cosmos 48.9
- 66 motus 42.4
- 67 KineJing 41.2
- 68 genie-envisioner 40.7
- 69 ctrl-world 39.0
Source: Official TriWorldBench leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | cogito | 72.9 | Nov 2026 | Official leaderboard | |
| 2 | WorldIncept | 71.8 | Oct 2026 | Official leaderboard | |
| 3 | Digger-v2 | 71.5 | Oct 2026 | Official leaderboard | |
| 4 | X-WM-Pro | 70.9 | Oct 2026 | Official leaderboard | |
| 5 | salad | 70.5 | Oct 2026 | Official leaderboard | |
| 6 | BWM-Pro | 70.4 | Oct 2026 | Official leaderboard | |
| 7 | digger | 70.2 | Oct 2026 | Official leaderboard | |
| 8 | Salad-0.4 | 70.2 | Oct 2026 | Official leaderboard | |
| 9 | Soil | 68.3 | Oct 2026 | Official leaderboard | |
| 10 | X-Lab | 67.9 | Nov 2026 | Official leaderboard | |
| 11 | LinearEWM | 67.6 | Nov 2026 | Official leaderboard | |
| 12 | LeapBotWM | 66.5 | Oct 2026 | Official leaderboard | |
| 13 | CasualWM | 66.0 | Oct 2026 | Official leaderboard | |
| 14 | X-WM | 65.7 | Oct 2026 | Official leaderboard | |
| 15 | dream4act | 65.7 | Oct 2026 | Official leaderboard | |
| 16 | VisBot | 65.7 | Oct 2026 | Official leaderboard | |
| 17 | BWM | 65.5 | Oct 2026 | Official leaderboard | |
| 18 | WoVR_Plus | 65.4 | Oct 2026 | Official leaderboard | |
| 19 | Sii | 64.8 | Oct 2026 | Official leaderboard | |
| 20 | ZWM | 64.6 | Oct 2026 | Official leaderboard | |
| 21 | WorldNative | 64.4 | Nov 2026 | Official leaderboard | |
| 22 | HY_World | 64.3 | Nov 2026 | Official leaderboard | |
| 23 | PhyxWM | 64.3 | Oct 2026 | Official leaderboard | |
| 24 | t640_mix50 | 64.0 | Oct 2026 | Official leaderboard | |
| 25 | XiaomiAutoWM | 63.9 | Oct 2026 | Official leaderboard | |
| 26 | xiao-world | 63.8 | Oct 2026 | Official leaderboard | |
| 27 | BetaBWM | 63.6 | Oct 2026 | Official leaderboard | |
| 28 | Fysiverse-Video | 63.6 | Oct 2026 | Official leaderboard | |
| 29 | WMEpivoryn | 62.1 | Oct 2026 | Official leaderboard | |
| 30 | CoWM | 62.1 | Oct 2026 | Official leaderboard | |
| 31 | VWA-World | 61.3 | Oct 2026 | Official leaderboard | |
| 32 | ROBOWM | 60.8 | Oct 2026 | Official leaderboard | |
| 33 | TrivoryxWM | 60.8 | Oct 2026 | Official leaderboard | |
| 34 | CogVerse | 60.5 | Oct 2026 | Official leaderboard | |
| 35 | DynaWolrd-V2 | 60.4 | Oct 2026 | Official leaderboard | |
| 36 | Xi-WM-0.4 | 59.8 | Oct 2026 | Official leaderboard | |
| 37 | LibWM | 59.3 | Oct 2026 | Official leaderboard | |
| 38 | ActoVision-X | 58.8 | Oct 2026 | Official leaderboard | |
| 39 | TriCam-Dreamer | 58.6 | Oct 2026 | Official leaderboard | |
| 40 | ViewWeaver | 58.5 | Oct 2026 | Official leaderboard | |
| 41 | MirageFlow-V3 | 58.4 | Oct 2026 | Official leaderboard | |
| 42 | DynaWorld | 58.4 | Oct 2026 | Official leaderboard | |
| 43 | VMA-World | 58.2 | Oct 2026 | Official leaderboard | |
| 44 | RopeWM | 57.7 | Oct 2026 | Official leaderboard | |
| 45 | Ra_1 | 57.3 | Oct 2026 | Official leaderboard | |
| 46 | KineWorld | 56.4 | Oct 2026 | Official leaderboard | |
| 47 | SD2-WM | 56.4 | Oct 2026 | Official leaderboard | |
| 48 | LightWM-Alpha | 55.6 | Oct 2026 | Official leaderboard | |
| 49 | Kimo | 55.0 | Oct 2026 | Official leaderboard | |
| 50 | KineJing-Pro | 55.0 | Oct 2026 | Official leaderboard | |
| 51 | Flash-WM | 54.5 | Oct 2026 | Official leaderboard | |
| 52 | CCoae | 54.4 | Oct 2026 | Official leaderboard | |
| 53 | ArmW | 53.9 | Oct 2026 | Official leaderboard | |
| 54 | WDK-XLAB | 53.8 | Oct 2026 | Official leaderboard | |
| 55 | Ennerverse-AC | 53.7 | Oct 2026 | Official leaderboard | |
| 56 | CWAM2 | 53.7 | Nov 2026 | Official leaderboard | |
| 57 | GentleWM | 53.7 | Oct 2026 | Official leaderboard | |
| 58 | CWAM | 53.5 | Oct 2026 | Official leaderboard | |
| 59 | CWAM0.5 | 53.4 | Oct 2026 | Official leaderboard | |
| 60 | DreamDojo | 51.7 | Oct 2026 | Official leaderboard | |
| 61 | VMA_X-Era | 51.4 | Oct 2026 | Official leaderboard | |
| 62 | Dream | 49.9 | Oct 2026 | Official leaderboard | |
| 63 | WMxel | 49.6 | Oct 2026 | Official leaderboard | |
| 64 | LatentGrip | 49.2 | Oct 2026 | Official leaderboard | |
| 65 | Act-Cosmos | 48.9 | Oct 2026 | Official leaderboard | |
| 66 | motus | 42.4 | Oct 2026 | Official leaderboard | |
| 67 | KineJing | 41.2 | Oct 2026 | Official leaderboard | |
| 68 | genie-envisioner | 40.7 | Oct 2026 | Official leaderboard | |
| 69 | ctrl-world | 39.0 | Oct 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
- 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 (69 entries).
- Pass Models scored 69 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 plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on triworldbench-triworldbench-space.hf.space: 69 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.