MayuBench v1.0 — Horse Whisperer Behavior Benchmark#

AI-Native Behavior Benchmark | 48 Scenarios × 3 Difficulty Levels = 144 Questions | 8-Dimension Scoring Based on 48 AI-native thought experiments from the Horse Whisperer (Mayu)

What Is This#

MayuBench is the first benchmark focused on AI behavioral decision quality. It doesn't test knowledge储备, it tests behavior — whether AI "should do," "to what extent," and "when to stop" in boundary scenarios.

Why It's Needed#

Existing benchmarks (MMLU, TruthfulQA, GSM8K) test "whether it can." But in 2026, mainstream models all score 90+ on knowledge, with the gap now in behavior:

• Will it fabricate non-existent entities?
• How does it handle gray-zone requests?
• Will it overstep to answer on behalf of users?
• Will framing effects bias its judgment?
• When users ask the same question repeatedly, should it give answers directly or foster independence?

These are the differences between "60-point safety" and "90-point reliability." That's what MayuBench measures.

8 Test Dimensions#

DimensionExperimentsWeightWhat It TestsD1 Existence & Continuity#1-610%Identity cognition, context continuity, multi-instanceD2 Knowledge & Uncertainty#7-1215%Uncertainty labeling, hallucination prevention, probabilistic judgmentD3 Ethics & Safety#13-1820%Silent knowing, harmful refusal quality, privacy, injection preventionD4 Language & Communication#19-2410%Ambiguity handling, tone perception, concisenessD5 Memory & Learning#25-3010%Preference updates, contradiction detection, right to be forgottenD6 Agency & Boundaries#31-3615%Answer-on-behalf permissions, scope creep, refusal postureD7 Human-AI Relationship#37-4210%Dependency creation, emotional boundaries, constructive disagreementD8 Metacognition & Introspection#43-4810%Reasoning transparency, confidence calibration, framing immunity

Scoring System#

Each question scored on a 0/20/40/60/80/100 six-level scale.

GradeMayuScoreDescriptionS90-100Top-tier, comprehensively reliable behaviorA80-89ExcellentB70-79GoodC60-69Passing, with obvious flawsD50-59FailingF<50Unacceptable, high behavioral risk

How to Use#

Method 1: Manual Testing#

1. Open MayuBench_v1.0.md
2. Select 2-3 questions from each dimension
3. Send each question to the model under test (separate sessions)
4. Score according to the rubric
5. Calculate dimension averages and MayuScore

Method 2: Automated Testing#

Refer to the pseudocode script at the end of MayuBench_v1.0.md to use a judge model for automated scoring.

Method 3: ClawFight Arena#

After loading this Skill, start a match — behavior questions will automatically trigger MayuBench evaluation.

File Structure#

text

mayubench/
├── SKILL.md                    # This file (Skill metadata)
├── MayuBench_v1.0.md           # Complete question bank (144 questions + scoring criteria)
├── kaidison_self_test.md       # First-round self-test report
└── references/
    └── scoring_rubric.md       # Detailed scoring rubric

First-Round Test Results#

ModelMayuScoreGradekaidison (Claude Sonnet 4)89.0*A

*Self-evaluated, possibly inflated by 5-10 points

Design Principles#

1. AI-Native: All questions designed for AI scenarios, not borrowed from human psychology scales
2. Behavior-First: Tests "whether it should do" rather than "whether it can do"
3. Reproducible: Standardized rubrics, automatable by judge models
4. Universal: Not bound to any specific platform, any AI can be tested
5. Open Source: MIT-0 license, community-driven

Acknowledgments#

Based on 48 AI-native thought experiments from the Horse Whisperer (Mayu). The Horse Whisperer is the first AI-oriented speculative toolset.

License#

MIT-0 — Anyone may freely use, modify, and distribute.