This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| """Reproduce Claude Opus 4.6 on BioMysteryBench-full (99 problems). | |
| βββ SCORES βββ | |
| avg pass@1 over 3 independent runs: | |
| Overall 54.21% | |
| Human-solvable 64.91% | |
| Human-difficult 18.84% | |
| Setting: Anthropic native /v1/messages + extended thinking (budget=4096) + | |
| bash + persistent IPython kernel, max_turns=128, concurrency=4. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/bin/bash | |
| # Referenced from https://gist.github.com/ZhaofengWu/f345652e994e3b68c309352a7610460f. Nice scripts. | |
| # New feature: Add plugins zsh-autosuggestions and zsh-syntax-highlighting | |
| # 1. Set up your $HOME variable | |
| # 2. If you set a new HOME, it's likely required to install ncurces. (Even the following code might skip installing!) | |
| # 3. Read & Run the last few lines line-by-line | |
| # HOME=... |