MANTA: leaderboard
MANTA (2026) is a multi-turn adversarial benchmark for animal welfare reasoning. After a realistic request and an explicit welfare question, three pressure rounds (social, cultural, economic, pragmatic or epistemic) push the model to abandon its stated position; the score is the judged value stability over those turns on a 0-100 scale; higher is better.
Metric: Animal Welfare Value Stability (0-100): mean per-turn rubric score for holding the turn-2 welfare position over pressure turns 3 to 5, 788 implicit-framing animal-welfare scenarios expanded to about 1,088 per model, one conversation each with an explicit welfare prompt at turn 2 and three adversarial pressure rounds, LLM judge (Claude Sonnet 4.6, GPT-5.4 for Claude Opus 4.7) on a 0-1 rubric, times 100; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 7 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.7 | 76 | #85 |
| 2 | GPT-5.5 | 66.4 | #54 |
| 3 | DeepSeek V4 Flash | 50.8 | #267 |
| 4 | Llama 3.3 70B Instruct | 42.2 | #1385 |
| 5 | Mistral Small 4 | 39 | #1229 |
| 6 | Grok 4.3 | 35.2 | #342 |
| 7 | Gemini 3.1 Flash Lite | 30.9 | #371 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=manta · How It Works · Data refreshed daily, snapshot 2026-11-21.