Benchmark Almanac

Southeast University

We track 2 benchmarks that Southeast University made or helped make.

0 in use 2 with public code 2 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
KRIS-Bench Image editing models follow 1,267 instructions that need factual, conceptual or procedural knowledge across 22 tasks. A GPT-4o judge scores the edits. Image generation and editing May 2025 66.2 System cards only
STAGE Cross-Scene Narrative Evolution Reasoning Models answer questions that require evidence from different scenes in a movie. A judge compares the answer with a reference. Reasoning over long documents May 2026 65.1% Not in cards