Benchmark
OpenAI-MRCR: 2 needle 1M Benchmark
What is OpenAI-MRCR: 2 needle 1M?
Multi-Round Co-reference Resolution benchmark that tests an LLM's ability to distinguish between multiple similar needles hidden in long conversations. Models…
- Modality
- text
- Evaluates
- long context, reasoning
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 5
Source provenance
OpenAI-MRCR: 2 needle 1M results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GPT-4.1 | OpenAI | 0.463 | 2025-04-14 | evidence |
| GPT-4.1 mini | OpenAI | 0.333 | 2025-04-14 | evidence |
| GPT-4.1 nano | OpenAI | 0.12 | 2025-04-14 | evidence |
| MiniMax M1 40K | MiniMax | 0.586 | 2025-06-16 | evidence |
| MiniMax M1 80K | MiniMax | 0.562 | 2025-06-16 | 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.