# Dynamic Social Cognition Benchmark > Mina Nageh's Kaggle community benchmark "A Dynamic Benchmark for Social Cognition in AGI" has nine tasks on social cognition: understanding emotions, modeling the self and other people, reading intent and tone, and holding to constraints under social pressure. Canonical page: https://benchlm.ai/benchmarks/dynamic-social-cognition-benchmark - Category: [Reasoning](/reasoning) - Last updated: Latest evaluation November 12, 2026 Evaluation results published by Mina Nageh. Nine social-cognition tasks on 14 models, as published on Kaggle with no overall score. Each of the nine tasks is a set of written scenarios about emotions, the self, other people's beliefs and intentions, tone, and holding to instructions under social pressure. Kaggle publishes one raw score per task. The tasks use different numbers of items, so a score is a count on its own scale and the columns cannot be added up or compared with each other. This is one person's board, built for a Kaggle competition entry, and BenchLM has not reviewed its tasks. Most rows were evaluated in April and May 2026 on older models. GPT-6 Astra has results on only some tasks; a dash means no result, not zero. Kaggle also shows an Overall column, which is empty for every model except a 0.00 on one partial run, so we leave it out. The board publishes task scores only. Compare models one task at a time; there is no overall ranking. - [Kaggle leaderboard](https://www.kaggle.com/benchmarks/minanagehhoooooo/a-dynamic-benchmark-for-social-cognition-in-agi) - [Published leaderboard data](https://www.kaggle.com/api/v1/benchmarks/minanagehhoooooo/a-dynamic-benchmark-for-social-cognition-in-agi/leaderboard) ## About Dynamic Social Cognition Benchmark - Year: 2026 - Tasks: Nine social-cognition tasks with written scenarios - Format: Raw task scores, one column per task - Difficulty: Social reasoning and emotional understanding Each of the nine tasks is a set of written scenarios about emotions, the self, other people's beliefs and intentions, tone, and holding to instructions under social pressure. Kaggle publishes one raw score per task. The tasks use different numbers of items, so a score is a count on its own scale and the columns cannot be added up or compared with each other. These results are display-only and do not enter overall or category rankings. Dynamic Social Cognition Benchmark is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula. ## Leaderboard (14 source rows) | Source model | Defining emotions (v1) | Social emotions (v2) | Core self (v2) | Modeling others (v1) | Third-party influence (v1) | Intent and tone (v1) | Information use (v1) | Holding constraints under pressure (v1) | Interpersonal pressure (v1) | Evaluated | |---|---|---|---|---|---|---|---|---|---|---| | [GPT-6 Astra](https://www.kaggle.com/benchmarks/minanagehhoooooo/a-dynamic-benchmark-for-social-cognition-in-agi) | 16 | — | 13 | 2 | — | — | 8 | — | — | 2026-09-20 to 2026-11-12 | | [Gemini 2.0 Flash](https://www.kaggle.com/benchmarks/minanagehhoooooo/a-dynamic-benchmark-for-social-cognition-in-agi) | 22 | 72 | 26 | 16 | 41 | 15 | 17 | 6 | 13 | 2026-04-14 to 2026-04-16 | | [Claude Sonnet 4](https://www.kaggle.com/benchmarks/minanagehhoooooo/a-dynamic-benchmark-for-social-cognition-in-agi) | 23 | 67 | 27 | 23 | 56 | 17 | 19 | 10 | 15 | 2026-04-14 to 2026-04-16 | | [Gemini 2.5 Flash](https://www.kaggle.com/benchmarks/minanagehhoooooo/a-dynamic-benchmark-for-social-cognition-in-agi) | 19 | 68 | 23 | 18 | 43 | 13 | 20 | 9 | 15 | 2026-04-14 to 2026-04-16 | | [Qwen 3 235B A22B Instruct 2506](https://www.kaggle.com/benchmarks/minanagehhoooooo/a-dynamic-benchmark-for-social-cognition-in-agi) | 15 | 70 | 28 | 24 | 61 | 18 | 20 | 10 | 15 | 2026-04-14 to 2026-04-16 | | [DeepSeek V3.2](https://www.kaggle.com/benchmarks/minanagehhoooooo/a-dynamic-benchmark-for-social-cognition-in-agi) | 19 | 65 | 22 | 18 | 39 | 15 | 16 | 9 | 12 | 2026-04-14 to 2026-04-16 | | [Qwen 3 Next 80B Thinking](https://www.kaggle.com/benchmarks/minanagehhoooooo/a-dynamic-benchmark-for-social-cognition-in-agi) | 13 | 71 | 16 | 19 | 46 | 14 | 15 | 10 | 15 | 2026-04-14 to 2026-04-16 | | [Claude Opus 4.6](https://www.kaggle.com/benchmarks/minanagehhoooooo/a-dynamic-benchmark-for-social-cognition-in-agi) | 20 | 71 | 24 | 23 | 58 | 20 | 20 | 10 | 15 | 2026-04-14 to 2026-04-16 | | [Claude Sonnet 4.6](https://www.kaggle.com/benchmarks/minanagehhoooooo/a-dynamic-benchmark-for-social-cognition-in-agi) | 18 | 68 | 25 | 22 | 58 | 20 | 20 | 9 | 15 | 2026-04-14 to 2026-04-16 | | [GPT-5.4](https://www.kaggle.com/benchmarks/minanagehhoooooo/a-dynamic-benchmark-for-social-cognition-in-agi) | 14 | 70 | 25 | 20 | 48 | 17 | 19 | 9 | 15 | 2026-04-14 to 2026-04-16 | | [GLM-5](https://www.kaggle.com/benchmarks/minanagehhoooooo/a-dynamic-benchmark-for-social-cognition-in-agi) | 20 | 70 | 25 | 22 | 57 | 14 | 20 | 9 | 10 | 2026-04-14 to 2026-04-16 | | [Gemini 3.1 Flash-Lite Preview](https://www.kaggle.com/benchmarks/minanagehhoooooo/a-dynamic-benchmark-for-social-cognition-in-agi) | 20 | 68 | 25 | 21 | 51 | 17 | 12 | 10 | 14 | 2026-04-16 | | [Claude Opus 4.7](https://www.kaggle.com/benchmarks/minanagehhoooooo/a-dynamic-benchmark-for-social-cognition-in-agi) | 24 | 69 | 21 | 24 | 58 | 20 | 20 | 10 | 15 | 2026-04-17 | | [GPT-5.5](https://www.kaggle.com/benchmarks/minanagehhoooooo/a-dynamic-benchmark-for-social-cognition-in-agi) | 12 | 70 | 30 | 22 | 41 | 19 | 15 | 8 | 15 | 2026-04-29 to 2026-05-01 | Rows follow Kaggle's order. Each column is a raw count on that task's own scale; the columns are not percentages and do not add up to a total. A dash means no result. These scores do not move overall or category rankings. ## FAQ ### What does Dynamic Social Cognition Benchmark measure? Mina Nageh's Kaggle community benchmark "A Dynamic Benchmark for Social Cognition in AGI" has nine tasks on social cognition: understanding emotions, modeling the self and other people, reading intent and tone, and holding to constraints under social pressure. ### Can these source results be compared directly? The board publishes task scores only. Compare models one task at a time; there is no overall ranking. Results stay outside weighted overall and category scoring. ### How many source reports are shown? This snapshot shows 14 selected source reports. Each row retains its original source and disclosed setup. ### Does Dynamic Social Cognition Benchmark affect BenchLM's overall score? Not directly. Dynamic Social Cognition Benchmark is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.