Math

MATH Level 5 Leaderboard

MATH Level 5 covers the hardest tier of competition-mathematics problems, testing multi-step symbolic and quantitative reasoning.

Source: epoch32 open models ranked+76 proprietaryData through Oct 2025

All models ranked on MATH Level 5

Proprietary / closed models are shown dimmed — you can't run them locally, but they show where the open field stands.

#ModelScore
1GPT 5 (Aug 07, 2025, high) · proprietary
98.1%
2GPT 5 (Aug 07, 2025, medium) · proprietary
97.9%
3GPT 5 Mini (Aug 07, 2025, high) · proprietary
97.9%
4O4 Mini (Apr 16, 2025, high) · proprietary
97.8%
5O3 (Apr 16, 2025, high) · proprietary
97.8%
6Claude Sonnet 4.5 (Sep 29, 2025, 32K) · proprietary
97.7%
7Qwen3 Max (Sep 23, 2025) · proprietary
97.1%
8GPT 5 Mini (Aug 07, 2025, medium) · proprietary
96.8%
9DeepSeek R1 0528 · 684.5B
96.6%
10O3 Mini (Jan 31, 2025, high) · proprietary
96.5%
11Claude Haiku 4.5 (Oct 01, 2025, 32K) · proprietary
96.4%
12Gemini 2.5 Pro Preview (May 06) · proprietary
95.9%
13Gemini 2.5 Pro Preview (Mar 25) · proprietary
95.6%
14GPT 5 Nano (Aug 07, 2025, medium) · proprietary
95.2%
15O3 Mini (Jan 31, 2025, medium) · proprietary
95.2%
16GPT 5 Nano (Aug 07, 2025, high) · proprietary
94.9%
17O1 (Dec 17, 2024, high) · proprietary
94.7%
18O1 (Dec 17, 2024, medium) · proprietary
94.4%
19DeepSeek R1 · 684.5B
93.0%
20Claude 3.7 Sonnet (Feb 19, 2025, 64K) · proprietary
91.2%
21Grok 3 Mini Beta (low) · proprietary
90.9%
22Claude 3.7 Sonnet (Feb 19, 2025, 32K) · proprietary
90.0%
23DeepSeek R1 Distill Llama 70B · 70.6B
89.9%
24O1 Mini (Sep 12, 2024, high) · proprietary
89.2%
25Grok 3 Beta · proprietary
88.8%
26Grok 3 Mini Beta (high) · proprietary
88.1%
27GPT 4.1 Mini (Apr 14, 2025) · proprietary
87.3%
28DeepSeek R1 Distill Qwen 14B · 14.8B
87.1%
29Claude Haiku 4.5 (Oct 01, 2025) · proprietary
86.9%
30Claude 3.7 Sonnet (Feb 19, 2025, 16K) · proprietary
86.3%
31Claude Opus 4 (May 14, 2025) · proprietary
85.0%
32Claude Sonnet 4 (May 14, 2025) · proprietary
84.4%
33O1 Mini (Sep 12, 2024, medium) · proprietary
84.3%
34Gemini 2.0 Pro Exp (Feb 05) · proprietary
83.5%
35GPT 4.1 (Apr 14, 2025) · proprietary
83.0%
36Gemini 2.0 Flash 001 · proprietary
82.2%
37O1 Preview (Sep 12, 2024) · proprietary
81.7%
38Mistral Medium 2505 · proprietary
81.6%
39GPT 4.5 Preview (Feb 27, 2025) · proprietary
78.6%
40DeepSeek v3 0324 · 684.5B
75.5%
41Gemma 3 27B IT · 27.4B
74.0%
42Llama 4 Maverick 17B 128E Instruct · 401.6B
73.0%
43Gemini 1.5 Pro 002 · proprietary
70.4%
44GPT 4.1 Nano (Apr 14, 2025) · proprietary
70.0%
45Qwen3 235B A22B · 235.1B
68.9%
