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
1Claude Fable 5high· Epoch AI Benchmarking Hub data100%
2Claude Fable 5.1max· Epoch AI Benchmarking Hub data100%
3Claude Opus 5.5max· Epoch AI Benchmarking Hub data100%
4Claude Sonnet 5.5max· Epoch AI Benchmarking Hub data100%
5Gemini 4 Argonhigh· Epoch AI Benchmarking Hub data100%
6Gemini 4 Carbonhigh· Epoch AI Benchmarking Hub data100%
7Gemini 4 Hydrogenxhigh· Epoch AI Benchmarking Hub data100%
8Gemini 4 Neonxhigh· Epoch AI Benchmarking Hub data100%
9GPT-5.6 Solmax· Epoch AI Benchmarking Hub data100%
10GPT-6 Astramax· Epoch AI Benchmarking Hub data100%
11GPT-6 Solmax· Epoch AI Benchmarking Hub data100%
12GPT-6.1 Solmax· Epoch AI Benchmarking Hub data100%
13GPT-6.1 Terramax· Epoch AI Benchmarking Hub data100%
14GPT-6.2 Astramax· Epoch AI Benchmarking Hub data100%
15Qwen3.8 Maxxhigh· Epoch AI Benchmarking Hub data100%
16Claude Fable 5max· Epoch AI Benchmarking Hub data99.7%
17Claude Fable 5.2max· Epoch AI Benchmarking Hub data99.7%
18GPT-5.6 Terramax· Epoch AI Benchmarking Hub data99.7%
19DeepSeek V4.1 Flash 1017max· Epoch AI Benchmarking Hub data99.4%
20Muse Wonder 1.0max· Epoch AI Benchmarking Hub data99.4%
21Doubao Seed Evolvinghigh· Epoch AI Benchmarking Hub data99.2%
22Grok 4.6xhigh· Epoch AI Benchmarking Hub data99.2%
23Muse Spark 1.3xhigh· Epoch AI Benchmarking Hub data99.2%
24Claude Haiku 5.5xhigh· Epoch AI Benchmarking Hub data98.9%
25Claude Opus 5max· Epoch AI Benchmarking Hub data98.9%
26Gemini 3.8 Flashhigh· Epoch AI Benchmarking Hub data98.9%
27GPT-6 Lunamax· Epoch AI Benchmarking Hub data98.9%
28DeepSeek V4 Pro 0813max· Epoch AI Benchmarking Hub data98.6%
29Claude Opus 4.8max· Epoch AI Benchmarking Hub data98.3%
30DeepSeek V4.1 Flashmax· Epoch AI Benchmarking Hub data98.3%
31GPT-5.6 Lunamax· Epoch AI Benchmarking Hub data98.3%
32Mistral Large 4high· Epoch AI Benchmarking Hub data98.3%
33Grok 4.7xhigh· Epoch AI Benchmarking Hub data98.1%
34Muse Spark Open 816B A42Bxhigh· Epoch AI Benchmarking Hub data98.1%
35Claude Opus 4.7xhigh· Epoch AI Benchmarking Hub data97.8%
36Claude Fable 5low· Epoch AI Benchmarking Hub data97.8%
37Claude Opus 4.8low· Epoch AI Benchmarking Hub data97.8%
38Claude Opus 5· Epoch AI Benchmarking Hub data97.8%
39GPT 5.4high· Epoch AI Benchmarking Hub data97.8%
40Grok 4.5high· Epoch AI Benchmarking Hub data97.8%
41Grok 4.6high· Epoch AI Benchmarking Hub data97.8%
42Claude Haiku 5.5high· Epoch AI Benchmarking Hub data97.2%
43Gemini 3.7 Flashhigh· Epoch AI Benchmarking Hub data97.2%
44Kimi K3max· Epoch AI Benchmarking Hub data97.2%
45DeepSeek V4 Promax· Epoch AI Benchmarking Hub data96.7%
46Doubao Seed 2.1 Turbohigh· Epoch AI Benchmarking Hub data96.1%
47GPT 5.2high· Epoch AI Benchmarking Hub data96.1%
48Kimi K2.6· Epoch AI Benchmarking Hub data96.1%
49GPT 5.2xhigh· Epoch AI Benchmarking Hub data96.1%
50Gemini 3.1 Pro Preview· Epoch AI Benchmarking Hub data95.6%

Showing 1–50 of 302 results.

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