Scicode S
AI benchmark · Coding
Full listing name: Scicode (HAL)
What is Scicode?
HAL's cost-aware agent leaderboard for Scicode scientific programming tasks.
Tier S
The standard: frontier labs report it, or a trusted evaluator scores hundreds of models on it.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- 474 models scored
- in curated RL directories (2 pts)
On X · mixed, moderate buzz, from 12 posts about Scicode in the last month
SciCode still appears in model comparisons and Artificial Analysis results, but audits found flawed specs and tests, prompting SciCode-Verified and doubts about score stagnation.
How we got to tier S
- Adoption: 474 models scored. Tier S.
- On X: mixed, moderate buzz. “SciCode still appears in model comparisons and Artificial Analysis results, but audits found flawed specs and tests, prompting SciCode-Verified and doubts about score stagnation.” No move.
- In curated RL directories: 2 points, a floor of C.
- Not yet confirmed by a line from its own site or paper.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Not on the map yet: no line from its own site or paper places it in a domain.
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-10-11 snapshot.