Skip to content

Benchmark

OpenAI-MRCR: 2 needle 128k

Long context benchmarks measure how well models use information in long inputs. Scores are percentages.

Models measured
9
Scores recorded
9
Sources
1
IQ weight
0.87

Score distribution

52.8%
Mean
47.2%
Median
23.3%
Std dev
31.9%
10th percentile
76.1%
90th percentile
18.7%
Min
18.7%95.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.87 for chat models, measured over 9 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1GPT 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim95.2%
2MiniMax M1 40K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.76.1%
3MiniMax M1 80K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.73.4%
4GPT 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57.2%
5GPT-4.1 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim47.2%
6GPT-4.5 Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim38.5%
7GPT-4.1 nano· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim36.6%
8GPT 4o· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim31.9%
9o3 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim18.7%

Data credits: Data by LLM Stats