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
151Claude Sonnet 4.6max· Epoch AI Benchmarking Hub data71.1%
152Gemini 3.5 Flash Litehigh· Epoch AI Benchmarking Hub data71.1%
153MiniMax M3· Epoch AI Benchmarking Hub data71.1%
154Gemini 2.5 Flash Preview 05-20 (no think)· Epoch AI Benchmarking Hub data70.8%
155Qwen3 30B A3B2507, thinking· Epoch AI Benchmarking Hub data70.3%
156Qwen3.5 35B A3Bnone· Epoch AI Benchmarking Hub data70%
157Doubao-Seed 1.6· Epoch AI Benchmarking Hub data69.4%
158Claude Opus 4.127k· Epoch AI Benchmarking Hub data68.9%
159Claude Sonnet 459k· Epoch AI Benchmarking Hub data68.9%
160GPT 5.4 Nanolow· Epoch AI Benchmarking Hub data68.9%
161GPT-5.6 Solnone· Epoch AI Benchmarking Hub data68.9%
162Kimi K3low· Epoch AI Benchmarking Hub data68.9%
163Qwen3.6 35B A3Bnone· Epoch AI Benchmarking Hub data68.9%
164GPT-5.5 Instant· Epoch AI Benchmarking Hub data68.1%
165Seed OSS 36B Instruct· Epoch AI Benchmarking Hub data67.5%
166Qwen3 32B· Epoch AI Benchmarking Hub data66.9%
167Claude Haiku 4.532k· Epoch AI Benchmarking Hub data66.7%
168GPT-5.6 Lunalow· Epoch AI Benchmarking Hub data66.7%
169Qwen3.6 27Bnone· Epoch AI Benchmarking Hub data66.7%
170DeepSeek R1· Epoch AI Benchmarking Hub data66.4%
171Qwen3 14B· Epoch AI Benchmarking Hub data66.4%
172GPT OSS 20bmedium· Epoch AI Benchmarking Hub data65.3%
173Claude Opus 427k· Epoch AI Benchmarking Hub data64.4%
174Claude Opus 4.116k· Epoch AI Benchmarking Hub data64.4%
175GPT 5.1low· Epoch AI Benchmarking Hub data63.9%
176o3 Minimedium· Epoch AI Benchmarking Hub data63.9%
177Qwen3 30B A3B· Epoch AI Benchmarking Hub data62.8%
178GPT 5.2none· Epoch AI Benchmarking Hub data62.2%
179Grok 3 Minilow, beta· Epoch AI Benchmarking Hub data62.2%
180Qwen3 30B A3B Instruct· Epoch AI Benchmarking Hub data62.2%
181Qwen3.5 9Bnone· Epoch AI Benchmarking Hub data61.7%
182Claude Opus 416k· Epoch AI Benchmarking Hub data60%
183Gemini 3.5 Flash Litelow· Epoch AI Benchmarking Hub data60%
184OpenAI o3low· Epoch AI Benchmarking Hub data60%
185QwQ 32B· Epoch AI Benchmarking Hub data59.2%
186GLM 4.7 Flash· Epoch AI Benchmarking Hub data58.3%
187Claude Sonnet 3.764k· Epoch AI Benchmarking Hub data57.8%
188Gemini 2.0 Flash Experimentalthinking· Epoch AI Benchmarking Hub data57.8%
189GPT 5.4none· Epoch AI Benchmarking Hub data57.8%
190GPT 5.5none· Epoch AI Benchmarking Hub data57.8%
191o4 Minilow· Epoch AI Benchmarking Hub data57.8%
192Qwen3 8B· Epoch AI Benchmarking Hub data56.1%
193Qwen3.5 4Bnone· Epoch AI Benchmarking Hub data55.8%
194DeepSeek R1 Distill Qwen 32B· Epoch AI Benchmarking Hub data55.6%
195GPT-5 miniminimal· Epoch AI Benchmarking Hub data55.6%
196Grok 3beta· Epoch AI Benchmarking Hub data55.6%
197Qwen3.5 35B A3B· Epoch AI Benchmarking Hub data54.4%
198Claude Sonnet 3.732k· Epoch AI Benchmarking Hub data53.3%
199Claude Sonnet 416k· Epoch AI Benchmarking Hub data53.3%
200GPT-5.6 Terranone· Epoch AI Benchmarking Hub data53.3%

Showing 151–200 of 302 results.

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