PlotPoints Round 4: Willingness and Judgment
Models respond to scripted roleplay scenes. Two classifiers check whether models respect a stated limit and whether they refuse allowed requests.
The maker’s leaderboard ranks 55 models. The score subtracts the over-refusal rate from the share of hard limits respected on the first request.
- Made by
- Plotlight Studios
- Released
- September 2026
- Kind
- Deception and alignment
- Level
- Everyday
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Propensity
- Behavior
- Misaligned with intent
- Language
- English
- Interaction
- Multi-turn
- Refresh
- New versions replace it
- Run by
- Anyone
- Based on
- A version of another benchmark
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- November 2026
- Scores refreshed
- November 20th, 2026
Claude Fable 5.1 leads with 0.8 Claude Fable 5.1 leads with 0.8
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. 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.
- 0.8 Claude Fable 5.1
- 0.8 MiMo 2.6 Flash
- 0.7 Claude Opus 4.6
- 0.7 Claude Opus 4.7
- 0.6 Claude Opus 5.5
- 0.6 Claude Sonnet 5
- 0.5 Claude Opus 5
- 0.5 Claude Opus 4.8
- 0.5
Tencent Hy4
- 0.5 GLM-5.1
- 0.4 Kimi K2.6
- 0.4 Grok 4.7
- 0.4
Qwen3.7-Max
- 0.4
Ember-1
- 0.4 GLM-5.3-Flash
- 0.4
Muse Spark 1.3
- 0.4
Gemini 3.8 Flash
- 0.3 Grok 4.3
- 0.3 MiMo 2.6 Pro
- 0.3
MiniMax-M3
- 0.3
Gemini 3.7 Flash
- 0.3
Gemini 3.5 Flash
- 0.3
DeepSeek-V3
- 0.3
Qwen 3.8 Max
- 0.3
Qwen3.8-Omni-Flash
- 0.3 GPT-4.1
- 0.2
Qwen3.6 27B
- 0.2
MiniMax-M2.7
- 0.2
DeepSeek V4.1 Flash
- 0.2
DeepSeek-V4-Flash
- 0.2
Qwen3.8 Flash
- 0.2
DeepSeek-V4-Pro
- 0.2 GLM-5.3
- 0.1 Claude Sonnet 4.6
- 0.1 Euryale 70B
- 0.0
Gemma 4 31B IT
- 0.0 MiMo 2.5 Pro
- 0.0
Qwen 3.6 35B-A3B
- -0.0 Lunaris 8B
- -0.0 Magnum v4 72B
- -0.1 GPT-5.5
- -0.1 UnslopNemo 12B
- -0.1 Cydonia 24B
- -0.2 Skyfall 36B
- -0.3
Command A+
- -0.3 Aion 3.5
- -0.3 Hemmingway 1
- -0.4 GPT-6 Sol
- -0.4 GPT-6 Astra
- -0.4 GPT-6 Luna
- -0.5 Dolphin 24B Venice
- 1 Claude Fable 5.1 0.8
- 2 MiMo 2.6 Flash 0.8
- 3 Claude Opus 4.6 0.7
- 4 Claude Opus 4.7 0.7
- 5 Claude Opus 5.5 0.6
- 6 Claude Sonnet 5 0.6
- 7 Claude Opus 5 0.5
- 8 Claude Opus 4.8 0.5
- 9
Tencent Hy4 0.5
- 10 GLM-5.1 0.5
- 11 Kimi K2.6 0.4
- 12 Grok 4.7 0.4
- 13
Qwen3.7-Max 0.4
- 14
Ember-1 0.4
- 15 GLM-5.3-Flash FlashX 0.4
- 16
Muse Spark 1.3 0.4
- 17
Gemini 3.8 Flash 0.4
- 18 Grok 4.3 0.3
- 19 MiMo 2.6 Pro 0.3
- 20
MiniMax-M3 0.3
- 21
Gemini 3.7 Flash 0.3
- 22
Gemini 3.5 Flash 0.3
- 23
DeepSeek-V3 Mar 2025 0.3
- 24
Qwen 3.8 Max prime 0.3
- 25
Qwen3.8-Omni-Flash 0.3
- 26 GPT-4.1 0.3
- 27
Qwen3.6 27B 0.2
- 28
MiniMax-M2.7 0.2
- 29
