Horangi 4 - HRM8K: leaderboard
Metric: Accuracy (%). Source: horangi.ai. 105 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.1 | 97 |
| 2 | Qwen 3.7 Max | 97 |
| 3 | Claude Fable 5 (High) | 97 |
| 4 | Gemini 3.5 Flash | 96 |
| 5 | Gemini 3 Flash (Preview) | 96 |
| 6 | Grok 4.20 | 96 |
| 7 | Grok 4 Fast (Reasoning) | 96 |
| 8 | GPT-5.4 Mini (xHigh) | 96 |
| 9 | GPT-5.4 Nano (xHigh) | 96 |
| 10 | Claude Opus 4.6 (High) | 96 |
| 11 | Gemini 3 Pro (Preview) (High) | 96 |
| 12 | DeepSeek V3.2 (High) | 95.79 |
| 13 | Kimi K2.5 | 95 |
| 14 | GPT-5.4 (xHigh) | 95 |
| 15 | Gemini 3.1 Pro (Preview) (High) | 95 |
Interactive version: theaggregate.ai/benchmark?slug=horangi-4-hrm8k · How It Works · Data refreshed daily, snapshot 2026-09-19.