Skip to content

Benchmark

MATH Level 5

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

Models measured
221
Scores recorded
238
Sources
2
IQ weight
1.72

Score distribution

32.6%
Mean
22%
Median
30.4%
Std dev
2.3%
10th percentile
87.1%
90th percentile
0%
Min
0%98.1%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.72 for chat models, measured over 221 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
201Qwen1.5-1.8B· Hugging Face Open LLM Leaderboard data3.2%
202gemma-2b· Hugging Face Open LLM Leaderboard data3%
203Mistral 7B Instruct v0.2· Hugging Face Open LLM Leaderboard data3%
204mistral-7b-v0.3· Hugging Face Open LLM Leaderboard data3%
205Gemma 7B IT· Hugging Face Open LLM Leaderboard data2.9%
206Mistral 7B v0.1· Hugging Face Open LLM Leaderboard data2.9%
207NexusRaven-V2-13B· Hugging Face Open LLM Leaderboard data2.9%
208phi-2· Hugging Face Open LLM Leaderboard data2.9%
209gemma2-2b· Hugging Face Open LLM Leaderboard data2.9%
210qwen2-0.5b-instruct· Hugging Face Open LLM Leaderboard data2.9%
211Zephyr 7B Beta· Hugging Face Open LLM Leaderboard data2.9%
212Qwen1.5-4B-Chat· Hugging Face Open LLM Leaderboard data2.8%
213Mistral (7B) Instruct v0.1· Hugging Face Open LLM Leaderboard data2.3%
214Nous-Hermes-2-Mixtral-8x7B-SFT· Hugging Face Open LLM Leaderboard data2.1%
215RedPajama-INCITE-7B-Instruct· Hugging Face Open LLM Leaderboard data2.1%
216Gemma 2B IT· Hugging Face Open LLM Leaderboard data2%
217recurrentgemma-2b· Hugging Face Open LLM Leaderboard data2%
218Llama-2-7b-chat-hf· Hugging Face Open LLM Leaderboard data2%
219Qwen1.5-1.8B-Chat· Hugging Face Open LLM Leaderboard data2%
220Gemma 1.1 2B IT· Hugging Face Open LLM Leaderboard data1.8%
221Yi-6B200k· Hugging Face Open LLM Leaderboard data1.8%
222Qwen1.5-0.5B· Hugging Face Open LLM Leaderboard data1.7%
223Llama-2-7B-32K-Instruct· Hugging Face Open LLM Leaderboard data1.6%
224RedPajama-INCITE-7B-Base· Hugging Face Open LLM Leaderboard data1.6%
225Yi-6B· Hugging Face Open LLM Leaderboard data1.6%
226RedPajama-INCITE-Base-3B-v1· Hugging Face Open LLM Leaderboard data1.4%
227Llama-2-13b-chat-hf· Hugging Face Open LLM Leaderboard data1.4%
228vicuna-7b-v1.5· Hugging Face Open LLM Leaderboard data1.4%
229RedPajama-INCITE-Instruct-3B-v1· Hugging Face Open LLM Leaderboard data1.3%
230Llama 3.2 1B· Hugging Face Open LLM Leaderboard data1.2%
231Nous-Hermes-llama-2-7b· Hugging Face Open LLM Leaderboard data0.906%
232RedPajama-INCITE-Chat-3B-v1· Hugging Face Open LLM Leaderboard data0.906%
233Qwen1.5-0.5B-Chat· Hugging Face Open LLM Leaderboard data0.68%
234RedPajama-INCITE-7B-Chat· Hugging Face Open LLM Leaderboard data0.68%
235Gemma 2 2B IT· Hugging Face Open LLM Leaderboard data0.0755%
236GLM 4 9B 0414· Hugging Face Open LLM Leaderboard data0%
237GLM-4-9b-chat· Hugging Face Open LLM Leaderboard data0%
238Qwen2.5 0.5b Instruct· Hugging Face Open LLM Leaderboard data0%

Showing 201–238 of 238 results.

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