Math

LiveBench Math Leaderboard

LiveBench Math measures mathematical problem-solving on contamination-free, regularly-refreshed questions, including competition-style problems.

Source: livebench8 open models ranked+29 proprietaryData through Jun 2026

Open models ranked on LiveBench Math

# shows rank among open models / rank overall (including proprietary).

#ModelScore
1 / 15DeepSeek V4 Pro · 861.6B
90.7
2 / 17GLM 5.2 · 753.3B
89.8
3 / 21Inkling · 952.4B
88.4
4 / 30Kimi K2.6 · 1058.6B
84.3
5 / 32Qwen3.6 27B · 27.8B
79.9
6 / 33DeepSeek V4 Flash · 158.1B
79.7
7 / 34Kimi K2.7 Code · 1058.6B
79.6
8 / 37MiniMax M3 · 427.0B
77.0

Score vs model size

Which models give the most quality for their size — the ones worth running locally.

100B1Tmodel size (log scale) →90.777.0Inkling · 952B · 88.4Kimi K2.6 · 1.1T · 84.3DeepSeek V4 Flash · 158B · 79.7Kimi K2.7 Code · 1.1T · 79.6MiniMax M3 · 427B · 77.0Qwen3.6 27B · 28B · 79.9Qwen3.6 27BGLM 5.2 · 753B · 89.8GLM 5.2DeepSeek V4 Pro · 862B · 90.7DeepSeek V4 Pro
Each dot is a model. Up = higher score, left = smaller (easier to run locally). The dashed line marks the efficiency frontier — the best score you can get at each size or smaller.
  • Qwen3.6 27B, 28B, score 79.9 — on the efficiency frontier (best score at its size or smaller).
  • GLM 5.2, 753B, score 89.8 — on the efficiency frontier (best score at its size or smaller).
  • DeepSeek V4 Pro, 862B, score 90.7 — on the efficiency frontier (best score at its size or smaller).

LiveBench Math: frequently asked questions

What is the best open LLM on LiveBench Math?
DeepSeek V4 Pro is the top open model on LiveBench Math, scoring 90.7. Among all models tested — including proprietary ones — it ranks #15. The top model overall is GPT 5.6 Sol Max (OpenAI) at 96.2.
What's the best LiveBench Math model you can run on a 24 GB GPU?
Qwen3.6 27B is the highest-scoring open model that fits in 24 GB at 4-bit quantization (about 15 GB), scoring 79.9 on LiveBench Math.
Can open models match proprietary models on LiveBench Math?
Not quite on LiveBench Math: the strongest proprietary model (GPT 5.6 Sol Max) scores 96.2, ahead of the best open model (DeepSeek V4 Pro) at 90.7 — but you can run the open one yourself.

Scores aggregated from livebench. llmrun does not run this benchmark — see the source for methodology, or the about benchmarks for what it measures.