Benchmark

OneMillion Bench

OneMillion Bench evaluates AI agents on high-economic-value tasks that require sustained, reliable execution across long-horizon real-world workflows.

Modality
text
Categories
long_context, reasoning, agents
Openness
unknown
Source
llm_stats
Reported scores
3

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Qwen3.8 MaxQwen0.5252026-08-02evidence
Seed 2.1 ProByteDance0.6882026-06-24evidence
Seed 2.1 TurboByteDance0.6662026-06-24evidence

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.