Skip to content

Benchmark

NOVA-63

Scores are percentages. Higher is better.

Models measured
12
Scores recorded
16
Sources
2
IQ weight
1.90

Score distribution

56%
Mean
58.1%
Median
4.7%
Std dev
54.2%
10th percentile
59.1%
90th percentile
42.4%
Min
42.4%59.1%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.90 for chat models, measured over 12 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Qwen3.5 397B A17B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim59.1%
2Qwen3.5 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.59.1%
3Qwen3.7 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim59%
4Qwen3.7 MaxQwen3.7-Max release · recommended reasoning-effort=xhigh system prompt· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.59%
5Qwen3.7 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim58.8%
6Qwen3.7 PlusQwen3.7-Plus release · recommended reasoning-effort=xhigh system prompt· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.58.8%
7Qwen3.5 122B-A10B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim58.6%
8Qwen3.5 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim58.1%
9Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57.9%
10Qwen3.6 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.57.9%
11Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57.1%
12Qwen3.5 9B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55.9%
13Qwen3.5 4B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54.3%
14Qwen3 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54.2%
15Qwen3.5 2B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim46.4%
16Qwen3.5 0.8B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim42.4%

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.