Benchmark
OpenAI-MRCR: 2 needle 256k
Multi-Round Co-reference Resolution (MRCR) benchmark that tests long-context reasoning by evaluating a model's ability to distinguish between similar…
- Modality
- text
- Categories
- long_context, reasoning
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 1
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GPT-5 | OpenAI | 0.868 | 2025-08-07 | evidence |
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.