Benchmark Almanac

AsgardBench

Claude Opus 4.5 76.5% leads since March 2026
Not in model cards

Agents adapt high-level action plans from images, action history and lightweight success signals in a controlled simulator.

AsgardBench contains 108 task instances across 12 task types and tests plan repair under visual feedback.

Released
March 2026
Kind
Simulated robots
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
In and out
Images, Text → Actions
Interaction
Agentic
Environment
A simulator
Items from
Generated
Refresh
One fixed set
Run by
Anyone
In views
Agents, Vision, Robotics
Strongest model tested
GPT-5.2 #51 on the capability index
Last model added
January 2026
Scores refreshed
November 21st, 2026
9
Entries in its paper, 7 models we track

Claude Opus 4.5 leads with 76.5% among models released by January 2026 Claude Opus 4.5 leads with 76.5% among models released by January 2026

Best score per entry from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. 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 January 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 Claude Opus 4.5 76.5%
  2. 2 Gemini 3 Pro 72.5%
  3. 3 GPT-5.2 71.3%
  4. 4 Kimi K2.5 68.8%
  5. 5 Qwen3-VL-235B 32.4%
  6. 6 GLM-4.6V 30.6%
  7. 7 GPT-4o (snapshot unspecified) 23.4%
  8. 8 Mistral Large 3 7.40%
  9. 9 Llama 4 Maverick 5.80%

Source: The AsgardBench paper

#EntryScoreSettingDateSource
1 Claude Opus 4.5 76.5% Nov 2025 Official leaderboard
2 Gemini 3 Pro 72.5% Nov 2025 Official leaderboard
3 GPT-5.2 71.3% Dec 2025 Official leaderboard
4 Kimi K2.5 68.8% Jan 2026 Official leaderboard
5 Qwen3-VL-235B 32.4% Official leaderboard
6 GLM-4.6V 30.6% Dec 2025 Official leaderboard
7 GPT-4o (snapshot unspecified) 23.4% Official leaderboard
8 Mistral Large 3 7.40% Dec 2025 Official leaderboard
9 Llama 4 Maverick 5.80% Apr 2025 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Opus 4.5 76.5% Nov 2025 Official leaderboard
2 Gemini 3 Pro 72.5% Nov 2025 Official leaderboard
3 GPT-5.2 71.3% Dec 2025 Official leaderboard
4 Kimi K2.5 68.8% Jan 2026 Official leaderboard
5 GLM-4.6V 30.6% Dec 2025 Official leaderboard
6 Mistral Large 3 7.40% Dec 2025 Official leaderboard
7 Llama 4 Maverick 5.80% 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.

Anthropic
Benchmark paper Not tested since Mar 2026

Source: The AsgardBench paper

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
In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Claude Opus 4.5 Llama 4 Maverick 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Claude Opus 4.5 Llama 4 Maverick

Source: Official AsgardBench 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

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 10 months ago, in January 2026, for Kimi K2.5. Every benchmark

Catalog record 2 pass
  • Pass Task access All 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 (9 entries).
  • Pass Models scored 7 models we track, plus 2 other entries on its leaderboard.
  • Warning Newest score The newest came 10 months ago, in January 2026, for Kimi K2.5.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.2 (#51).
  • Pass Headroom The best is 76.5%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 7 rows for models we track and 2 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