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
1Claude Fable 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.2%
2Claude Fable 5.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim65%
3Claude Opus 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim64.7%
4Claude Fable 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim64.5%
5Claude Opus 5.5Opus 5.5 System Card capability section · no tools · 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.64.4%
6GLM 5.3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim62.5%
7Muse Spark 1.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim62.1%
8Claude Fable 5.1no tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.60.9%
9Claude Fable 5.1Opus 5.5 System Card capability section · no tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.60.9%
10Claude Fable 5.1System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted · no tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.60.9%
11DeepSeek V4 Pro 0813· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60%
12Muse Spark· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim58.4%
13Claude Opus 4.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57.9%
14Claude Fable 5no tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.57.8%
15Claude Fable 5System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted · no tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.57.8%
16Claude Sonnet 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57.4%
17GPT-5.5 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57.2%
18Claude Sonnet 5.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · no tools · 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.56.9%
19Claude Opus 5no tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.56.6%
20Claude Opus 5Opus 5.5 System Card capability section · no tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.56.6%
21Claude Opus 5System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted · no tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.56.6%
22Claude Fable 5Opus 5 System Card capability summary · adaptive thinking · max effort unless noted · no tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.56.5%
23Claude Opus 5DeepSeek V4.1 launch chart · exact public value · setting not further specified · full set· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.56.3%
24Claude Opus 5Opus 5 System Card capability summary · adaptive thinking · max effort unless noted · no tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.56.3%
25Kimi K3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim56%
26Doubao Seed 2.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55.7%
27GLM 5.3 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55.3%
28Claude Opus 4.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54.7%
29GLM 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54.7%
30Doubao Seed 2.1 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54.6%
31Claude Fable 5Qwen表:无工具· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.53.3%
32Claude Opus 4.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim53.1%
33GLM 5.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim52.3%
34GPT 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim52.2%
35Muse Spark 1.1Meta Model API · xhigh · 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.52.2%
36Gemini 3.1 Pro Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim51.4%
37Kimi K3.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim51.1%
38Kimi K2 Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
51%
39Kimi K2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
50.2%
40Fugu UltraFugu official headline evaluation · text-only· Reported by Sakana AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.50%
41Claude Opus 4.8Fable/Mythos 5 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted · no tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.49.8%
42Claude Opus 4.8max · 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.49.8%
43Claude Opus 4.8Opus 4.8 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted · no tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.49.8%
44Claude Opus 4.8Opus 5 System Card capability summary · adaptive thinking · max effort unless noted · no tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.49.8%
45Claude Sonnet 4.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim49%
46Qwen3.5 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
48.5%
47Qwen3.5 122B-A10B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
47.5%
48Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
47.4%
49GPT-5.6 SolQwen表:无工具· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.47.2%
50Claude Opus 4.7Gemini 3.5 Flash Model Card · May 2026 · full text + multimodal set· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.46.9%

Showing 1–50 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)