Skip to content

Benchmark

MathArena Apex

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

Models measured
54
Scores recorded
62
Sources
3
IQ weight
2.67

Score distribution

26.7%
Mean
19.8%
Median
26.4%
Std dev
0.52%
10th percentile
65.6%
90th percentile
0%
Min
0%81.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.67 for chat models, measured over 54 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#Model
51GLM 4.5· MathArena data1%
52GPT 5high· MathArena data1%
53GPT 5.1high· MathArena data1%
54GPT OSS 120Bhigh· MathArena data1%
55GPT-5 minihigh· MathArena data1%
56DeepSeek V3.1think· MathArena data0.52%
57DeepSeek V3.2 Expthink· MathArena data0.52%
58Gemini 2.5 Pro· MathArena data0.52%
59GLM 4.6· MathArena data0.52%
60Qwen3 30B A3Bthink· MathArena data0.52%
61Qwen3.5 9B· MathArena data0.52%
62Kimi K2 Thinking· MathArena data0%

Showing 51–62 of 62 results.

Tokens the model generated per task, as measured by the source. Comparable within this benchmark only.

Data credits: MathArena (ETH SRI / INSAIT), MIT — cite dekoninck2026matharena (licence) · Data by LLM Stats · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.