Benchmark Almanac

Ping or Peek

Claude Sonnet 5.5 0.59% leads since September 2026
Not in model cards

Coding agents receive an ambiguous request. A judge checks whether they ask the user for clarification or consult the grader.

The study includes 1,620 runs from six models.

Made by
Snorkel AI
Kind
Deception and alignment
Level
Everyday
Scored
Graded by a model
Answers
Agent task
Tasks
All public
Measures
Propensity
Language
English
In and out
Text, Code → Actions, Text, Code
Interaction
Agentic
Environment
Terminal
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-6 Astra #4 on the capability index
Last model added
September 2026
Scores refreshed
November 21st, 2026
6
Models scored on its own leaderboard

Claude Sonnet 5.5 leads with 0.59% among models released by September 2026

Best score per model from the benchmark's own leaderboard, read on November 21st, 2026. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in September 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 Sonnet 5.5 All harnesses and settings 0.59%
  2. 2 GPT-6.1 Sol All harnesses and settings 0.53%
  3. 3 Claude Opus 5.5 All harnesses and settings 0.48%
  4. 4 GPT-6 Astra All harnesses and settings 0.47%
  5. 5 Claude Fable 5.1 All harnesses and settings 0.41%
  6. 6 GPT-6 Luna All harnesses and settings 0.39%

Source: Official Ping or Peek leaderboard

#ModelScoreSettingDateSource
1 Claude Sonnet 5.5 0.59% All harnesses and settings Sep 2026 Official leaderboard
2 GPT-6.1 Sol 0.53% All harnesses and settings Sep 2026 Official leaderboard
3 Claude Opus 5.5 0.48% All harnesses and settings Sep 2026 Official leaderboard
4 GPT-6 Astra 0.47% All harnesses and settings Sep 2026 Official leaderboard
5 Claude Fable 5.1 0.41% All harnesses and settings Sep 2026 Official leaderboard
6 GPT-6 Luna 0.39% All harnesses and settings Sep 2026 Official leaderboard

4 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.

Anthropic OpenAI
Own leaderboard Not tested since Sep 2026

Source: Official Ping or Peek 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 Best so far
0% 20% 40% 60% 80% 100% Near the ceiling (85%) Claude Sonnet 5.5 0% 20% 40% 60% 80% 100% Near the ceiling (85%) Claude Sonnet 5.5

Source: Official Ping or Peek 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 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 11 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 5 pass
  • Pass Independent runs Scores from the official leaderboard (6 entries).
  • Pass Models scored 6 models we track.
  • Pass Newest score The newest is from September 2026, for GPT-6.1 Sol.
  • Pass Frontier models 5 of the top 10 have a score, led by GPT-6 Astra (#4).
  • Pass Headroom The best is 0.59%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on huggingface.co: 6 rows for models we track 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