Benchmark Almanac

EmbodiedVerse-Bench

o4-mini 50.7 leads since April 2025
Not in model cards

Models answer questions about spatial relationships and actions from visual observations. The leaderboard compares models across embodied reasoning tasks.

The publisher lists 23 model directories in the public leaderboard results.

Kind
Embodied reasoning
Level
Everyday
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
In and out
Images, Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
In views
Vision
Strongest model tested
o4-mini #95 on the capability index
Last model added
September 2025
Scores refreshed
November 21st, 2026
22
Entries on its own leaderboard, 17 models we track

o4-mini leads with 50.7 among models released by September 2025 o4-mini leads with 50.7 among models released by September 2025

Best score per entry from the benchmark's own leaderboard, read on November 21st, 2026. The leaderboard's Average is the arithmetic mean of its ten dataset overall scores. 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 September 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 o4-mini 50.7
  2. 2 InternVL3-78B 49.6
  3. 3 InternVL2.5-38B 44.2
  4. 4 InternVL3-8B 40.3
  5. 5 VeBrain 36.0
  6. 6 Molmo-7B-D 35.4
  7. 7 MiniCPM-o-2_6 34.0
  8. 8 Cosmos-Reason1-7B 31.0
  9. 9 Qwen2-VL-2B-Instruct 30.2
  10. 10 Magma-8B 29.6
  11. 11 Phi-4-multimodal 22.8
  12. 12 Gemini 2.5 Pro Jun 2025 0.52
  13. 13 Gemini 2.5 Flash Sep 2025 0.51
  14. 14 Qwen2.5-VL-32B 0.47
  15. 15 GPT-4o Nov 2024 0.46
  16. 16 claude-sonnet-4-20250514-official 0.45
  17. 17 Gemini 2.0 Pro 0.45
  18. 18 Qwen2.5-VL-72B 0.45
  19. 19 Mistral-Small-3.1-24B-Instruct-2503 0.40
  20. 20 Qwen2.5-VL-7B 0.32
  21. 21 Qwen2-VL-7B-Instruct 0.32
  22. 22 Qwen2.5-VL-3B 0.29

Source: Official EmbodiedVerse-Bench leaderboard

#EntryScoreSettingDateSource
1 o4-mini 50.7 Apr 2025 Official leaderboard
2 InternVL3-78B 49.6 Apr 2025 Official leaderboard
3 InternVL2.5-38B 44.2 Dec 2024 Official leaderboard
4 InternVL3-8B 40.3 Apr 2025 Official leaderboard
5 VeBrain 36.0 Official leaderboard
6 Molmo-7B-D 35.4 Sep 2024 Official leaderboard
7 MiniCPM-o-2_6 34.0 Jan 2025 Official leaderboard
8 Cosmos-Reason1-7B 31.0 Official leaderboard
9 Qwen2-VL-2B-Instruct 30.2 Aug 2024 Official leaderboard
10 Magma-8B 29.6 Official leaderboard
11 Phi-4-multimodal 22.8 Feb 2025 Official leaderboard
12 Gemini 2.5 Pro Jun 2025 0.52 Jun 2025 Official leaderboard
13 Gemini 2.5 Flash Sep 2025 0.51 Sep 2025 Official leaderboard
14 Qwen2.5-VL-32B 0.47 Mar 2025 Official leaderboard
15 GPT-4o Nov 2024 0.46 Nov 2024 Official leaderboard
16 claude-sonnet-4-20250514-official 0.45 Official leaderboard
17 Gemini 2.0 Pro 0.45 Feb 2025 Official leaderboard
18 Qwen2.5-VL-72B 0.45 Jan 2025 Official leaderboard
19 Mistral-Small-3.1-24B-Instruct-2503 0.40 Official leaderboard
20 Qwen2.5-VL-7B 0.32 Jan 2025 Official leaderboard
21 Qwen2-VL-7B-Instruct 0.32 Aug 2024 Official leaderboard
22 Qwen2.5-VL-3B 0.29 Jan 2025 Official leaderboard
#ModelScoreSettingDateSource
1 o4-mini 50.7 Apr 2025 Official leaderboard
2 InternVL3-78B 49.6 Apr 2025 Official leaderboard
3 InternVL2.5-38B 44.2 Dec 2024 Official leaderboard
4 InternVL3-8B 40.3 Apr 2025 Official leaderboard
5 Molmo-7B-D 35.4 Sep 2024 Official leaderboard
6 MiniCPM-o-2_6 34.0 Jan 2025 Official leaderboard
7 Qwen2-VL-2B-Instruct 30.2 Aug 2024 Official leaderboard
8 Phi-4-multimodal 22.8 Feb 2025 Official leaderboard
9 Gemini 2.5 Pro Jun 2025 0.52 Jun 2025 Official leaderboard
10 Gemini 2.5 Flash Sep 2025 0.51 Sep 2025 Official leaderboard
11 Qwen2.5-VL-32B 0.47 Mar 2025 Official leaderboard
12 GPT-4o Nov 2024 0.46 Nov 2024 Official leaderboard
13 Gemini 2.0 Pro 0.45 Feb 2025 Official leaderboard
14 Qwen2.5-VL-72B 0.45 Jan 2025 Official leaderboard
15 Qwen2.5-VL-7B 0.32 Jan 2025 Official leaderboard
16 Qwen2-VL-7B-Instruct 0.32 Aug 2024 Official leaderboard
17 Qwen2.5-VL-3B 0.29 Jan 2025 Official leaderboard

5 models have held number one on the official leaderboard since 2023

Lab claims count from the day the card came out, independent runs from the model’s release.

Qwen Ai2 Shanghai AI Lab OpenAI
Own leaderboard Not tested since Sep 2025
o4-mini 50.7

Source: Official EmbodiedVerse-Bench leaderboard

Scores over time

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

Plot with other benchmarks
On the benchmark’s own leaderboard
0.00 20.0 40.0 60.0 2025 0.00 20.0 40.0 60.0 2025

Source: Official EmbodiedVerse-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 Robotics

All 172 in Robotics
  • ERQA In use 400 multiple-choice visual questions from robot and egocentric footage on spatial, trajectory, action and state reasoning. Accuracy. Gemini Robotics ER 2 78.5%
  • SimplerEnv In use Real-to-sim replicas of Google Robot and WidowX/Bridge setups. Policies scored by success rate on pick, move, drawer and Bridge tasks. Praxis-1 80%
  • RoboLab In use Zero-shot DROID Franka policies in Isaac Lab on 120 tabletop tasks at three instruction levels, 10 episodes each. Success rate. Praxis-1 46.2%
  • RoboDojo In use Generalist manipulation policies run 42 Isaac Sim tasks and 18 remote real-robot tasks. Scored by task score and success rate. GPT-6 Astra 27.6%
  • Progress classification (Google DeepMind) In use Models assign each frame of a robot video to one of five task-progress bands from 0 to 100 percent. Scored by accuracy. Gemini Robotics ER 2 57.4%
  • Human proximity (Google DeepMind robotics) In use Models judge from robot camera views whether a human is within 1 meter, a spatial awareness check for safe robot behavior. Scored by accuracy. Gemini Robotics ER 2 93%

Data audit

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash. 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 (22 entries).
  • Pass Models scored 17 models we track, plus 5 other entries on its leaderboard.
  • Warning Newest score The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash.
  • Note Frontier models None of the top 10 has a score. The strongest tested is o4-mini (#95).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on huggingface.co: 17 rows for models we track and 5 other entries at the last read.
  • Pass Last read November 21st, 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