Interactive Terminal Task on Terminal-Bench 2.0 (full)
31.9Pass@1GPT-5 mini (2025-08-07)
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-5 mini (2025-08-07)Peak Len.=400k, Evaluation Mode=Single (×1)2026.07 | 31.9 | |
| Qwen3.5-35B-A3BPeak Len.=64k, Evaluation Mode=Compacted (×4)2026.07 | 27 | |
| GLM-4.5-Air (106B-A30B) + CompactionRLPeak Len.=80k, Evaluation Mode=Compacted (×4), Scaffold=Terminus-KIRA2026.07 | 24.5 | |
| Qwen3-Coder-480B-A35B-InstructPeak Len.=256k, Evaluation Mode=Single (×1)2026.07 | 23.9 | |
| GLM-4.5-Air (106B-A30B) + RL (w/o compaction)Peak Len.=80k, Evaluation Mode=Compacted (×4), Scaffold=Terminus-KIRA2026.07 | 23.6 | |
| GLM-4.5-Air (106B-A30B)Peak Len.=80k, Evaluation Mode=Compacted (×4), Scaffold=Terminus-KIRA2026.07 | 21.4 | |
| GLM-4.5-Air (106B-A30B) + CompactionRLPeak Len.=80k, Evaluation Mode=Single (×1), Scaffold=Terminus-KIRA2026.07 | 21.4 | |
| GLM-4.7-Flash (30B-A3B) + CompactionRLPeak Len.=64k, Evaluation Mode=Compacted (×4), Scaffold=Terminus-KIRA2026.07 | 20.2 | |
| GLM-4.5-Air (106B-A30B) + RL (w/o compaction)Peak Len.=80k, Evaluation Mode=Single (×1), Scaffold=Terminus-KIRA2026.07 | 20.2 | |
| gpt-oss-120bPeak Len.=128k, Evaluation Mode=Single (×1)2026.07 | 18.7 | |
| GLM-4.5-Air (106B-A30B)Peak Len.=80k, Evaluation Mode=Single (×1), Scaffold=Terminus-KIRA2026.07 | 17.9 | |
| GLM-4.7-Flash (30B-A3B) + RL (w/o compaction)Peak Len.=64k, Evaluation Mode=Single (×1), Scaffold=Terminus-KIRA2026.07 | 16.9 | |
| GLM-4.7-Flash (30B-A3B) + CompactionRLPeak Len.=64k, Evaluation Mode=Single (×1), Scaffold=Terminus-KIRA2026.07 | 16.9 | |
| Qwen3-Coder-30B-A3B-InstructPeak Len.=256k, Evaluation Mode=Single (×1)2026.07 | 14.6 | |
| GLM-4.7-Flash (30B-A3B)Peak Len.=64k, Evaluation Mode=Single (×1), Scaffold=Terminus-KIRA2026.07 | 14.6 | |
| Qwen3-235B-A22B-Instruct-2507Peak Len.=256k, Evaluation Mode=Single (×1)2026.07 | 13.5 | |
| GLM-4.7-Flash (30B-A3B)Peak Len.=64k, Evaluation Mode=Compacted (×4), Scaffold=Terminus-KIRA2026.07 | 13.4 | |
| GLM-4.7-Flash (30B-A3B) + RL (w/o compaction)Peak Len.=64k, Evaluation Mode=Compacted (×4), Scaffold=Terminus-KIRA2026.07 | 12.4 | |
| Qwen3-30B-A3B-Instruct-2507Peak Len.=256k, Evaluation Mode=Single (×1)2026.07 | 5.34 |