Skip to content

Benchmark

Humanity's Last Exam

Scores are percentages. Higher is better.

Models and systems measured
120
Scores recorded
230
Sources
3
IQ weight
1.67

Score distribution

34%
Mean
34.8%
Median
15.5%
Std dev
12.5%
10th percentile
55.7%
90th percentile
3.7%
Min
3.7%73.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.67 for chat models, measured over 113 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
201o4 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim14.7%
202OpenAI o3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim14.7%
203GLM 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim14.4%
204GLM 4.7 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
14.4%
205Qwen3 VL 235Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.13.6%
206MiniMax M2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.
Values from 2 sources
12.5%
207Nemotron 3.5 Lightning 30B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim11.7%
208Nemotron 3.5 Lightning 30B A3Btext-only · no tools· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.11.7%
209Sarvam 105B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim11.2%
210Gemini 2.5 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim11%
211GPT OSS 20b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
10.9%
212GPT OSS 20bofficial model card Table 3 · reasoning high · no tools · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.10.9%
213GLM 4.5 Air· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim10.6%
214Magistral Medium· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim9%
215Gemma 4 26B A4BGemma 4 official model card · no tools· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.8.7%
216GPT-5 nano· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim8.7%
217GPT OSS 120Bofficial model card Table 3 · reasoning medium · no tools · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.8.6%
218MiniMax M1 80K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.8.4%
219DeepSeek V4 FlashDeepSeek V4 official model card · Non-Think· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.8.1%
220MiniMax M1 40K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.7.2%
221GPT OSS 20bofficial model card Table 3 · reasoning medium · no tools · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.7%
222GPT 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim5.4%
223GPT 4o· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim5.3%
224Gemma 4 12B It· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim5.2%
225GPT OSS 120Bofficial model card Table 3 · reasoning low · no tools · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.5.2%
226Gemini 2.5 Flash-Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim5.1%
227Kimi K2 Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim4.7%
228GPT OSS 20bofficial model card Table 3 · reasoning low · no tools · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.4.2%
229GPT-4.1 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim3.7%

Showing 201–229 of 229 results.

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
Muse Spark (version unspecified)Meta Model API · highest effort · version unspecified · no tools · full 2,500 questions · o3-mini judge· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.42.8%

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. · OpenEvals/leaderboard-data, MIT (licence)