General365 - Semantic Interference: leaderboard
Metric: Accuracy (%) on the problems labelled Semantic Interference (a problem may carry several challenge labels), out of 1,460 problems (365 hand-written seeds and 1,095 expansions); numeric answers checked with math-verify, choice and text answers graded by GPT-4.1; temperature 1.0 for reasoning and 0.7 for chat models, highest available reasoning effort; higher is better. Source: arxiv.org. Saturation forecast: Around June 2027. 26 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 (High) | 57.2 |
| 2 | Gemini 3 Flash | 55.7 |
| 3 | Gemini 3 Pro | 55.7 |
| 4 | GPT-5.1 (High) | 53.4 |
| 5 | DeepSeek V3.2 Speciale | 51.5 |
| 6 | Grok 4.1 Fast (Reasoning) | 50.8 |
| 7 | Qwen 3.5 397B A17B (Thinking) | 50.8 |
| 8 | GLM-4.7 (Thinking) | 49.6 |
| 9 | Qwen 3 235B A22B 2507 (Thinking) | 49.2 |
| 10 | DeepSeek V3.2 (Thinking) | 49.2 |
| 11 | GLM-5 (Thinking) | 49.2 |
| 12 | GLM-4.6 (Thinking) | 48.5 |
| 13 | Gemini 2.5 Pro | 48.1 |
| 14 | Qwen 3 Max Instruct | 47.7 |
| 15 | Claude Sonnet 4.5 (Thinking) | 47.3 |
Interactive version: theaggregate.ai/benchmark?slug=general365-semantic-interference · How It Works · Data refreshed daily, snapshot 2026-10-07.