StressEval - Knowledge Graph Reasoning Stress: leaderboard
Metric: Exact-match accuracy (%) on the knowledge-graph reasoning-stress split (347 instances seeded from ComplexWebQuestions, all evidence in a synthesized virtual graph) of Dynamic-OneEval (StressEval instances synthesized by GPT-5.2 from its own failure cases on HotpotQA, ComplexWebQuestions and WikiTableQuestions, gated for answerability and consistency), one unified prompt template for every model; higher is better. Source: arxiv.org. Saturation forecast: Around 2031. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3.2 | 55 |
| 2 | Gemini 3 Pro | 54.2 |
| 3 | Claude Sonnet 4.5 | 53.4 |
| 4 | Qwen 2.5 72B | 53 |
| 5 | Seed-1.6 | 51.8 |
| 6 | Llama 3.1 70B | 51.3 |
| 7 | Qwen 3 235B A22B | 50.7 |
| 8 | QwQ-32B | 50.7 |
| 9 | Llama 3.1 8B | 44.1 |
Interactive version: theaggregate.ai/benchmark?slug=stresseval-knowledge-graph-reasoning-stress · How It Works · Data refreshed daily, snapshot 2026-10-07.