Benchmark
MRCR · ≤128K · 2/4/8-needle
Long context benchmarks measure how well models use information in long inputs. Scores are percentages. Higher is better.
- Models measured
- 1
- Scores recorded
- 1
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 45.7%
- Mean
- 45.7%
- Median
- 0%
- Std dev
- 45.7%
- 10th percentile
- 45.7%
- 90th percentile
- 45.7%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | MiMo V2 FlashMiMo-V2-Flash final evaluation · 2/4/8-needle · maximum 128K· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 45.7% |