Benchmark Almanac

H2R-Bench

Not in model cards

Models turn first-person demonstrations into videos of a specified robot performing the task. The benchmark checks contacts, object responses, and completion of the goal.

Made by
Dingyi Rong and colleagues
Released
August 2026
Kind
Video generation
Level
Everyday
Scored
Graded by a model
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English
In and out
Video, Text → Video
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Last model added
March 2026
Scores refreshed
November 20th, 2026
11
Entries on its own leaderboard, 5 models we track

Dreamina Seedance 2.0 leads with 81.0 among models released by March 2026 Dreamina Seedance 2.0 leads with 81.0 among models released by March 2026

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. The leaderboard gives no overall score, so this is the plain mean of gripper and hand H2RCore. 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. This view shows only models we track, each at its best.

The newest model with a score here came out in March 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Dreamina Seedance 2.0 Video-conditioned generation 81.0
  2. 2 Wan2.7 Video-conditioned generation 79.8
  3. 3 Kling-V3 Video-conditioned generation 78.1
  4. 4 Mitty-EPIC14B Image / frame-conditioned generation 58.8
  5. 5 Veo 3.1 Audio Image / frame-conditioned generation 53.3
  6. 6 Grok Imagine Video Image / frame-conditioned generation 49.6
  7. 7 LTX-2.3 Image / frame-conditioned generation 36.0
  8. 8 SkyReels-V3-R2V Image / frame-conditioned generation 33.0
  9. 9 Wan2.2 Image / frame-conditioned generation 33.0
  10. 10 LongCat Image / frame-conditioned generation 31.5
  11. 11 HunyuanVideo 1.5 Image / frame-conditioned generation 30.4

Source: Official H2R-Bench leaderboard

#EntryScoreSettingDateSource
1 Dreamina Seedance 2.0 81.0 Video-conditioned generation Official leaderboard
2 Wan2.7 79.8 Video-conditioned generation Official leaderboard
3 Kling-V3 78.1 Video-conditioned generation Official leaderboard
4 Mitty-EPIC14B 58.8 Image / frame-conditioned generation Official leaderboard
5 Veo 3.1 Audio 53.3 Image / frame-conditioned generation Official leaderboard
6 Grok Imagine Video 49.6 Image / frame-conditioned generation Official leaderboard
7 LTX-2.3 36.0 Image / frame-conditioned generation Mar 2026 Official leaderboard
8 SkyReels-V3-R2V 33.0 Image / frame-conditioned generation Official leaderboard
9 Wan2.2 33.0 Image / frame-conditioned generation Official leaderboard
10 LongCat 31.5 Image / frame-conditioned generation Official leaderboard
11 HunyuanVideo 1.5 30.4 Image / frame-conditioned generation Official leaderboard
#ModelScoreSettingDateSource
1 Dreamina Seedance 2.0 81.0 Video-conditioned generation Official leaderboard
2 Veo 3.1 Audio 53.3 Image / frame-conditioned generation Official leaderboard
3 Grok Imagine Video 49.6 Image / frame-conditioned generation Official leaderboard
4 LTX-2.3 36.0 Image / frame-conditioned generation Mar 2026 Official leaderboard
5 HunyuanVideo 1.5 30.4 Image / frame-conditioned generation Official leaderboard

Rankings by part

We read 12 parts from the benchmark’s own leaderboard in 2 groups: parallel-jaw gripper and dexterous hand. Each ranks models on one part of the test. Dreamina Seedance 2.0 leads 10 of them, and HunyuanVideo 1.5 leads the other 2. Arrows show how far a model moved from its overall rank among the models we track.

Parallel-Jaw Gripper: Goal completion

5 models we track have a score here.

  1. 1 Dreamina Seedance 2.0 0.72
  2. 2 Veo 3.1 Audio 0.72
  3. 3 Grok Imagine Video 0.66
  4. 4 HunyuanVideo 1.5 ↑1 0.54
  5. 5 LTX-2.3 ↓1 0.47

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
36.0 2026 36.0 2026

Source: Official H2R-Bench 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 Audio and video

All 695 in Audio and video
  • Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy. Qwen 3.8 Max 88.7%
  • LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization. Gemini 4 Argon 91.7%
  • MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy. Qwen 3.8 Max 82.4%
  • MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy. Qwen 3.8 Max 90.8%
  • FLEURS In use Models transcribe read speech in 102 languages built from FLoRes-101 sentences. Model cards usually report word error rate, so lower scores are better. Phi-4-multimodal 4.00%
  • VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules. Qwen3.5-Omni-Plus 93.1%

Data audit

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 8 months ago, in March 2026, for LTX-2.3. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (11 entries).
  • Pass Models scored 5 models we track, plus 6 other entries on its leaderboard.
  • Warning Newest score The newest came 8 months ago, in March 2026, for LTX-2.3.
  • 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 rongdingyi.github.io: 5 rows for models we track and 6 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