Skip to content

Benchmark

MRCR v2 (8-needle)

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

Models measured
26
Scores recorded
26
Sources
1
IQ weight
1.05

Score distribution

49.6%
Mean
44.1%
Median
27.3%
Std dev
21.3%
10th percentile
92.9%
90th percentile
13.5%
Min
13.5%98.5%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.05 for chat models, measured over 26 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Muse Spark 1.3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim98.5%
2Gemini 3.7 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim97%
3Qwen3.8 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim92.9%
4GPT-5.6 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91.5%
5GPT-5.6 Terra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89.6%
6Claude Opus 4.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim76%
7GPT 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim74%
8Gemma 4 31B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim66.4%
9Gemini 3.1 Flash Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60.1%
10Gemini 3.6 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54%
11Seed 2.0 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim51.4%
12Inkling 2 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim46.4%
13Gemma 4 26B A4B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim44.1%
14Gemma 4 12B It· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim43.4%
15GPT-5.6 Luna· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim41.3%
16GPT-5.4 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim33.6%
17GPT 5.4 Nano· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim33.1%
18Gemini 3.5 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim26.6%
19Gemini 3 Pro Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim26.3%
20Gemini 3.1 Pro Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim26.3%
21Gemma 4 E4B-it· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim25.4%
22Gemini 3 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim22.1%
23Gemini 3.5 Flash Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim21.3%
24Gemma 4 E2B-it· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim19.1%
25Gemini 2.5 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim16.4%
26Gemma 3 27B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim13.5%

Data credits: Data by LLM Stats