AI EVALUATION, IN CONTEXT.BY EQUALITY MACHINE

LLM Stats

SciCode

SciCode is a research coding benchmark curated by scientists that challenges language models to code solutions for scientific problems. It contains 338 subproblems decomposed from 80 challenging main problems across 16 natural science sub-fields including mathematics, physics, chemistry, biology, and materials science. Problems require knowledge recall, reasoning, and code synthesis skills.

评测信息与证据

来源
LLM Stats
发布者
未收录
评测发布日期
2024-07-18
采集日期
2026-08-17
模态
text

本站保留来源报告的结果,不代表独立复测。请先核对任务版本、评测协议、分数单位和报告日期;不同运行条件不能直接合并为统一排名。

原始资料

报告成绩 21

按来源中的观察顺序展示,顺序不代表排名。日期保留原始精度。

模型数值单位协议报告日期与口径来源
Seed 2.1 Pro0.598未收录未收录2026-06-24 · model_announcementLLM Stats
Gemini 3.1 Pro0.59未收录未收录2026-02-19 · model_announcementLLM Stats
Seed 2.1 Turbo0.578未收录未收录2026-06-24 · model_announcementLLM Stats
Qwen3.7 Max0.535未收录未收录2026-05-19 · model_announcementLLM Stats
Kimi K2.60.522未收录未收录2026-04-20 · model_announcementLLM Stats
Qwen3.7-Plus0.513未收录未收录2026-05-31 · model_announcementLLM Stats
Inkling-Small0.487未收录未收录2026-07-30 · model_announcementLLM Stats
Kimi K2.50.487未收录未收录2026-01-27 · model_announcementLLM Stats
Kimi K2-Thinking-09050.448未收录未收录2025-09-05 · model_announcementLLM Stats
Nemotron 3 Ultra (550B A55B)0.446未收录未收录2026-06-04 · model_announcementLLM Stats
Muse Glimmer-30B0.436未收录未收录2026-08-10 · model_announcementLLM Stats
Nemotron 3 Super (120B A12B)0.4205未收录未收录2026-03-11 · model_announcementLLM Stats
GLM-4.50.417未收录未收录2025-07-28 · model_announcementLLM Stats
MiniMax M2.10.39未收录未收录2025-12-23 · model_announcementLLM Stats
North Mini Code 1.00.382未收录未收录2026-06-09 · model_announcementLLM Stats
Command A+0.38未收录未收录2026-05-20 · model_announcementLLM Stats
Mercury 20.38未收录未收录2026-02-24 · model_announcementLLM Stats
GLM-4.5-Air0.373未收录未收录2025-07-28 · model_announcementLLM Stats
MiniMax M20.36未收录未收录2025-10-27 · model_announcementLLM Stats
Nemotron 3 Nano (30B A3B)0.333未收录未收录2025-12-15 · model_announcementLLM Stats
Nemotron 3.5 Lightning (30B A3B)0.326未收录未收录2026-08-11 · model_announcementLLM Stats