Official benchmarks map / Long-Horizon-Terminal-Bench
moonshotai/Kimi-K3 is ranked first on the Long-Horizon-Terminal-Bench leaderboard with 6, 100.0% ahead of deepseek-ai/DeepSeek-V4-Pro. Read live from the Hugging Face API on November 6, 2026.
| # | Model | Organization | Score |
|---|---|---|---|
| 1 | moonshotai/Kimi-K3 | moonshotai | 6 |
| 2 | deepseek-ai/DeepSeek-V4-Pro | deepseek-ai | 3 |
| 3 | MiniMaxAI/MiniMax-M3 | MiniMaxAI | 3 |
| 4 | moonshotai/Kimi-K2.7-Code | moonshotai | 3 |
| 5 | zai-org/GLM-5.1 | zai-org | 2 |
| 6 | deepseek-ai/DeepSeek-V4-Flash | deepseek-ai | 2 |
| 7 | zai-org/GLM-5.2 | zai-org | 1 |
| 8 | tencent/Hy3 | tencent | 1 |
| 9 | moonshotai/Kimi-K2.6 | moonshotai | 0 |
Long-Horizon-Terminal-Bench is a dataset that Hugging Face marks as an official benchmark. Its leaderboard is built automatically from the .eval_results files that model repositories publish, so entries are mostly self-reported by model authors and evaluation settings differ between submissions. A verified tag appears only where Hugging Face marks an entry as verified.
Original board: huggingface.co/datasets/IntelligenceLab/Long-Horizon-Terminal-Bench
Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.