Benchmark Almanac

AerialSim

Claude Haiku 4.5 73.2% leads since May 2026
Not in model cards

Agents fly a simulated drone using camera observations or write a program for the flight. The simulator checks the recorded trajectory against the mission requirements.

In October 2026, Claude Haiku 4.5 completed 41 of 56 held-out missions. Qwen3.5-4B completed 11 before training and 19 after training.

Made by
Nahid Alam
Released
May 2026
Kind
Simulated robots
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Images, Time series → Actions, Code
Interaction
Agentic
Environment
A simulator
Items from
Generated
Refresh
One fixed set
Run by
Anyone
In views
Agents, Vision, Robotics
Strongest model tested
Claude Haiku 4.5 #110 on the capability index
Last model added
February 2026
Scores refreshed
November 20th, 2026
2
Models scored on its own leaderboard

Claude Haiku 4.5 leads with 73.2%

Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.

  1. 1 Claude Haiku 4.5 Reference 73.2%
  2. 2 Qwen3.5-4B Trained 33.9%

Source: Official AerialSim leaderboard

#ModelScoreSettingDateSource
1 Claude Haiku 4.5 73.2% Reference Oct 2025 Official leaderboard
2 Qwen3.5-4B 33.9% Trained Feb 2026 Official leaderboard

Number one over time

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

Anthropic
Own leaderboard Not tested since May 2026

Source: Official AerialSim 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% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Haiku 4.5 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Haiku 4.5

Source: Official AerialSim 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 9 months ago, in February 2026, for Qwen3.5-4B. 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 (2 entries).
  • Note Models scored Only 2 models we track.
  • Warning Newest score The newest came 9 months ago, in February 2026, for Qwen3.5-4B.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Claude Haiku 4.5 (#110).
  • Pass Headroom The best is 73.2%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on nahidalam.github.io: 3 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.

How we check