HardcoreLogic - Total — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 20 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 69.1 |
| 2 | Grok 4 | 59.55 |
| 3 | GPT-5 Mini | 54.49 |
| 4 | GPT-OSS-120B | 51.97 |
| 5 | O4 Mini | 50.13 |
| 6 | Qwen 3 235B A22B (Thinking) | 43.33 |
| 7 | Grok 3 Mini | 42.56 |
| 8 | DeepSeek V3.1 | 41.43 |
| 9 | DeepSeek R1 0528 | 41.37 |
| 10 | Gemini 2.5 Pro | 40.58 |
| 11 | Seed-OSS-36B-Instruct | 38.96 |
| 12 | Qwen 3 30B A3B 2507 (Thinking) | 37.33 |
| 13 | Qwen 3 Next 80B A3B (Thinking) | 36.35 |
| 14 | Claude Sonnet 4 (Thinking) | 30.51 |
| 15 | GLM-4.5 | 21.67 |
Interactive version: aibenchmarks.dev/benchmark?slug=hardcorelogic-total · How the rankings work · Data refreshed daily, snapshot 2026-07-17.