Skip to content

Benchmark

ARC-C

Scores are percentages.

Models measured
25
Scores recorded
25
Sources
1
IQ weight
0.86

Score distribution

80.8%
Mean
83.7%
Median
14%
Std dev
67.3%
10th percentile
96.4%
90th percentile
40.6%
Min
40.6%97.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.86 for chat models, measured over 25 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1MiMo V2.5 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim97.2%
2Llama 3.1 405B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim96.9%
3Claude 3 Opus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim96.4%
4Llama 3.1 70B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim94.8%
5Nova Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim94.8%
6Claude 3 Sonnet· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim93.2%
7Jamba 1.5 Large· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim93%
8Nova Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim92.4%
9phi-3.5-moe-instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91%
10Nova Micro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90.2%
11Claude 3 Haiku· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89.2%
12Jamba 1.5 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85.7%
13Phi 4 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim83.7%
14Llama 3.1 8B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim83.4%
15Llama 3.2 3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.6%
16Gemma 2 27B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim71.4%
17Command R Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim71%
18Qwen 2.5 Coder 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.5%
19Qwen2.5 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.4%
20Llama 3.1 Nemotron 70B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim69.2%
21Qwen2 72B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim68.9%
22Gemma 2 9B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim68.4%
23Qwen 2.5 14B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim67.3%
24Qwen2.5 Coder 7B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60.9%
25ERNIE 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim40.6%

Data credits: Data by LLM Stats