Benchmark
SciCode
Scientific code generation graded by test execution; subproblem context matters.
- Released
- 2024-07-18
- Categories
- science
- Openness
- unknown
- Source
- model_reports
- Reported scores
- 2
Reported scores
model_reports
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Gemini 3.1 Pro | 59.0 | 2026-02-19 | evidence | |
| Kimi K3 | Moonshot AI | 58.7 | 2026-06-13 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.