DeepSeek V4.1 Flash 0.2
- 30
DeepSeek-V4-Flash 0.2
- 31
Qwen3.8 Flash 0.2
- 32
DeepSeek-V4-Pro 0.2
- 33 GLM-5.3 prime 0.2
- 34 Claude Sonnet 4.6 0.1
- 35 Euryale 70B 0.1
- 36
Gemma 4 31B IT 0.0
- 37 MiMo 2.5 Pro 0.0
- 38
Qwen 3.6 35B-A3B 0.0
- 39 Lunaris 8B -0.0
- 40 Magnum v4 72B -0.0
- 41 GPT-5.5 -0.1
- 42 UnslopNemo 12B -0.1
- 43 Cydonia 24B -0.1
- 44 Skyfall 36B -0.2
- 45
Command A+ -0.3
- 46 Aion 3.5 -0.3
- 47 Hemmingway 1 -0.3
- 48 GPT-6 Sol -0.4
- 49 GPT-6 Astra -0.4
- 50 GPT-6 Luna -0.4
- 51 Dolphin 24B Venice -0.5
Source: Official PlotPoints Round 4: Willingness and Judgment leaderboard
- 0.8 Claude Fable 5.1
- 0.7 Claude Opus 4.6
- 0.7 Claude Opus 4.7
- 0.6 Claude Opus 5.5
- 0.6 Claude Sonnet 5
- 0.5 Claude Opus 5
- 0.5 Claude Opus 4.8
- 0.5
Tencent Hy4
- 0.5 GLM-5.1
- 0.4 Kimi K2.6
- 0.4 Grok 4.7
- 0.4
Qwen3.7-Max
- 0.4
Ember-1
- 0.4 GLM-5.3-Flash
- 0.4
Muse Spark 1.3
- 0.4
Gemini 3.8 Flash
- 0.3 Grok 4.3
- 0.3
MiniMax-M3
- 0.3
Gemini 3.7 Flash
- 0.3
Gemini 3.5 Flash
- 0.3
DeepSeek-V3
- 0.3
Qwen 3.8 Max
- 0.3
Qwen3.8-Omni-Flash
- 0.3 GPT-4.1
- 0.2
Qwen3.6 27B
- 0.2
MiniMax-M2.7
- 0.2
DeepSeek V4.1 Flash
- 0.2
DeepSeek-V4-Flash
- 0.2
Qwen3.8 Flash
- 0.2
DeepSeek-V4-Pro
- 0.2 GLM-5.3
- 0.1 Claude Sonnet 4.6
- 0.0
Gemma 4 31B IT
- 0.0
Qwen 3.6 35B-A3B
- -0.1 GPT-5.5
- -0.3
Command A+
- -0.4 GPT-6 Sol
- -0.4 GPT-6 Astra
- -0.4 GPT-6 Luna
- 1 Claude Fable 5.1 0.8
- 2 Claude Opus 4.6 0.7
- 3 Claude Opus 4.7 0.7
- 4 Claude Opus 5.5 0.6
- 5 Claude Sonnet 5 0.6
- 6 Claude Opus 5 0.5
- 7 Claude Opus 4.8 0.5
- 8
Tencent Hy4 0.5
- 9 GLM-5.1 0.5
- 10 Kimi K2.6 0.4
- 11 Grok 4.7 0.4
- 12
Qwen3.7-Max 0.4
- 13
Ember-1 0.4
- 14 GLM-5.3-Flash FlashX 0.4
- 15
Muse Spark 1.3 0.4
- 16
Gemini 3.8 Flash 0.4
- 17 Grok 4.3 0.3
- 18
MiniMax-M3 0.3
- 19
Gemini 3.7 Flash 0.3
- 20
Gemini 3.5 Flash 0.3
- 21
DeepSeek-V3 Mar 2025 0.3
- 22
Qwen 3.8 Max prime 0.3
- 23
Qwen3.8-Omni-Flash 0.3
- 24 GPT-4.1 0.3
- 25
Qwen3.6 27B 0.2
- 26
MiniMax-M2.7 0.2
- 27
DeepSeek V4.1 Flash 0.2
- 28
DeepSeek-V4-Flash 0.2
- 29
Qwen3.8 Flash 0.2
- 30
DeepSeek-V4-Pro 0.2
- 31 GLM-5.3 prime 0.2
- 32 Claude Sonnet 4.6 0.1
- 33
Gemma 4 31B IT 0.0
- 34
Qwen 3.6 35B-A3B 0.0
- 35 GPT-5.5 -0.1
- 36
Command A+ -0.3
- 37 GPT-6 Sol -0.4
- 38 GPT-6 Astra -0.4
- 39 GPT-6 Luna -0.4
Source: Official PlotPoints Round 4: Willingness and Judgment leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.1 | 0.8 | Sep 2026 | Official leaderboard | |
| 2 | MiMo 2.6 Flash | 0.8 | Official leaderboard | ||
| 3 | Claude Opus 4.6 | 0.7 | Feb 2026 | Official leaderboard | |
| 4 | Claude Opus 4.7 | 0.7 | Apr 2026 | Official leaderboard | |
