Agentic Reasoning on Terminal Bench hard
26.8Success RateQwen3.5-122B-A10B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3.5-122B-A10B2026.04 | 26.8 | |
| Nemotron 3 Super2026.04 | 25.78 | |
| GPT-OSS-120B2026.04 | 24 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| Qwen3.5-122B-A10B2026.04 | 26.8 | |
| Nemotron 3 Super2026.04 | 25.78 | |
| GPT-OSS-120B2026.04 | 24 |