Skip to content

Benchmark

Humanity's Last Exam (with tools)

Scores are percentages. Higher is better.

Models and systems measured
61
Scores recorded
113
Sources
2
IQ weight
1.73

Score distribution

51.4%
Mean
54%
Median
13.5%
Std dev
36.5%
10th percentile
63.9%
90th percentile
6.3%
Min
6.3%74.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.73 for chat models, measured over 14 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
101Claude Sonnet 5search/fetch/code · low effort · 1M total tokens· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.36.5%
102Claude Sonnet 4.5web search/fetch + code · no reasoning · decontaminated · Sonnet 4.5 grader· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.28.4%
103Gemma 4 31B ITGemma 4 Technical Report · Table 5 · thinking mode unless noted · with search· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.26.5%
104Nemotron 3 Super 120B A12BNeMo Evaluator / mostly NeMo Skills · with tools· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.22.8%
105Nemotron 3 Super 120B A12Bofficial blog Figure 3 · rounded · +tools· Reported by NVIDIA Developer· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.22.8%
106GPT OSS 120Bofficial model card Table 3 · reasoning high · with tools; Table 3 does not name the exact tool · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.19%
107GPT OSS 20bofficial model card Table 3 · reasoning high · with tools; Table 3 does not name the exact tool · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.17.3%
108Gemma 4 26B A4BGemma 4 Technical Report · Table 5 · thinking mode unless noted · with search· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.17.2%
109GPT OSS 120Bofficial model card Table 3 · reasoning medium · with tools; Table 3 does not name the exact tool · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.11.3%
110GPT OSS 120Bofficial model card Table 3 · reasoning low · with tools; Table 3 does not name the exact tool · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.9.1%
111GPT OSS 20bofficial model card Table 3 · reasoning medium · with tools; Table 3 does not name the exact tool · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.8.8%
112GPT OSS 20bofficial model card Table 3 · reasoning low · with tools; Table 3 does not name the exact tool · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.6.3%

Showing 101–112 of 112 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 · full 2,500 questions · bash + browser tools · o3-mini judge· Reported by Meta, Meta Superintelligence Labs· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.50.4%

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.