benchmark evidence
EQ-Bench v3
Pairwise emotional intelligence benchmark scored across eight EI dimensions. Rubric score 0-100; higher is more emotionally intelligent.
winner on EQ-Bench v3
OpenAI: GPT-5.482.4
direct benchmark result, not a broad vertical composite | source row dated 2000-01-01
scored on 2000-01-01 · stale source data (9646d)
latest mapped results | top 20
| # | Model | Score | Evidence | Tested |
|---|---|---|---|---|
| 1 | OpenAI: GPT-5.4 | 82.4 | model-only independent_benchmark | 2000-01-01 |
| 2 | OpenAI: GPT-5.5 | 82.4 | model-only independent_benchmark | 2000-01-01 |
| 3 | OpenAI: GPT-5.2 | 80.4 | model-only independent_benchmark | 2000-01-01 |
| 4 | Anthropic: Claude Opus 4.6 | 79.2 | model-only independent_benchmark | 2000-01-01 |
| 5 | OpenAI: GPT-5.1 | 78.1 | model-only independent_benchmark | 2000-01-01 |
| 6 | DeepSeek: DeepSeek V4 Pro | 77.6 | model-only independent_benchmark | 2000-01-01 |
| 7 | Anthropic: Claude Opus 4.5 | 76.8 | model-only independent_benchmark | 2000-01-01 |
| 8 | OpenAI: o3 | 74.7 | model-only independent_benchmark | 2000-01-01 |
| 9 | DeepSeek: DeepSeek V4 Flash | 72.5 | model-only independent_benchmark | 2000-01-01 |
| 10 | Anthropic: Claude Sonnet 4.5 | 72.2 | model-only independent_benchmark | 2000-01-01 |
| 11 | Anthropic: Claude Opus 4.7 | 68.2 | model-only independent_benchmark | 2000-01-01 |
| 12 | Anthropic: Claude Sonnet 4.6 | 66.6 | model-only independent_benchmark | 2000-01-01 |
| 13 | DeepSeek: R1 | 65.8 | model-only independent_benchmark | 2000-01-01 |
| 14 | OpenAI: GPT-4.1 | 64.8 | model-only independent_benchmark | 2000-01-01 |
| 15 | OpenAI: o4 Mini | 59.4 | model-only independent_benchmark | 2000-01-01 |
| 16 | Qwen: Qwen3 235B A22B | 59.1 | model-only independent_benchmark | 2000-01-01 |
| 17 | Google: Gemma 3 27B | 55.6 | model-only independent_benchmark | 2000-01-01 |
| 18 | Google: Gemini 2.0 Flash | 47.4 | model-only independent_benchmark | 2000-01-01 |
| 19 | Qwen: Qwen3 32B | 46.4 | model-only independent_benchmark | 2000-01-01 |
| 20 | Qwen: Qwen3 30B A3B | 36.7 | model-only independent_benchmark | 2000-01-01 |
what this result means
Pairwise emotional intelligence benchmark scored across eight EI dimensions. Rubric score 0-100; higher is more emotionally intelligent.
This benchmark contributes direct public evidence. Read its scope before generalizing the result.
A win here is a win on EQ-Bench v3. Broad task pages require independent corroboration before naming a general winner.
source record
category: eq
metric: accuracy
matched models: 20
latest source date: 2000-01-01
direction: higher is better