ALIVE-Bench
Agents interpret social cues and act in simulated conversations. The evaluator tracks what agents perceive, what they infer, and how their actions affect other characters.
- Made by
- Tsinghua University and collaborators
- Released
- November 2026
- Kind
- Simulated robots
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Agent task
- Measures
- Capability
- Language
- English
- Interaction
- Multi-agent
- Environment
- ALIVE-World
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- A host
- Strongest model tested
- Claude Opus 4.6 #39 on the capability index
- Last model added
- February 2026
- Scores refreshed
- November 20th, 2026
Gemini 3 Pro leads with 80.4% among models released by February 2026
Best score per model from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports no combined score. The headline is Shopping kinesic cue recognition accuracy, its first measure. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in February 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1
Gemini 3 Pro 80.4%
- 2 Claude Sonnet 4.6 77.6%
- 3 GPT-5 Chat 77.3%
- 4 Claude Opus 4.6 75.3%
- 5
Gemini 3 Flash 73.8%
- 6 GLM-4.6V 72%
- 7
Qwen3-VL-32B-Thinking 71.4%
- 8 GPT-5 71%
- 9
Qwen3-VL-235B-A22B thinking 65.9%
- 10
Qwen3-VL-32B-Instruct 63.9%
- 11
Qwen3-VL-235B-A22B-Instruct 62.8%
- 12 o3 60.1%
Source: The ALIVE-Bench paper
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 80.4% | Nov 2025 | Official leaderboard | |
| 2 | Claude Sonnet 4.6 | 77.6% | Feb 2026 | Official leaderboard | |
| 3 | GPT-5 Chat | 77.3% | Aug 2025 | Official leaderboard | |
| 4 | Claude Opus 4.6 | 75.3% | Feb 2026 | Official leaderboard | |
| 5 | | 73.8% | Dec 2025 | Official leaderboard | |
| 6 | GLM-4.6V | 72% | Dec 2025 | Official leaderboard | |
| 7 | | 71.4% | Oct 2025 | Official leaderboard | |
| 8 | GPT-5 | 71% | Aug 2025 | Official leaderboard | |
| 9 | | 65.9% | thinking | Sep 2025 | Official leaderboard |
| 10 | | 63.9% | Oct 2025 | Official leaderboard | |
| 11 | | 62.8% | Sep 2025 | Official leaderboard | |
| 12 | o3 | 60.1% | Apr 2025 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The ALIVE-Bench paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official ALIVE-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
- 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 10 checks pass, 2 warnings. 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 1 warning 3 pass 1 note
- Pass Independent runs Scores from the benchmark’s paper (12 entries).
- Pass Models scored 12 models we track.
- Warning Newest score The newest came 9 months ago, in February 2026, for Claude Sonnet 4.6.
- Note Frontier models None of the top 10 has a score. The strongest tested is Claude Opus 4.6 (#39).
- Pass Headroom The best is 80.4%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 12 rows for models we track 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.