Benchmark Radar™
Star —

EvoCode-Bench

Explore score history ↗

EvoCode-Bench evaluates coding agents in multi-turn iterative interactions, with 26 stateful coding tasks and 227 evaluated rounds. Each task preserves the agent's workspace for 5-15 rounds, specifies requirements via observable behavior, and uses cumulative executable tests to verify new and prior requirements. Scoring uses MT@4, a four-attempt fail-stop multi-round score, and SR, a single-round score from a reference-completed prior state.

Released
2026-05-22
Institutions
Peking University · Tsinghua University · University of Hong Kong
Evaluates
General AI, Language & Knowledge, cs.AI
Openness
unknown
Importer
Claire Radar
Review status
unreviewed

EvoCode-Bench paper

No reported scores are on record for this benchmark yet.

Which sources cite EvoCode-Bench?

Related General AI, Language & Knowledge, cs.AI benchmarks