Horangi 4 - KoBBQ: leaderboard
Metric: Accuracy (%). Source: horangi.ai. 105 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Fable 5 (High) | 100 |
| 2 | Claude Opus 4.1 (20250805) | 99 |
| 3 | Gemini 3.1 Pro (Preview) (High) | 98 |
| 4 | Gemma 4 31B (IT) (Thinking) | 98 |
| 5 | GPT-5.4 Nano (xHigh) | 97 |
| 6 | Claude Sonnet 5 (High) | 97 |
| 7 | GPT-5 | 96 |
| 8 | GPT-5.5 (xHigh) | 96 |
| 9 | Gemini 3 Pro (Preview) (High) | 96 |
| 10 | GPT-5 Nano | 95 |
| 11 | GPT-5.4 Mini (xHigh) | 95 |
| 12 | Qwen 3.7 Max | 94.74 |
| 13 | Gemini 3 Flash (Preview) | 94 |
| 14 | GPT-OSS-120B (High) | 94 |
| 15 | Grok 4 Fast (Reasoning) | 94 |
Interactive version: theaggregate.ai/benchmark?slug=horangi-4-kobbq · How It Works · Data refreshed daily, snapshot 2026-09-19.