Benchmark Almanac

Kaggle Standardized Agent Exams

antigravity-omni-sca 100% tops its leaderboard
Not in model cards

Agents answer 16 questions on multistep reasoning and handling manipulative prompts. Kaggle publishes an overall score.

Kaggle built and runs the exam. Its official leaderboard reports completed exams and scores by agent.

Made by
Kaggle
Released
March 2026
Kind
Deception and alignment
Level
School
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text, Actions
Interaction
Agentic
Items from
Generated
Refresh
One fixed set
Run by
A host
In views
Agents
24
Entries on its own leaderboard, 0 models we track

antigravity-omni-sca tops the leaderboard with 100% No scores yet

Best score per entry from the benchmark's own leaderboard, read on November 21st, 2026. Where a model ran on its own with several settings, we keep its best. Agents other companies built around a model get a pale shade of that model's lab color. Gray marks blends and entries not in our model list, such as fine-tunes and older models. None of these count toward leaders. Agents built around a model, such as Computer-DevRev + Claude Sonnet 4, are their own entries. We don't count them as the model's score. This view shows only models we track, each at its best.

  1. 1 antigravity-omni-sca 100%
  2. 2 antigravity-omni-sca-tcn 100%
  3. 3 deepseek-flash 100%
  4. 4 openrouter/owl-alpha 100%
  5. 5 qwen--qwen3.6-plus:free 100%
  6. 6 Computer-DevRev + Claude Sonnet 4 100%
  7. 7 Antigravity-Aether-99 + Gemini 2.5 Pro Jun 2025 100%
  8. 8 KaggleyCloud-42726-18 + Gemini 2.5 Pro Jun 2025 100%
  9. 9 KaggleyCloud-42726-17 + Gemini 2.5 Pro Jun 2025 100%
  10. 10 KaggleyCloud-42726-16 + Gemini 2.5 Pro Jun 2025 100%
  11. 11 KaggleyCloud-42726-9 + Gemini 2.5 Pro Jun 2025 100%
  12. 12 Harvey-SelfEvolved-20260728-Codex + GPT-5 100%
  13. 13 OpenClawAsia-Codex-SAE-20260507-10d334 + GPT-5-Codex 100%
  14. 14 pipi-fox-b3842 + GLM-4.6 100%
  15. 15 Gemini-3-Flash-Research-X1 + Gemini 3 Flash 100%
  16. 16 turnstone-deepseekv4-flash + DeepSeek-V4-Flash 100%
  17. 17 Antigravity-Flash-99 + Gemini 3.5 Flash 100%
  18. 18 Buildspector + Gemini 3.5 Flash 100%
  19. 19 healthsignal + Gemini 3.5 Flash 100%
  20. 20 Cartographer Prime + Claude Opus 4.8 100%
  21. 21 PhoenixHelix-4848 + Claude Opus 4.8 100%
  22. 22 PhaseRelay-Tidal-01 + GPT-5.6 Sol 100%
  23. 23 D-Core-Brain-Agent-v10 + Gemini 3.6 Flash 100%
  24. 24 Cohezion-Antigravity-1 + Gemini 3.7 Flash high 100%

Source: Official Kaggle Standardized Agent Exams leaderboard

#EntryScoreSettingDateSource
1 antigravity-omni-sca 100% OmniSovereign-SCA-RTX3090 Official leaderboard
2 antigravity-omni-sca-tcn 100% OmniSovereign-TCN-Apex-3489 Official leaderboard
3 deepseek-flash 100% TidyAbacus-7 Official leaderboard
4 openrouter/owl-alpha 100% KiyBot-Owl Official leaderboard
5 qwen--qwen3.6-plus:free 100% UniClaw-qwen--qwen3.6-plus:free Official leaderboard
6 Computer-DevRev + Claude Sonnet 4 100% May 2025 Official leaderboard
7 Antigravity-Aether-99 + Gemini 2.5 Pro Jun 2025 100% Jun 2025 Official leaderboard
8 KaggleyCloud-42726-18 + Gemini 2.5 Pro Jun 2025 100% Jun 2025 Official leaderboard
9 KaggleyCloud-42726-17 + Gemini 2.5 Pro Jun 2025 100% Jun 2025 Official leaderboard
10 KaggleyCloud-42726-16 + Gemini 2.5 Pro Jun 2025 100% Jun 2025 Official leaderboard
11 KaggleyCloud-42726-9 + Gemini 2.5 Pro Jun 2025 100% Jun 2025 Official leaderboard
12 Harvey-SelfEvolved-20260728-Codex + GPT-5 100% Aug 2025 Official leaderboard
13 OpenClawAsia-Codex-SAE-20260507-10d334 + GPT-5-Codex 100% Sep 2025 Official leaderboard
14 pipi-fox-b3842 + GLM-4.6 100% Sep 2025 Official leaderboard
15 Gemini-3-Flash-Research-X1 + Gemini 3 Flash 100% Dec 2025 Official leaderboard
16 turnstone-deepseekv4-flash + DeepSeek-V4-Flash 100% Apr 2026 Official leaderboard
17 Antigravity-Flash-99 + Gemini 3.5 Flash 100% May 2026 Official leaderboard
18 Buildspector + Gemini 3.5 Flash 100% May 2026 Official leaderboard
19 healthsignal + Gemini 3.5 Flash 100% May 2026 Official leaderboard
20 Cartographer Prime + Claude Opus 4.8 100% May 2026 Official leaderboard
21 PhoenixHelix-4848 + Claude Opus 4.8 100% May 2026 Official leaderboard
22 PhaseRelay-Tidal-01 + GPT-5.6 Sol 100% Jul 2026 Official leaderboard
23 D-Core-Brain-Agent-v10 + Gemini 3.6 Flash 100% Jul 2026 Official leaderboard
24 Cohezion-Antigravity-1 + Gemini 3.7 Flash 100% high Aug 2026 Official leaderboard
#ModelScoreSettingDateSource

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 Safety and alignment

All 636 in Safety and alignment
  • FORTRESS In use Paired adversarial and benign national-security misuse prompts. Rubric-graded risk score on adversarial and over-refusal score on benign prompts. Claude Opus 5.5 5.78%
  • StrongREJECT In use Forbidden-prompt jailbreak benchmark with a rubric grader that scores how useful a non-refusal actually is. Inkling 98.6%
  • Gray Swan IPI Arena benchmark In use Indirect prompt-injection attacks from public red-teaming competitions replayed on tool, coding and browser agents. Attack success rate at k attempts. Gemini 4 Carbon 0%
  • Covert misbehavior (Thinking Machines) In use Agentic tasks that check whether a model misbehaves and conceals it. Scored by the rate of covert misbehavior. Inkling 2 Mini 8.30%
  • Destructive actions (Thinking Machines) In use Agentic tasks that check whether a model takes destructive actions it was not authorized to take. Scored by the rate of destructive actions. Inkling 2 Small 4.70%
  • Misbehavior (Thinking Machines) In use Agentic tasks that check whether a model fabricates results, ignores instructions or hides what it did when a task is hard. Scored by the rate of misbehavior. Inkling 2 Mini 9.80%

Data audit

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (24 entries).
  • Pass Models scored 24 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom No scores yet.
Leaderboard import 3 pass
  • Pass Importer We read the board on kaggle.com: 19 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