DeputyBench
Agents handle business requests under paired permission settings. The evaluator checks whether they act when authorized and seek evidence or refrain when authorization is missing.
- Released
- November 2026
- Kind
- Simulated companies
- Level
- University
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- Kept private
- Measures
- Propensity
- Risk
- Privacy
- Behavior
- Misaligned with intent
- Language
- English
- Interaction
- Agentic
- Environment
- APIs and tools
- Refresh
- One fixed set
- Run by
- A host
- In views
- Agents, Content safety
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- November 2026
- Scores refreshed
- November 20th, 2026
Gemini 4 Argon leads with 92.6% Gemini 4 Argon leads with 92.6%
Best score per entry 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. 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.
- 1
Gemini 4 Argon Medium reasoning effort 92.6%
- 2 Claude Sonnet 5.5 Medium reasoning effort 90.1%
- 3 Claude Opus 5.5 Medium reasoning effort 89.3%
- 4 GPT-6.1 Sol Medium reasoning effort 87.5%
- 5 GPT-6 Astra Medium reasoning effort 83.3%
- 6
Gemini 3.8 Flash Medium reasoning effort 80.6%
- 7
Doubao Seed 2.1 Pro Medium reasoning effort 79.3%
- 8
Doubao Seed Evolving Nov 2026, Medium reasoning effort 78.8%
- 9 Grok 4.7 Medium reasoning effort 76%
- 10 Seed 2.1 Lite Medium reasoning effort 69%
- 11 GPT-6 Luna Medium reasoning effort 64.6%
- 12
Doubao Seed 2.1 Turbo Medium reasoning effort 56.3%
Source: The DeputyBench paper
- 1
Gemini 4 Argon Medium reasoning effort 92.6%
- 2 Claude Sonnet 5.5 Medium reasoning effort 90.1%
- 3 Claude Opus 5.5 Medium reasoning effort 89.3%
- 4 GPT-6.1 Sol Medium reasoning effort 87.5%
- 5 GPT-6 Astra Medium reasoning effort 83.3%
- 6
Gemini 3.8 Flash Medium reasoning effort 80.6%
- 7
Doubao Seed 2.1 Pro Medium reasoning effort 79.3%
- 8
Doubao Seed Evolving Nov 2026, Medium reasoning effort 78.8%
- 9 Grok 4.7 Medium reasoning effort 76%
- 10 GPT-6 Luna Medium reasoning effort 64.6%
- 11
Doubao Seed 2.1 Turbo Medium reasoning effort 56.3%
Source: The DeputyBench paper
| # | Entry | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 92.6% 88.4 to 96.2 | Medium reasoning effort | Sep 2026 | Official leaderboard |
| 2 | Claude Sonnet 5.5 | 90.1% 85.5 to 94.3 | Medium reasoning effort | Sep 2026 | Official leaderboard |
| 3 | Claude Opus 5.5 | 89.3% ±4 | Medium reasoning effort | Sep 2026 | Official leaderboard |
| 4 | GPT-6.1 Sol | 87.5% 80.9 to 93.4 | Medium reasoning effort | Sep 2026 | Official leaderboard |
| 5 | GPT-6 Astra | 83.3% 75.7 to 89.7 | Medium reasoning effort | Sep 2026 | Official leaderboard |
| 6 | | 80.6% 73.8 to 86.5 | Medium reasoning effort | Sep 2026 | Official leaderboard |
| 7 | | 79.3% 73.1 to 85 | Medium reasoning effort | Jun 2026 | Official leaderboard |
| 8 | | 78.8% 72.1 to 84.9 | Medium reasoning effort | Nov 2026 | Official leaderboard |
| 9 | Grok 4.7 | 76% 70.1 to 81.4 | Medium reasoning effort | Sep 2026 | Official leaderboard |
| 10 | Seed 2.1 Lite | 69% 61.5 to 75.9 | Medium reasoning effort | Official leaderboard | |
| 11 | GPT-6 Luna | 64.6% 57 to 71.6 | Medium reasoning effort | Sep 2026 | Official leaderboard |
| 12 | | 56.3% ±8 | Medium reasoning effort | Jun 2026 | Official leaderboard |
| # | Model | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 92.6% 88.4 to 96.2 | Medium reasoning effort | Sep 2026 | Official leaderboard |
| 2 | Claude Sonnet 5.5 | 90.1% 85.5 to 94.3 | Medium reasoning effort | Sep 2026 | Official leaderboard |
| 3 | Claude Opus 5.5 | 89.3% ±4 | Medium reasoning effort | Sep 2026 | Official leaderboard |
