Skip to content

Benchmark

C-Eval

Scores are percentages. Higher is better.

Models and systems measured
24
Scores recorded
27
Sources
2
IQ weight
1.93

Score distribution

85.7%
Mean
90.2%
Median
12.4%
Std dev
77.2%
10th percentile
93%
90th percentile
40.7%
Min
40.7%93.7%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.93 for chat models, measured over 21 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#Model or systemScore
1Qwen3 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim93.7%
2Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim93.3%
3Qwen3.6 PlusQwen official release table · thinking mode unless benchmark requires otherwise· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.93.3%
4Qwen3.5 397B A17B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim93%
5Qwen3.5 397B A17BQwen3.5 release/model card · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.93%
6Qwen3.5 Omni PlusQwen3.5-Omni release · no-thinking setting· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.92%
7Qwen3.5 122B-A10B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91.9%
8MiMo V2.5 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91.5%
9Qwen3.6 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91.4%
10Qwen3.6 27BQwen official release table · thinking mode unless benchmark requires otherwise· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.91.4%
11Qwen3.5 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90.5%
12Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90.2%
13Qwen3.6 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90%
14Qwen3.6 FlashQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.90%
15Qwen3.5 9B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim88.2%
16DeepSeek V3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86.5%
17Qwen3 14B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86.2%
18Qwen3.5 Omni FlashQwen3.5-Omni release · no-thinking setting· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.86%
19Qwen3.5 4B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85.1%
20Qwen2 72B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim83.8%
21Qwen2 7B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.2%
22Qwen3.5 2B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.2%
23Qwen3.5 0.8B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim50.5%
24ERNIE 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim40.7%

Not ranked

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
DeepSeek V4.1 Flash BaseEM · 5-shot· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.92.1%
MiMo V2 Flash Baseofficial Base table · 5-shot· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.87.9%
Qwen3.5-397B-A17B-BaseQwen3.5 release/model card · base-model table· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.91.8%

Data credits: Data by LLM Stats · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.