long context benchmark
OneMillion Bench
OneMillion Bench evaluates AI agents on high-economic-value tasks that require sustained, reliable execution across long-horizon real-world workflows.
Updated Aug 11, 2026
Models2
Model coverage2
MetricScore
EvidenceB
OneMillion Bench Ranking
Higher score ranks better on this benchmark.
| 01 | BY | 68.8% | 100.0% | 2 | C | |
| 02 | BY | 66.6% | 0.0% | 2 | C |
OneMillion Bench Score Distribution
A closer view of the leading scores on this benchmark.
OneMillion Bench Highlights
The leading models and scores on this benchmark.
What is OneMillion Bench?
What OneMillion Bench measures and how its scores work.
OneMillion Bench evaluates AI agents on high-economic-value tasks that require sustained, reliable execution across long-horizon real-world workflows.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- OneMillion Bench
- Modality
- text
- Primary category
- long context
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- onemillion-bench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about OneMillion Bench.
Which model scores highest on OneMillion Bench?
Seed 2.1 Pro is currently ranked first with 68.8%.
What does OneMillion Bench measure?
OneMillion Bench evaluates AI agents on high-economic-value tasks that require sustained, reliable execution across long-horizon real-world workflows.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.