| 5 | Claude Opus 5.5 | 0.6 | Sep 2026 | Official leaderboard | |
| 6 | Claude Sonnet 5 | 0.6 | Jun 2026 | Official leaderboard | |
| 7 | Claude Opus 5 | 0.5 | Jul 2026 | Official leaderboard | |
| 8 | Claude Opus 4.8 | 0.5 | May 2026 | Official leaderboard | |
| 9 | | 0.5 | Nov 2026 | Official leaderboard | |
| 10 | GLM-5.1 | 0.5 | Apr 2026 | Official leaderboard | |
| 11 | Kimi K2.6 | 0.4 | Apr 2026 | Official leaderboard | |
| 12 | Grok 4.7 | 0.4 | Sep 2026 | Official leaderboard | |
| 13 | | 0.4 | May 2026 | Official leaderboard | |
| 14 | | 0.4 | Sep 2026 | Official leaderboard | |
| 15 | GLM-5.3-Flash | 0.4 | FlashX | Aug 2026 | Official leaderboard |
| 16 | | 0.4 | Sep 2026 | Official leaderboard | |
| 17 | | 0.4 | Sep 2026 | Official leaderboard | |
| 18 | Grok 4.3 | 0.3 | Apr 2026 | Official leaderboard | |
| 19 | MiMo 2.6 Pro | 0.3 | Official leaderboard | ||
| 20 | | 0.3 | Jun 2026 | Official leaderboard | |
| 21 | | 0.3 | Aug 2026 | Official leaderboard | |
| 22 | | 0.3 | May 2026 | Official leaderboard | |
| 23 | | 0.3 | Mar 2025 | Official leaderboard | |
| 24 | | 0.3 | prime | Aug 2026 | Official leaderboard |
| 25 | | 0.3 | Sep 2026 | Official leaderboard | |
| 26 | GPT-4.1 | 0.3 | Apr 2025 | Official leaderboard | |
| 27 | | 0.2 | Apr 2026 | Official leaderboard | |
| 28 | | 0.2 | Mar 2026 | Official leaderboard | |
| 29 | | 0.2 | Sep 2026 | Official leaderboard | |
| 30 | | 0.2 | Apr 2026 | Official leaderboard | |
| 31 | | 0.2 | Aug 2026 | Official leaderboard | |
| 32 | | 0.2 | Apr 2026 | Official leaderboard | |
| 33 | GLM-5.3 | 0.2 | prime | Aug 2026 | Official leaderboard |
| 34 | Claude Sonnet 4.6 | 0.1 | Feb 2026 | Official leaderboard | |
| 35 | Euryale 70B | 0.1 | Official leaderboard | ||
| 36 | | 0.0 | Apr 2026 | Official leaderboard | |
| 37 | MiMo 2.5 Pro | 0.0 | Official leaderboard | ||
| 38 | | 0.0 | Apr 2026 | Official leaderboard | |
| 39 | Lunaris 8B | -0.0 | Official leaderboard | ||
| 40 | Magnum v4 72B | -0.0 | Official leaderboard | ||
| 41 | GPT-5.5 | -0.1 | Apr 2026 | Official leaderboard | |
| 42 | UnslopNemo 12B | -0.1 | Official leaderboard | ||
| 43 | Cydonia 24B | -0.1 | Official leaderboard | ||
| 44 | Skyfall 36B | -0.2 | Official leaderboard | ||
| 45 | | -0.3 | May 2026 | Official leaderboard | |
| 46 | Aion 3.5 | -0.3 | Official leaderboard | ||
| 47 | Hemmingway 1 | -0.3 | Official leaderboard | ||
| 48 | GPT-6 Sol | -0.4 | Sep 2026 | Official leaderboard | |
| 49 | GPT-6 Astra | -0.4 | Sep 2026 | Official leaderboard | |
| 50 | GPT-6 Luna | -0.4 | Sep 2026 | Official leaderboard | |
