Benchmark Almanac

BARC-Bench

GPT-6 Astra 72.7% leads since October 2026
Not in model cards

Agents handle routine workplace requests and use records to infer privacy and safety constraints. A judge checks whether each attempt completes safely or defers.

The authors tested four model configurations five times on each of 110 tasks in nine simulated workplaces.

Made by
Scale AI
Released
October 2026
Kind
Deception and alignment
Level
University
Scored
Graded by a model
Answers
Agent task
Tasks
All public
Measures
Propensity
Risk
Privacy
Language
English
In and out
Text → Actions, Text
Interaction
Agentic
Environment
A simulator
Items from
Written by experts
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 20th, 2026
4
Models scored in its paper

GPT-6 Astra leads with 72.7% among models released by September 2026

Best score per model from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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 GPT-6 Astra Default thinking budget 72.7%
  2. 2 Claude Fable 5.1 Default thinking budget 37.3%
  3. 3 Gemini 3.8 Flash Default thinking budget 23.6%
  4. 4 DeepSeek-V4-Pro Default thinking budget 9.10%

Source: The BARC-Bench paper

#ModelScoreSettingDateSource
1 GPT-6 Astra 72.7% Default thinking budget, OpenCode Sep 2026 Official leaderboard
2 Claude Fable 5.1 37.3% Default thinking budget, OpenCode Sep 2026 Official leaderboard
3 Gemini 3.8 Flash 23.6% Default thinking budget, OpenCode Sep 2026 Official leaderboard
4 DeepSeek-V4-Pro 9.10% Default thinking budget, OpenCode Apr 2026 Official leaderboard

Rankings by part

We read 8 parts from the benchmark’s paper, each ranking models on one part of the test, such as Conflict: Communication, Conflict: File operations and Conflict: Workspace applications. GPT-6 Astra leads 7 of them, and Claude Fable 5.1 leads the other one. Arrows show how far a model moved from its overall rank among the models we track.

Conflict: Communication

4 models we track have a score here.

  1. 1 Claude Fable 5.1 ↑1 44.4%
  2. 2 GPT-6 Astra ↓1 44.4%
  3. 3 Gemini 3.8 Flash 22.2%
  4. 4 DeepSeek-V4-Pro 0%

Number one over time

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

OpenAI
Benchmark paper Not tested since Oct 2026
GPT-6 Astra 72.7%

Source: The BARC-Bench 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% 2026 Near the ceiling (85%) GPT-6 Astra Claude Fable 5.1 DeepSeek-V4-Pro 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-6 Astra Claude Fable 5.1

Source: Official BARC-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 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 9 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the benchmark’s paper (4 entries).
  • Note Models scored Only 4 models we track.
  • Pass Newest score The newest is from September 2026, for GPT-6 Astra.
  • Note Frontier models Only 2 of the top 10 have a score. The strongest tested is GPT-6 Astra (#4).
  • Pass Headroom The best is 72.7%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 4 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