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
101Muse Spark 1.3xhigh· Epoch AI Benchmarking Hub data14.1%
102Claude Sonnet 4.6· Epoch AI Benchmarking Hub data14%
103GPT 5minimal· Epoch AI Benchmarking Hub data14%
104GPT 5.2none· Epoch AI Benchmarking Hub data14%
105GPT-5.6 Terranone· Epoch AI Benchmarking Hub data14%
106Qwen3.7 Flashnone· Epoch AI Benchmarking Hub data14%
107Claude Opus 4.7· Epoch AI Benchmarking Hub data13%
108Gemini 3.5 Flash Liteminimal· Epoch AI Benchmarking Hub data12%
109GPT 4· Epoch AI Benchmarking Hub data12%
110GPT-4o mini· Epoch AI Benchmarking Hub data12%
111GPT-5.6 Lunamedium· Epoch AI Benchmarking Hub data12%
112Kimi K2.6none· Epoch AI Benchmarking Hub data12%
113Kimi K3low· Epoch AI Benchmarking Hub data12%
114Qwen3.6 Flash· Epoch AI Benchmarking Hub data12%
115Qwen3.6 Plusnone· Epoch AI Benchmarking Hub data12%
116GPT-5.4 mininone· Epoch AI Benchmarking Hub data11%
117GPT 5.2low· Epoch AI Benchmarking Hub data10%
118GPT-5 miniminimal· Epoch AI Benchmarking Hub data10%
119GPT-5.6 Terramedium· Epoch AI Benchmarking Hub data10%
120GPT 5.4 Nanonone· Epoch AI Benchmarking Hub data9%
121GPT-5 nanolow· Epoch AI Benchmarking Hub data9%
122GPT-5 nanomedium· Epoch AI Benchmarking Hub data9%
123Qwen 3 235B A22B Thinking 2507· Epoch AI Benchmarking Hub data9%
124GLM 5.3 Flashmax· Epoch AI Benchmarking Hub data8%
125GPT-5 nanohigh· Epoch AI Benchmarking Hub data8%
126GPT-5.4 minilow· Epoch AI Benchmarking Hub data8%
127MiniMax M3none· Epoch AI Benchmarking Hub data8%
128Claude Opus 4.6low· Epoch AI Benchmarking Hub data7%
129GPT-4.1 mini· Epoch AI Benchmarking Hub data7%
130GPT-5.4 minimedium· Epoch AI Benchmarking Hub data7%
131GPT-6 Lunamax· Epoch AI Benchmarking Hub data7%
132MiniMax M3· Epoch AI Benchmarking Hub data7%
133o3 Minihigh· Epoch AI Benchmarking Hub data7%
134Qwen3.6 27Bnone· Epoch AI Benchmarking Hub data7%
135GPT 5.4 Nanomedium· Epoch AI Benchmarking Hub data6%
136Inkling Smallxhigh· Epoch AI Benchmarking Hub data6%
137GPT 5.4 Nanohigh· Epoch AI Benchmarking Hub data5%
138GPT-5 minihigh· Epoch AI Benchmarking Hub data5%
139GPT-5 nanominimal· Epoch AI Benchmarking Hub data5%
140o4 Minihigh· Epoch AI Benchmarking Hub data5%
141Qwen3 Max· Epoch AI Benchmarking Hub data5%
142GPT-5 minimedium· Epoch AI Benchmarking Hub data4%
143GPT 5.4 Nanolow· Epoch AI Benchmarking Hub data3%
144GPT-3.5 Turbo· Epoch AI Benchmarking Hub data3%
145GPT OSS 120Bmedium· Epoch AI Benchmarking Hub data2%
146GPT OSS 120Bhigh· Epoch AI Benchmarking Hub data0%

Showing 101–146 of 146 results.

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