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
1Claude Fable 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim74.2%
2Kimi K3.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70%
3Claude Opus 5.5Opus 5.5 System Card capability section · web search/fetch + programmatic tools + code · auto thinking · 1M total-token cap· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.67.7%
4Claude Fable 5.1Opus 5.5 System Card capability section · with tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.65.6%
5Claude Fable 5.1System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted · with tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.65%
6Claude Fable 5.1with tools· Reported by OpenAI, Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.65%
7Claude Opus 5Opus 5 System Card capability summary · adaptive thinking · max effort unless noted · with tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.64.7%
8Claude Fable 5Qwen表:with tools· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.64.5%
9Claude Sonnet 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim64.5%
10Claude Sonnet 5.5web search/fetch + programmatic tools + code · auto thinking · 980K task budget· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.64.5%
11GPT-5.6 SolZ.ai设置· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.64.5%
12Claude Fable 5Opus 5 System Card capability summary · adaptive thinking · max effort unless noted · with tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.63.9%
13DeepSeek V4.1 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim63.9%
14DeepSeek V4.1 FlashDeepSeek V4.1 launch chart · exact public value · setting not further specified· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.63.9%
15DeepSeek V4.1 FlashPass@1 / tools· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.63.9%
16Claude Fable 5System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted · with tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.63.8%
17Claude Fable 5with tools· Reported by OpenAI, Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.63.8%
18Claude Opus 5DeepSeek V4.1 launch chart · exact public value · setting not further specified· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.63.6%
19Claude Opus 5Opus 5.5 System Card capability section · with tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.63.6%
20Claude Opus 5System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted · with tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.63.6%
21Claude Opus 5with tools· Reported by OpenAI, Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.63.6%
22GLM 5.3DeepSeek V4.1 launch chart · exact public value · setting not further specified· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.62.5%
23GLM 5.3Z.ai设置· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.62.5%
24Muse Spark 1.1Meta Model API · xhigh · 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.62.1%
25Muse Spark Open· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim61%
26DeepSeek V4 Pro 0813DeepSeek V4.1 launch chart · exact public value · setting not further specified· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.60%
27DeepSeek V4 Pro 0813with tools · pass@1· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.60%
28DeepSeek V4 Pro 0813Z.ai设置· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.60%
29Kimi K3DeepSeek V4.1 launch chart · exact public value · setting not further specified· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.59.8%
30Kimi K3Z.ai设置· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.59.8%
31GPT-5.4 Prowith tools· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.58.7%
32GPT-5.6 SolQwen表:with tools· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.58%
33Claude Opus 4.8Fable/Mythos 5 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted · with tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.57.9%
34Claude Opus 4.8max · 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.57.9%
35Claude Opus 4.8Opus 4.8 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted · with tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.57.9%
36Claude Opus 4.8Opus 5 System Card capability summary · adaptive thinking · max effort unless noted · with tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.57.9%
37Claude Opus 4.8Qwen表:with tools· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.57.9%
38Claude Opus 4.8Z.ai设置· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.57.9%
39Claude Haiku 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57.4%
40Claude Haiku 5.5web search/fetch + programmatic tools + code · auto thinking · 980K task budget· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.57.4%
41Claude Sonnet 5search/fetch/code · max effort · 1M total tokens· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.57.4%
42GPT-5.5 Prowith tools · xhigh· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.57.2%
43GPT-6 AstraOpus 5.5 System Card capability section · with tools · provider-reported· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.57.2%
44GPT-6 Astrawith tools· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.57.2%
45Ling 3.0 Flash SanteLing-3.0-flash-Sante official evaluation image · highest reasoning tier · temperature 1.0 / top_p 0.95 unless otherwise stated · exact API snapshot and run count not published · with tools · 256K · no context-management strategy· Reported by Ant inclusionAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.57.1%
46Qwen3.8 MaxQwen表:with tools· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.56.2%
47Qwen3.8 MaxZ.ai设置· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.56.2%
48Kimi K3full set · tools · max effort · temp 1.0· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.56%
49Kimi K2.6Kimi K2.6 official benchmark table · thinking · temp 1.0 · top_p 1.0 · 262,144 context · text-only subset · with tools · footnote result· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.55.5%
50Hy4 previewtext-only subset · with tools· Reported by Tencent Hy· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.55.4%

Showing 1–50 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.