Skip to content

Benchmark

Humanity's Last Exam (with tools, text-only)

Scores are percentages.

Models measured
11
Scores recorded
11
Sources
1
IQ weight
1.21

Score distribution

54.2%
Mean
55.4%
Median
7.5%
Std dev
46%
10th percentile
63.1%
90th percentile
40.9%
Min
40.9%67.7%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.21 for chat models, measured over 11 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Claude Opus 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim67.7%
2LongCat 2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim63.1%
3DeepSeek V4 Pro 0813· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60%
4GPT-6 Astra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57.2%
5Qwen3.8 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim56.2%
6Hy4 preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55.4%
7Hy3 (Deep Infra)· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim53.2%
8Qwen3 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim49.8%
9Step 3.7 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim47.2%
10Inkling FP4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim46%
11Doubao Seed 1.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim40.9%

Data credits: Data by LLM Stats