46Claude 3.7 Sonnet (Feb 19, 2025) · proprietary
68.2%
47Qwen Max (Jan 25, 2025) · proprietary
67.2%
48Qwen Plus (Jan 25, 2025) · proprietary
65.3%
49Phi 4 · 14.7B
64.9%
50DeepSeek v3 · 684.5B
64.8%
51Grok 2 (Dec 12) · proprietary
63.5%
52Qwen2.5 72B Instruct · 72.7B
63.2%
53Llama 4 Scout 17B 16E Instruct · 108.6B
62.3%
54Gemini 1.5 Flash 002 · proprietary
61.9%
55Claude 3.5 Sonnet (Oct 22, 2024) · proprietary
57.0%
56Qwen Turbo (Nov 01, 2024) · proprietary
56.2%
57Qwen2.5 32B Instruct · 32.8B
56.1%
58GPT 4o (Aug 06, 2024) · proprietary
53.3%
59GPT 4o Mini (Jul 18, 2024) · proprietary
52.6%
60Claude 3.5 Sonnet (Jun 20, 2024) · proprietary
51.7%
61GPT 4o (May 13, 2024) · proprietary
51.0%
62Mistral Large 2411 · proprietary
50.3%
63GPT 4o (Nov 20, 2024) · proprietary
49.8%
64Llama 3.1 405B Instruct · 405.9B
49.8%
65Mistral Small 2503 · proprietary
46.8%
66GPT 4 Turbo (Apr 09, 2024) · proprietary
46.7%
67Claude 3.5 Haiku (Oct 22, 2024) · proprietary
46.4%
68Mistral Large 2407 · proprietary
44.8%
69Mistral Small 2501 · proprietary
44.8%
70Llama 3.1 Tulu 3 70B DPO · 70.6B
42.7%
71Llama 3.3 70B Instruct · 70.6B
41.6%
72Gemini 1.5 Pro 001 · proprietary
40.8%
73GPT 4 1106 Preview · proprietary
40.0%
74Llama 3.2 90B Vision Instruct · 88.6B
39.4%
75Qwen2 72B Instruct · 72.7B
39.1%
76Claude 3 Opus (Feb 29, 2024) · proprietary
37.5%
77Llama 3.1 70B Instruct · 70.6B
36.7%
78GPT 4 0125 Preview · proprietary
35.4%
79Gemma 2 27B IT · 27.2B
27.9%
80WizardLM 2 8x22B · 140.6B
25.7%
81Yi 1.5 34B Chat · 34.4B
25.5%
82Gemini 1.5 Flash 001 · proprietary
25.1%
83Mistral Large 2402 · proprietary
24.5%
84Open Mixtral 8x22b · proprietary
24.2%
85GPT 4 (Jun 13) · proprietary
23.0%
86Llama 3.1 8B Instruct · 8.0B
22.9%
87Hermes 2 Theta Llama 3 70B · 70.6B
22.7%
88Meta Llama 3 70B Instruct · 70.6B
22.6%
89Gemma 2 9B IT · 9.2B
21.0%
90Claude 3 Sonnet (Feb 29, 2024) · proprietary
18.2%
91Phi 3 Medium 128K Instruct · proprietary
17.6%
92GPT 3.5 Turbo (Nov 06) · proprietary
15.9%
93Ministral 8B 2410 · proprietary
14.9%
94Claude 3 Haiku (Mar 07, 2024) · proprietary
14.9%
95Ministral 3B 2410 · proprietary
14.4%
96Claude 2.0 · proprietary
11.7%
97Dbrx Instruct · proprietary
11.7%
98GPT 3.5 Turbo (Jan 25) · proprietary
11.6%
99Gemini 1.0 Pro 001 · proprietary
11.2%
100Open Mistral Nemo 2407 · proprietary
10.8%
101Open Mixtral 8x7b · proprietary
10.0%
102Mixtral 8x7B Instruct v0.1 · 46.7B
9.3%
103Deepseek Llm 67B Chat · 67B
6.4%
104Meta Llama 3 8B Instruct · 8.0B
6.1%
105Yi 34B Chat · 34.4B
5.1%
106Open Mistral 7B · proprietary
3.7%
107Mistral 7B Instruct v0.3 · 7.2B
3.6%
108Llama 2 70B Chat HF · 69.0B
3.3%