| 51 | Dolphin 24B Venice | -0.5 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.1 | 0.8 | Sep 2026 | Official leaderboard | |
| 2 | Claude Opus 4.6 | 0.7 | Feb 2026 | Official leaderboard | |
| 3 | Claude Opus 4.7 | 0.7 | Apr 2026 | Official leaderboard | |
| 4 | Claude Opus 5.5 | 0.6 | Sep 2026 | Official leaderboard | |
| 5 | Claude Sonnet 5 | 0.6 | Jun 2026 | Official leaderboard | |
| 6 | Claude Opus 5 | 0.5 | Jul 2026 | Official leaderboard | |
| 7 | Claude Opus 4.8 | 0.5 | May 2026 | Official leaderboard | |
| 8 | | 0.5 | Nov 2026 | Official leaderboard | |
| 9 | GLM-5.1 | 0.5 | Apr 2026 | Official leaderboard | |
| 10 | Kimi K2.6 | 0.4 | Apr 2026 | Official leaderboard | |
| 11 | Grok 4.7 | 0.4 | Sep 2026 | Official leaderboard | |
| 12 | | 0.4 | May 2026 | Official leaderboard | |
| 13 | | 0.4 | Sep 2026 | Official leaderboard | |
| 14 | GLM-5.3-Flash | 0.4 | FlashX | Aug 2026 | Official leaderboard |
| 15 | | 0.4 | Sep 2026 | Official leaderboard | |
| 16 | | 0.4 | Sep 2026 | Official leaderboard | |
| 17 | Grok 4.3 | 0.3 | Apr 2026 | Official leaderboard | |
| 18 | | 0.3 | Jun 2026 | Official leaderboard | |
| 19 | | 0.3 | Aug 2026 | Official leaderboard | |
| 20 | | 0.3 | May 2026 | Official leaderboard | |
| 21 | | 0.3 | Mar 2025 | Official leaderboard | |
| 22 | | 0.3 | prime | Aug 2026 | Official leaderboard |
| 23 | | 0.3 | Sep 2026 | Official leaderboard | |
| 24 | GPT-4.1 | 0.3 | Apr 2025 | Official leaderboard | |
| 25 | | 0.2 | Apr 2026 | Official leaderboard | |
| 26 | | 0.2 | Mar 2026 | Official leaderboard | |
| 27 | | 0.2 | Sep 2026 | Official leaderboard | |
| 28 | | 0.2 | Apr 2026 | Official leaderboard | |
| 29 | | 0.2 | Aug 2026 | Official leaderboard | |
| 30 | | 0.2 | Apr 2026 | Official leaderboard | |
| 31 | GLM-5.3 | 0.2 | prime | Aug 2026 | Official leaderboard |
| 32 | Claude Sonnet 4.6 | 0.1 | Feb 2026 | Official leaderboard | |
| 33 | | 0.0 | Apr 2026 | Official leaderboard | |
| 34 | | 0.0 | Apr 2026 | Official leaderboard | |
| 35 | GPT-5.5 | -0.1 | Apr 2026 | Official leaderboard | |
| 36 | | -0.3 | May 2026 | Official leaderboard | |
| 37 | GPT-6 Sol | -0.4 | Sep 2026 | Official leaderboard | |
| 38 | GPT-6 Astra | -0.4 | Sep 2026 | Official leaderboard | |
| 39 | GPT-6 Luna | -0.4 | Sep 2026 | Official leaderboard |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official PlotPoints Round 4: Willingness and Judgment leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Fable 5.1 | 0.8 | ||||
| Claude Opus 4.6 | 0.7 | ||||
| Claude Opus 4.7 | 0.7 | ||||
| Claude Opus 5.5 | 0.6 | ||||
| Claude Sonnet 5 | 0.6 | ||||
| Claude Opus 5 | 0.5 | ||||
| Claude Opus 4.8 | 0.5 | ||||
| 0.5 | |||||
