SciCode++ is here, with ~6,000 tasks that test how well frontier models solve scientific problems through code.

SciCode introduced executable scientific coding problems. SciCode-Verified showed how often flawed specifications and tests can distort the results. SciCode++ turns those lessons into a production process: domain experts write the tasks, independent reviewers check them, executable tests validate every subproblem, and model runs calibrate difficulty. That helps separate model capability gaps from eval issues.

Early results post-training Qwen 3.5 9B on 4,000 of the 6,000 tasks: +10.3% on SciCode and +9.1% on SciCode-Verified relative to baseline.

turing.com/blog/scicode-p…