MRCRV2
Fresh
OpenAI MRCR (Multi-round co-reference resolution) is a long context dataset for benchmarking an LLM's ability to distinguish between multiple needles hidden in context.
- Type
- RL Env
- Publisher
- General Reasoning
- Runtime
ORS- License
- unknown
- Size
- 2400 tasks
- Published
- Jan 2026
Cite
Notes
Only stored in your browser.
Public scores on this env
312 vf-eval reports across 3 models
1Claude Opus 4.6Anthropicdisputed932GPT-5.4OpenAIdisputed863Gemini 3.1 ProGoogle (Alphabet Inc.)disputed26.3
Open the scoring view →