Benchmark
GDM-MRCRv2: 8 needle 512k
Long context benchmarks measure how well models use information in long inputs. Scores are percentages.
- Models measured
- 40
- Scores recorded
- 107
- Sources
- 1
- IQ weight
- 1.96
Score distribution
- 31.4%
- Mean
- 29.7%
- Median
- 15.4%
- Std dev
- 13.2%
- 10th percentile
- 52.5%
- 90th percentile
- 7.3%
- Min
This benchmark has a weight of 1.96 for chat models, measured over 40 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 101 | Claude Opus 4.7high· Context Arena data | 9.1% |
| 102 | Claude Opus 4.7· Context Arena data | 9.1% |
| 103 | MiMo V2 Pro· Context Arena data | 9% |
| 104 | Claude Opus 4.7medium· Context Arena data | 8.8% |
| 105 | Claude Opus 4.7xhigh· Context Arena data | 8.6% |
| 106 | Claude Opus 4.7low· Context Arena data | 7.5% |
| 107 | Grok 4.3· Context Arena data | 7.3% |
Showing 101–107 of 107 results.