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
MRCR v2 (8-needle)
MRCR v2 (8-needle) is a variant of the Multi-Round Coreference Resolution benchmark that includes 8 needle items to retrieve from long contexts. This tests models' ability to simultaneously track and reason about multiple pieces of information across extended conversations.
Evaluation context and evidence
- Source
- LLM Stats
- Publisher
- Not recorded
- Benchmark release
- Not recorded
- Collected
- 2026-08-17
- Modality
- text
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.
Original sources
Reported results 23
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| Gemini 3.7 Flash | 0.97 | Not recorded | Not recorded | 2026-08-13 · model_announcement | LLM Stats |
| Qwen3.8 Max | 0.929 | Not recorded | Not recorded | 2026-08-02 · model_announcement | LLM Stats |
| GPT-5.6 Sol | 0.915 | Not recorded | Not recorded | 2026-07-09 · model_announcement | LLM Stats |
| GPT-5.6 Terra | 0.896 | Not recorded | Not recorded | 2026-07-09 · model_announcement | LLM Stats |
| Claude Opus 4.6 | 0.76 | Not recorded | Not recorded | 2026-02-05 · model_announcement | LLM Stats |
| GPT-5.5 | 0.74 | Not recorded | Not recorded | 2026-04-23 · model_announcement | LLM Stats |
| Gemma 4 31B | 0.664 | Not recorded | Not recorded | 2026-04-02 · model_announcement | LLM Stats |
| Gemini 3.1 Flash-Lite | 0.601 | Not recorded | Not recorded | 2026-03-03 · model_announcement | LLM Stats |
| Gemini 3.6 Flash | 0.54 | Not recorded | Not recorded | 2026-07-21 · model_announcement | LLM Stats |
| Gemma 4 26B-A4B | 0.441 | Not recorded | Not recorded | 2026-04-02 · model_announcement | LLM Stats |
| Gemma 4 12B | 0.434 | Not recorded | Not recorded | 2026-05-23 · model_announcement | LLM Stats |
| GPT-5.6 Luna | 0.413 | Not recorded | Not recorded | 2026-07-09 · model_announcement | LLM Stats |
| GPT-5.4 mini | 0.336 | Not recorded | Not recorded | 2026-03-17 · model_announcement | LLM Stats |
| GPT-5.4 nano | 0.331 | Not recorded | Not recorded | 2026-03-17 · model_announcement | LLM Stats |
| Gemini 3.5 Flash | 0.266 | Not recorded | Not recorded | 2026-05-19 · model_announcement | LLM Stats |
| Gemini 3.1 Pro | 0.263 | Not recorded | Not recorded | 2026-02-19 · model_announcement | LLM Stats |
| Gemini 3 Pro | 0.263 | Not recorded | Not recorded | 2025-11-18 · model_announcement | LLM Stats |
| Gemma 4 E4B | 0.254 | Not recorded | Not recorded | 2026-04-02 · model_announcement | LLM Stats |
| Gemini 3 Flash | 0.221 | Not recorded | Not recorded | 2025-12-17 · model_announcement | LLM Stats |
| Gemini 3.5 Flash-Lite | 0.213 | Not recorded | Not recorded | 2026-07-21 · model_announcement | LLM Stats |
| Gemma 4 E2B | 0.191 | Not recorded | Not recorded | 2026-04-02 · model_announcement | LLM Stats |
| Gemini 2.5 Pro Preview 06-05 | 0.164 | Not recorded | Not recorded | 2025-06-05 · model_announcement | LLM Stats |
| Gemma 3 27B | 0.135 | Not recorded | Not recorded | 2025-03-12 · model_announcement | LLM Stats |