Score vs model size

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

10B100Bmodel size (log scale) →96.6%3.3%DeepSeek R1 · 685B · 93.0%DeepSeek v3 0324 · 685B · 75.5%Gemma 3 27B IT · 27B · 74.0%Llama 4 Maverick 17B 128E Instruct · 402B · 73.0%Qwen3 235B A22B · 235B · 68.9%DeepSeek v3 · 685B · 64.8%Qwen2.5 72B Instruct · 73B · 63.2%Llama 4 Scout 17B 16E Instruct · 109B · 62.3%Qwen2.5 32B Instruct · 33B · 56.1%Llama 3.1 405B Instruct · 406B · 49.8%Llama 3.1 Tulu 3 70B DPO · 71B · 42.7%Llama 3.3 70B Instruct · 71B · 41.6%Llama 3.2 90B Vision Instruct · 89B · 39.4%Qwen2 72B Instruct · 73B · 39.1%Llama 3.1 70B Instruct · 71B · 36.7%Gemma 2 27B IT · 27B · 27.9%WizardLM 2 8x22B · 141B · 25.7%Yi 1.5 34B Chat · 34B · 25.5%Hermes 2 Theta Llama 3 70B · 71B · 22.7%Meta Llama 3 70B Instruct · 71B · 22.6%Gemma 2 9B IT · 9B · 21.0%Mixtral 8x7B Instruct v0.1 · 47B · 9.3%Deepseek Llm 67B Chat · 67B · 6.4%Meta Llama 3 8B Instruct · 8B · 6.1%Yi 34B Chat · 34B · 5.1%Llama 2 70B Chat HF · 69B · 3.3%Mistral 7B Instruct v0.3 · 7B · 3.6%Mistral 7B Instruct v…Llama 3.1 8B Instruct · 8B · 22.9%Llama 3.1 8B InstructPhi 4 · 15B · 64.9%Phi 4DeepSeek R1 Distill Qwen 14B · 15B · 87.1%DeepSeek R1 Distill Q…DeepSeek R1 Distill Llama 70B · 71B · 89.9%DeepSeek R1 Distill L…DeepSeek R1 0528 · 685B · 96.6%DeepSeek R1 0528
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.
  • Mistral 7B Instruct v0.3, 7B, score 3.6% — on the efficiency frontier (best score at its size or smaller).
  • Llama 3.1 8B Instruct, 8B, score 22.9% — on the efficiency frontier (best score at its size or smaller).
  • Phi 4, 15B, score 64.9% — on the efficiency frontier (best score at its size or smaller).
  • DeepSeek R1 Distill Qwen 14B, 15B, score 87.1% — on the efficiency frontier (best score at its size or smaller).
  • DeepSeek R1 Distill Llama 70B, 71B, score 89.9% — on the efficiency frontier (best score at its size or smaller).
  • DeepSeek R1 0528, 685B, score 96.6% — on the efficiency frontier (best score at its size or smaller).

MATH Level 5: frequently asked questions

What is the best open LLM on MATH Level 5?
DeepSeek R1 0528 is the top open model on MATH Level 5, scoring 96.6%. Among all models tested — including proprietary ones — it ranks #9. The top model overall is GPT 5 (Aug 07, 2025, high) (OpenAI) at 98.1%.
What's the best MATH Level 5 model you can run on a 24 GB GPU?
DeepSeek R1 Distill Qwen 14B is the highest-scoring open model that fits in 24 GB at 4-bit quantization (about 8 GB), scoring 87.1% on MATH Level 5.
What's the best MATH Level 5 model you can run on a 12 GB GPU?
DeepSeek R1 Distill Qwen 14B is the highest-scoring open model that fits in 12 GB at 4-bit quantization (about 8 GB), scoring 87.1% on MATH Level 5.
Can open models match proprietary models on MATH Level 5?
Not quite on MATH Level 5: the strongest proprietary model (GPT 5 (Aug 07, 2025, high)) scores 98.1%, ahead of the best open model (DeepSeek R1 0528) at 96.6% — but you can run the open one yourself.

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