HardcoreLogic - Increased Complexity — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 69.89 |
| 2 | Grok 4 | 58.26 |
| 3 | GPT-5 Mini | 55.76 |
| 4 | O4 Mini | 55.11 |
| 5 | GPT-OSS-120B | 54.08 |
| 6 | Grok 3 Mini | 48.48 |
| 7 | Qwen 3 235B A22B (Thinking) | 46.93 |
| 8 | DeepSeek R1 0528 | 45.87 |
| 9 | DeepSeek V3.1 | 44.61 |
| 10 | Gemini 2.5 Pro | 43.8 |
| 11 | Qwen 3 Next 80B A3B (Thinking) | 41.97 |
| 12 | Seed-OSS-36B-Instruct | 41.01 |
| 13 | Claude Sonnet 4 (Thinking) | 34.67 |
| 14 | Qwen 3 32B | 25.38 |
| 15 | Gemini 2.5 Flash | 25.11 |
Interactive version: aibenchmarks.dev/benchmark?slug=hardcorelogic-increased-complexity · How the rankings work · Data refreshed daily, snapshot 2026-07-17.