Skip to content

Benchmark

Mystery Game Puzzles

Scores are percentages.

Models measured
85
Scores recorded
146
Sources
1
IQ weight
2.37

Score distribution

25.3%
Mean
19%
Median
19.7%
Std dev
7%
10th percentile
56%
90th percentile
0%
Min
0%95%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.37 for chat models, measured over 85 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
51Kimi K3max· Epoch AI Benchmarking Hub data26%
52Qwen3.7 Maxnone· Epoch AI Benchmarking Hub data26%
53Claude Opus 4.6max· Epoch AI Benchmarking Hub data25%
54Gemini 3 Flashminimal· Epoch AI Benchmarking Hub data25%
55Gemini 3.6 Flashminimal· Epoch AI Benchmarking Hub data25%
56Muse Spark 1.3max· Epoch AI Benchmarking Hub data25%
57Gemini 3.6 Flashlow· Epoch AI Benchmarking Hub data23%
58GPT 5high· Epoch AI Benchmarking Hub data23%
59GPT 5.2high· Epoch AI Benchmarking Hub data23%
60OpenAI o3medium· Epoch AI Benchmarking Hub data23%
61Claude Opus 4.548k· Epoch AI Benchmarking Hub data22%
62GPT 5.2medium· Epoch AI Benchmarking Hub data22%
63Qwen3.6 35B A3Bnone· Epoch AI Benchmarking Hub data22%
64Claude Opus 4.124k· Epoch AI Benchmarking Hub data21%
65GPT-5.6 Lunamax· Epoch AI Benchmarking Hub data21%
66Gemini 3 Flashhigh· Epoch AI Benchmarking Hub data20%
67GPT-5.6 Lunanone· Epoch AI Benchmarking Hub data20%
68Nemotron 3 Ultra· Epoch AI Benchmarking Hub data20%
69Qwen3.5 Flash· Epoch AI Benchmarking Hub data20%
70Gemini 3.5 Flash Litelow· Epoch AI Benchmarking Hub data19%
71GLM 5.2low· Epoch AI Benchmarking Hub data19%
72GPT 5.1low· Epoch AI Benchmarking Hub data19%
73GPT-5.6 Terralow· Epoch AI Benchmarking Hub data19%
74Qwen3.6 Max Previewnone· Epoch AI Benchmarking Hub data19%
75GLM 5.2minimal· Epoch AI Benchmarking Hub data18%
76GLM 5.2none· Epoch AI Benchmarking Hub data18%
77GPT 5.5none· Epoch AI Benchmarking Hub data18%
78Kimi K2.6· Epoch AI Benchmarking Hub data18%
79Qwen3.5 397B A17Bnone· Epoch AI Benchmarking Hub data18%
80Qwen3.6 Flashnone· Epoch AI Benchmarking Hub data18%
81Claude Sonnet 4.548k· Epoch AI Benchmarking Hub data17%
82DeepSeek V4 Pronone· Epoch AI Benchmarking Hub data17%
83GPT 5.4low· Epoch AI Benchmarking Hub data17%
84GPT-5.6 Lunalow· Epoch AI Benchmarking Hub data17%
85Mistral Large 4high· Epoch AI Benchmarking Hub data17%
86Qwen3.5 122B-A10Bnone· Epoch AI Benchmarking Hub data17%
87Qwen3.5 Plusnone· Epoch AI Benchmarking Hub data17%
88Qwen3.7 Plus· Epoch AI Benchmarking Hub data17%
89Claude Sonnet 4.6low· Epoch AI Benchmarking Hub data16%
90Claude Sonnet 5· Epoch AI Benchmarking Hub data16%
91GPT 5low· Epoch AI Benchmarking Hub data16%
92GPT 5.1medium· Epoch AI Benchmarking Hub data16%
93GPT 5.4none· Epoch AI Benchmarking Hub data16%
94Qwen3.5 Flashnone· Epoch AI Benchmarking Hub data16%
95Qwen3.5 Plus· Epoch AI Benchmarking Hub data16%
96Claude Opus 4.6· Epoch AI Benchmarking Hub data15%
97GLM 5.2medium· Epoch AI Benchmarking Hub data15%
98GPT 5medium· Epoch AI Benchmarking Hub data15%
99GPT 5.1none· Epoch AI Benchmarking Hub data15%
100Qwen3.7 Flash· Epoch AI Benchmarking Hub data15%

Showing 51–100 of 146 results.

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)