ConflictQA - KG Conflict (Non-Complementary): leaderboard
Metric: Exact match (%) on 802 single-hop (non-complementary) questions when the provided evidence contains conflicting knowledge-graph triples (TripleConf); zero-shot with a conflict-aware prompt, the mean of two evidence orders; exact match of the generated answer set; higher is better. Source: arxiv.org. Saturation forecast: Around 2031. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O3 Mini | 38.03 |
| 2 | GPT-3.5 Turbo (0125) | 36.41 |
| 3 | DeepSeek V3.2 (Thinking) | 33.23 |
| 4 | GPT-4o | 32.67 |
| 5 | Llama 3.1 70B Instruct | 32.67 |
| 6 | GPT-5.1 | 32.05 |
| 7 | DeepSeek V3.2 (Non-reasoning) | 30.3 |
| 8 | Mistral Large 3 | 29.3 |
| 9 | Llama 3.1 8B Instruct | 19.2 |
| 10 | Qwen 3 8B | 7.61 |
Interactive version: theaggregate.ai/benchmark?slug=conflictqa-kg-conflict-non-complementary · How It Works · Data refreshed daily, snapshot 2026-10-07.