AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
LLM Stats
Multi-round Co-reference Resolution (MRCR) benchmark for evaluating an LLM's ability to distinguish between multiple needles hidden in long context. Models are given a long, multi-turn synthetic conversation and must retrieve a specific instance of a repeated request, requiring reasoning and disambiguation skills beyond simple retrieval.
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| GPT-5 | 0.952 | Not recorded | Not recorded | 2025-08-07 · model_announcement | LLM Stats |
| MiniMax M1 40K | 0.761 | Not recorded | Not recorded | 2025-06-16 · model_announcement | LLM Stats |
| MiniMax M1 80K | 0.734 | Not recorded | Not recorded | 2025-06-16 · model_announcement | LLM Stats |
| GPT-4.1 | 0.572 | Not recorded | Not recorded | 2025-04-14 · model_announcement | LLM Stats |
| GPT-4.1 mini | 0.472 | Not recorded | Not recorded | 2025-04-14 · model_announcement | LLM Stats |
| GPT-4.5 | 0.385 | Not recorded | Not recorded | 2025-02-27 · model_announcement | LLM Stats |
| GPT-4.1 nano | 0.366 | Not recorded | Not recorded | 2025-04-14 · model_announcement | LLM Stats |
| GPT-4o | 0.319 | Not recorded | Not recorded | 2024-08-06 · model_announcement | LLM Stats |
| o3-mini | 0.187 | Not recorded | Not recorded | 2025-01-30 · model_announcement | LLM Stats |