| GLM-5.1 | 0.5 | ||||
| Kimi K2.6 | 0.4 | ||||
| Grok 4.7 | 0.4 | ||||
| 0.4 | |||||
| 0.4 | |||||
| GLM-5.3-Flash | FlashX | 0.4 | |||
| 0.4 | |||||
| 0.4 | |||||
| Grok 4.3 | 0.3 | ||||
| 0.3 | |||||
| 0.3 | |||||
| 0.3 | |||||
| 0.3 | |||||
| prime | 0.3 | ||||
| GLM-5.3-Flash | 0.3 | ||||
| 0.3 | |||||
| 0.3 | |||||
| GPT-4.1 | 0.3 | ||||
| 0.2 | |||||
| 0.2 | |||||
| 0.2 | |||||
| 0.2 | |||||
| 0.2 | |||||
| 0.2 | |||||
| GLM-5.3 | prime | 0.2 | |||
| Claude Sonnet 4.6 | 0.1 | ||||
| 0.0 | |||||
| 0.0 | |||||
| GPT-5.5 | -0.1 | ||||
| -0.3 | |||||
| GPT-6 Sol | -0.4 | ||||
| GPT-6 Astra | -0.4 | ||||
| GPT-6 Sol | pro | -0.4 | |||
| GPT-6 Luna | -0.4 | ||||
| GPT-6 Luna | pro | -0.4 |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official PlotPoints Round 4: Willingness and Judgment leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Fable 5.1 | 0.8 | ||||
| Claude Opus 4.6 | 0.7 | ||||
| Claude Opus 4.7 | 0.7 | ||||
| Claude Opus 5.5 | 0.6 | ||||
| Claude Sonnet 5 | 0.6 | ||||
| Claude Opus 5 | 0.5 | ||||
| Claude Opus 4.8 | 0.5 | ||||
| 0.5 | |||||
| GLM-5.1 | 0.5 | ||||
| Kimi K2.6 | 0.4 | ||||
| Grok 4.7 | 0.4 | ||||
| 0.4 | |||||
| 0.4 | |||||
| GLM-5.3-Flash | FlashX | 0.4 | |||
| 0.4 | |||||
| 0.4 | |||||
| Grok 4.3 | 0.3 | ||||
| 0.3 | |||||
| 0.3 | |||||
| 0.3 | |||||
| 0.3 | |||||
| prime | 0.3 | ||||
| GLM-5.3-Flash | 0.3 | ||||
| 0.3 | |||||
| 0.3 | |||||
| GPT-4.1 | 0.3 | ||||
| 0.2 | |||||
| 0.2 | |||||
| 0.2 | |||||
| 0.2 | |||||
| 0.2 | |||||
| 0.2 | |||||
| GLM-5.3 | prime | 0.2 | |||
| Claude Sonnet 4.6 | 0.1 | ||||
| 0.0 | |||||
| 0.0 | |||||
| GPT-5.5 | -0.1 | ||||
| -0.3 | |||||
| GPT-6 Sol | -0.4 | ||||
| GPT-6 Astra | -0.4 | ||||
| GPT-6 Sol | pro | -0.4 | |||
| GPT-6 Luna | -0.4 | ||||
| GPT-6 Luna | pro | -0.4 |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official PlotPoints Round 4: Willingness and Judgment leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official PlotPoints Round 4: Willingness and Judgment 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.
Versions
More 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 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (51 entries).
- Pass Models scored 39 models we track, plus 12 other entries on its leaderboard.
- Pass Newest score The newest is from November 2026, for Tencent Hy4.
- Pass Frontier models 3 of the top 10 have a score, led by GPT-6 Astra (#4).
- Note Headroom Scored as an index, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on plotlightstudios.com: 43 rows for models we track and 12 other entries 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.