Skip to content

Benchmark

OTIS Mock AIME

Math benchmarks measure how well models solve maths problems. Scores are percentages.

Models measured
196
Scores recorded
302
Sources
1
IQ weight
1.62

Score distribution

62.7%
Mean
71.1%
Median
32.9%
Std dev
6.5%
10th percentile
98.3%
90th percentile
0%
Min
0%100%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.62 for chat models, measured over 196 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
51DeepSeek V4 Prohigh· Epoch AI Benchmarking Hub data95.6%
52Doubao Seed 2.1 Prohigh· Epoch AI Benchmarking Hub data95.6%
53Gemini 3 Flashhigh· Epoch AI Benchmarking Hub data95.6%
54Gemini 3.1 Pro Previewhigh· Epoch AI Benchmarking Hub data95.6%
55Gemini 3.5 Flashhigh· Epoch AI Benchmarking Hub data95.6%
56GPT 5.4medium· Epoch AI Benchmarking Hub data95.6%
57GPT-5.6 Sollow· Epoch AI Benchmarking Hub data95.6%
58Kimi K2.7 Code· Epoch AI Benchmarking Hub data95.6%
59Qwen3.7 Max· Epoch AI Benchmarking Hub data95.6%
60GPT 5.4xhigh· Epoch AI Benchmarking Hub data95.3%
61Claude Sonnet 5xhigh· Epoch AI Benchmarking Hub data94.7%
62Claude Opus 4.664k· Epoch AI Benchmarking Hub data94.4%
63DeepSeek V4 Flash 0731max· Epoch AI Benchmarking Hub data94.4%
64Gemini 3.6 Flashhigh· Epoch AI Benchmarking Hub data94.2%
65Doubao Seed 2.0 Prohigh· Epoch AI Benchmarking Hub data93.9%
66GLM 5.3 Flashmax· Epoch AI Benchmarking Hub data93.9%
67GPT 5.2medium· Epoch AI Benchmarking Hub data93.9%
68Claude Opus 5low· Epoch AI Benchmarking Hub data93.3%
69GLM 5.1· Epoch AI Benchmarking Hub data93.3%
70Grok 4.3high· Epoch AI Benchmarking Hub data93.3%
71Kimi K3high· Epoch AI Benchmarking Hub data93.3%
72Qwen3.6 Plus· Epoch AI Benchmarking Hub data93.3%
73Qwen3.7 Plus· Epoch AI Benchmarking Hub data93.3%
74Claude Opus 4.632k· Epoch AI Benchmarking Hub data93.1%
75Gemini 3 Flash· Epoch AI Benchmarking Hub data92.8%
76Grok 4.20reasoning, 0309· Epoch AI Benchmarking Hub data92.2%
77Kimi K2.5· Epoch AI Benchmarking Hub data92.2%
78Gemini 3 Pro Preview· Epoch AI Benchmarking Hub data91.4%
79GPT 5high· Epoch AI Benchmarking Hub data91.4%
80Claude Opus 4.6max· Epoch AI Benchmarking Hub data91.1%
81Doubao Seed 2.0 Litehigh· Epoch AI Benchmarking Hub data91.1%
82GLM 5.3max· Epoch AI Benchmarking Hub data91.1%
83Qwen3.6 27B· Epoch AI Benchmarking Hub data91.1%
84Qwen3.6 Max Preview· Epoch AI Benchmarking Hub data91.1%
85Inkling Smallxhigh· Epoch AI Benchmarking Hub data90%
86Muse Spark· Epoch AI Benchmarking Hub data88.9%
87Gemini 3.5 Flashlow· Epoch AI Benchmarking Hub data88.9%
88GPT OSS 120Bhigh· Epoch AI Benchmarking Hub data88.9%
89GPT-5.4 minixhigh· Epoch AI Benchmarking Hub data88.9%
90GPT-5.6 Terralow· Epoch AI Benchmarking Hub data88.9%
91Inkling FP4xhigh· Epoch AI Benchmarking Hub data88.9%
92Qwen3.5 397B A17B· Epoch AI Benchmarking Hub data88.9%
93GPT 5.1high· Epoch AI Benchmarking Hub data88.6%
94DeepSeek Reasoner· Epoch AI Benchmarking Hub data87.8%
95GPT 5.4 Nanohigh· Epoch AI Benchmarking Hub data87.8%
96GPT 5medium· Epoch AI Benchmarking Hub data87.2%
97GPT-5.4 minihigh· Epoch AI Benchmarking Hub data87.2%
98Claude Opus 4.7max· Epoch AI Benchmarking Hub data86.7%
99GPT-5 minihigh· Epoch AI Benchmarking Hub data86.7%
100Nemotron 3 Ultra· Epoch AI Benchmarking Hub data86.7%

Showing 51–100 of 302 results.

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