Terminal-Bench 2.0 - Easy
Agents · 2026-06-04
The Easy split of Terminal-Bench 2.0. This child benchmark separates a source-reported subtask or subtrack from the parent aggregate so scores at different grains do not share one benchmark_slug.
Top models (higher is better)
| Model | Score |
|---|---|
| Haiku 4.5 | 100.0 |
| Opus 4.5 | 100.0 |
| Opus 4.6 | 100.0 |
| Opus 4.7 | 100.0 |
| Gemini 2.5 Pro | 100.0 |
| Gemini 3.1 Pro Preview | 100.0 |
| Gemini 3.5 Flash | 100.0 |
| Gemini 3 Flash Preview | 100.0 |
| GPT-5.3-Codex | 100.0 |
| GPT-5.4 | 100.0 |
| Grok 4.20 | 100.0 |
| Grok 4 Fast | 100.0 |
| Opus 4.8 | 91.7 |
| GPT-5.5 | 85.0 |
| Qwen3.7-Max | 83.3 |
| Sonnet 4.5 | 75.0 |
| Sonnet 4.6 | 75.0 |
| DeepSeek-V3.2 | 75.0 |
| DeepSeek-V4-Pro | 75.0 |
| Gemini 2.5 Flash Preview (09-2025) | 75.0 |
| Gemini 3 Pro Preview | 75.0 |
| Gemma 4 31B IT | 75.0 |
| GLM 4.6 | 75.0 |
| GLM-4.7 | 75.0 |
| GLM-5.1 | 75.0 |
| GLM-5 | 75.0 |
| GPT-5.1 | 75.0 |
| GPT-5.2 | 75.0 |
| GPT-5.4 Mini | 75.0 |
| GPT-5.4 Nano | 75.0 |
| GPT-5 | 75.0 |
| GPT-5 Mini | 75.0 |
| Grok 4 | 75.0 |
| Grok 4.1 Fast | 75.0 |
| Kimi K2.5 | 75.0 |
| Kimi K2.6 | 75.0 |
| Laguna M.1 | 75.0 |
| Laguna XS.2 | 75.0 |
| MiniMax M2.5 | 75.0 |
| MiniMax M2.7 | 75.0 |