Benchmark
OpenAI-MRCR: 2 needle 128k Benchmark
What is OpenAI-MRCR: 2 needle 128k?
Multi-round Co-reference Resolution (MRCR) benchmark for evaluating an LLM's ability to distinguish between multiple needles hidden in long context. Models are…
- Modality
- text
- Evaluates
- long context, reasoning
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 9
Source provenance
OpenAI-MRCR: 2 needle 128k results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GPT-4.1 | OpenAI | 0.572 | 2025-04-14 | evidence |
| GPT-4.1 mini | OpenAI | 0.472 | 2025-04-14 | evidence |
| GPT-4.1 nano | OpenAI | 0.366 | 2025-04-14 | evidence |
| GPT-4.5 | OpenAI | 0.385 | 2025-02-27 | evidence |
| GPT-4o | OpenAI | 0.319 | 2024-08-06 | evidence |
| GPT-5 | OpenAI | 0.952 | 2025-08-07 | evidence |
| MiniMax M1 40K | MiniMax | 0.761 | 2025-06-16 | evidence |
| MiniMax M1 80K | MiniMax | 0.734 | 2025-06-16 | evidence |
| o3-mini | OpenAI | 0.187 | 2025-01-30 | 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.