# MRCRv2

> A long-context benchmark for memory, retrieval, and multi-round coherence over large contexts.

Canonical page: https://benchlm.ai/benchmarks/mrcrv2

- Category: [Reasoning](/reasoning)
- Last updated: September 18, 2026

## About MRCRv2

- Year: 2025
- Tasks: Long-context retrieval
- Format: Multi-round long-context evaluation
- Difficulty: Hard long-context
- Paper: [Introducing GPT-5.2 and GPT-5.2 Pro](https://openai.com/index/introducing-gpt-5-2/)

MRCRv2 is especially useful for models that compete on long context, since it checks whether they can retrieve the right information across long, multi-round interactions.

MRCRv2 is currently weighted in BenchLM's scoring formula. The Reasoning category carries 17% of the overall score, and MRCRv2 contributes 20% of that category score.

## Leaderboard (9 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Sakana Fugu-Ultra](/models/sakana-fugu-ultra) | Sakana AI | 93.6% |
| 2 | [Qwen3.8 Max](/models/qwen3-8-max) | Alibaba | 92.9% |
| 3 | [Qwen3.7 Plus](/models/qwen3-7-plus) | Alibaba | 91.7% |
| 4 | [Qwen3.7 Max](/models/qwen3-7-max) | Alibaba | 90.4% |
| 5 | [Sakana Fugu](/models/sakana-fugu) | Sakana AI | 86.6% |
| 6 | [Gemini 3.5 Flash](/models/gemini-3-5-flash) | Google | 77.3% |
| 7 | [Gemini 3.5 Flash-Lite](/models/gemini-3-5-flash-lite) | Google | 72.2% |
| 8 | [Pokee-Isaac 28B](/models/pokee-isaac-28b) | Pokee AI | 60.7% |
| 9 | [Gemma 4 12B](/models/gemma-4-12b) | Google | 43.4% |

## FAQ

### What does MRCRv2 measure?

A long-context benchmark for memory, retrieval, and multi-round coherence over large contexts.

### Which model scores highest on MRCRv2?

Sakana Fugu-Ultra by Sakana AI currently leads with a score of 93.6% on MRCRv2.

### How many models are evaluated on MRCRv2?

9 AI models have been evaluated on MRCRv2 on BenchLM.

### Does MRCRv2 affect BenchLM's overall score?

Yes. MRCRv2 is a weighted benchmark inside the Reasoning category, which carries 17% of BenchLM's overall score. MRCRv2 itself contributes 20% of that category score.

## Compare Top Models on MRCRv2

- [Sakana Fugu-Ultra vs Qwen3.8 Max](/compare/qwen3-8-max-vs-sakana-fugu-ultra)
- [Qwen3.8 Max vs Qwen3.7 Plus](/compare/qwen3-7-plus-vs-qwen3-8-max)
- [Qwen3.7 Plus vs Qwen3.7 Max](/compare/qwen3-7-max-vs-qwen3-7-plus)
- [Qwen3.7 Max vs Sakana Fugu](/compare/qwen3-7-max-vs-sakana-fugu)