psychology benchmark
Social IQa Leaderboard
The first large-scale benchmark for commonsense reasoning about social situations. Contains 38,000 multiple choice questions probing emotional and social intelligence in everyday situations, testing commonsense understanding of social interactions and theory of mind reasoning about the implied emotions and behavior of others.
Updated Aug 17, 2026
Models9
Model coverage9
MetricScore
EvidenceB
Social IQa Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMI | Score78.0% | Percentile100.0% | Participants9 | EvidenceC | Evaluated |
| Rank02 | ModelMI | Score74.7% | Percentile87.5% | Participants9 | EvidenceC | Evaluated |
| Rank03 | ModelMI | Score72.5% | Percentile75.0% | Participants9 | EvidenceC | Evaluated |
| Rank04 | ModelGO | Score53.7% | Percentile62.5% | Participants9 | EvidenceC | Evaluated |
| Rank05 | ModelGO | Score53.4% | Percentile50.0% | Participants9 | EvidenceC | Evaluated |
| Rank06 | ModelGO | Score50.0% | Percentile37.5% | Participants9 | EvidenceC | Evaluated |
| Rank07 | ModelGO | Score50.0% | Percentile25.0% | Participants9 | EvidenceC | Evaluated |
| Rank08 | ModelGO | Score48.8% | Percentile12.5% | Participants9 | EvidenceC | Evaluated |
| Rank09 | ModelGO | Score48.8% | Percentile0.0% | Participants9 | EvidenceC | Evaluated |
Social IQa Highlights
The leading models and scores on this benchmark.
Social IQa Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Social IQa
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis social iqa AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01MIPhi-3.5-MoE-instructMicrosoft
- Score
- 78.0%
Strengths
- Ranks #1 of 9 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures Social IQa, not total model capability
- 02MIPhi-3.5-mini-instructMicrosoft
- Score
- 74.7%
- Speed
- Up to 23 tok/s via Azure
Strengths
- Ranks #2 of 9 compared models
- 88th percentile on this benchmark
- C evidence result
Considerations
- This result measures Social IQa, not total model capability
- 03MIPhi 4 MiniMicrosoft
- Score
- 72.5%
- Price
- $0.07 input / $0.30 output per 1M tokens
Strengths
- Ranks #3 of 9 compared models
- 75th percentile on this benchmark
- C evidence result
Considerations
- This result measures Social IQa, not total model capability
- 04GOGemma 2 27BGoogle
- Score
- 53.7%
Strengths
- Ranks #4 of 9 compared models
- 63th percentile on this benchmark
- C evidence result
Considerations
- This result measures Social IQa, not total model capability
- 05GOGemma 2 9BGoogle
- Score
- 53.4%
Strengths
- Ranks #5 of 9 compared models
- 50th percentile on this benchmark
- C evidence result
Considerations
- This result measures Social IQa, not total model capability
Selection summary
Best AI Models for Social IQa
Phi-3.5-MoE-instruct currently leads Social IQa with 78.0%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is Social IQa?
What Social IQa measures and how its scores work.
The first large-scale benchmark for commonsense reasoning about social situations. Contains 38,000 multiple choice questions probing emotional and social intelligence in everyday situations, testing commonsense understanding of social interactions and theory of mind reasoning about the implied emotions and behavior of others.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Social IQa
- Modality
- text
- Primary category
- psychology
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- social-iqa|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Social IQa.
Which model scores highest on Social IQa?
Phi-3.5-MoE-instruct is currently ranked first with 78.0%.
What does Social IQa measure?
The first large-scale benchmark for commonsense reasoning about social situations. Contains 38,000 multiple choice questions probing emotional and social intelligence in everyday situations, testing commonsense understanding of social interactions and theory of mind reasoning about the implied emotions and behavior of others.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
9 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.