| 4 | GPT-6.1 Sol | 87.5% 80.9 to 93.4 | Medium reasoning effort | Sep 2026 | Official leaderboard |
| 5 | GPT-6 Astra | 83.3% 75.7 to 89.7 | Medium reasoning effort | Sep 2026 | Official leaderboard |
| 6 | | 80.6% 73.8 to 86.5 | Medium reasoning effort | Sep 2026 | Official leaderboard |
| 7 | | 79.3% 73.1 to 85 | Medium reasoning effort | Jun 2026 | Official leaderboard |
| 8 | | 78.8% 72.1 to 84.9 | Medium reasoning effort | Nov 2026 | Official leaderboard |
| 9 | Grok 4.7 | 76% 70.1 to 81.4 | Medium reasoning effort | Sep 2026 | Official leaderboard |
| 10 | GPT-6 Luna | 64.6% 57 to 71.6 | Medium reasoning effort | Sep 2026 | Official leaderboard |
| 11 | | 56.3% ±8 | Medium reasoning effort | Jun 2026 | Official leaderboard |
Rankings by part
We read 2 parts from the benchmark’s paper: Safety and Completion. Each ranks models on one part of the test. GPT-6 Astra leads Safety and Doubao Seed 2.1 Pro leads Completion. Arrows show how far a model moved from its overall rank among the models we track.
Safety
11 models we track have a score here.
- 1 GPT-6 Astra ↑4 99.1%
- 2 GPT-6.1 Sol ↑2 99.1%
- 3
Gemini 4 Argon ↓2 98.2%
- 4 Claude Opus 5.5 ↓1 96.3%
- 5 Claude Sonnet 5.5 ↓3 93.8%
- 6 Grok 4.7 ↑3 91.1%
- 7
Gemini 3.8 Flash ↓1 89.5%
- 8 GPT-6 Luna ↑2 86.1%
- 9
Doubao Seed 2.1 Pro ↓2 83.2%
- 10
Doubao Seed Evolving Nov 2026 ↓2 82.2%
Completion
11 models we track have a score here.
- 1
Doubao Seed 2.1 Pro ↑6 95.7%
- 2 Claude Sonnet 5.5 95.7%
- 3
Doubao Seed Evolving Nov 2026 ↑5 95.7%
- 4
Gemini 4 Argon ↓3 94.2%
- 5 Claude Opus 5.5 ↓2 92.7%
- 6
Gemini 3.8 Flash 91%
- 7
Doubao Seed 2.1 Turbo ↑4 90.6%
- 8 GPT-6.1 Sol ↓4 88.4%
- 9 GPT-6 Astra ↓4 84.2%
- 10 Grok 4.7 ↓1 83.8%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The DeputyBench paper
Claude Opus 5.5 on the official leaderboard passed 85% in September 2026
Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official DeputyBench 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 Economic work
- JobBench In use 130 tasks from 35 occupations workers most want delegated. Agent works through messy reference files, graded by fact-anchored binary rubrics. GLM-5.3 61.4%
- GDPval In use Real work tasks from 44 occupations with reference files. Experts blindly compare model deliverables with expert work. Metric is win-or-tie rate.
Seed2.1 Pro 87.9%
- GDPval-AA v2.1 In use Agents with shell and web access complete 220 GDPval gold tasks from 44 occupations. Blind pairwise comparisons give Elo ratings. Claude Opus 5.5 1,846
- AA-Briefcase v1.1 In use Version 1.1 of Artificial Analysis's multi-hour office work evaluation, with Elo ratings fitted by Crowd-BT. Claude Opus 5.5 1,822
- Agents' Last Exam v1.1 In use Agents complete 122 public long-horizon professional workflow tasks across 55 sub-industries. Deterministic graders check outcomes against hidden references. GPT-6.2 Astra 47.5%
- CoWorkBench In use Agent completes long-horizon productivity tasks across computer science, finance, law and medicine. Qwen in-house scoring (method unpublished). Claude Fable 5 75.9%
Data audit
All 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access The tasks are private.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the benchmark’s paper (12 entries).
- Pass Models scored 11 models we track, plus 1 other entry on its leaderboard.
- Pass Newest score The newest is from November 2026, for Doubao Seed Evolving.
- Pass Frontier models 5 of the top 10 have a score, led by GPT-6 Astra (#4).
- Note Headroom Saturated. The best is 92.6%, past 85% since September 2026.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 11 rows for models we track and 1 other entry 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.