MATH-500

math · math · 141 scores

rank	variant	root	org	score	conf	context
1	NVIDIA-Nemotron-Nano-12B-v2	nvidia/NVIDIA-Nemotron-Nano-12B-v2-Base	nvidia	97.75	medium	MATH500
2	NVIDIA-Nemotron-Nano-12B-v2-GGUF	nvidia/NVIDIA-Nemotron-Nano-12B-v2-Base	Mungert	97.75	medium	MATH500
3	cwm	facebook/cwm	facebook	97.2	low
4	cwm-pretrain	facebook/cwm-pretrain	facebook	97.2	low
5	Nemotron-H-47B-Reasoning-128K	nvidia/Nemotron-H-47B-Reasoning-128K	nvidia	96.6	medium	MATH500
6	Nemotron-H-47B-Reasoning-128K-FP8	nvidia/Nemotron-H-47B-Reasoning-128K	nvidia	96.6	medium	MATH500
7	NVIDIA-Nemotron-Nano-9B-v2	nvidia/NVIDIA-Nemotron-Nano-12B-v2-Base	nvidia	96.3	medium	MATH500
8	NVIDIA-Nemotron-Nano-9B-v2-FP8	nvidia/NVIDIA-Nemotron-Nano-9B-v2	nvidia	96.3	medium	MATH500
9	NVIDIA-Nemotron-Nano-9B-v2-NVFP4	nvidia/NVIDIA-Nemotron-Nano-9B-v2	nvidia	96.3	medium	MATH500
10	NVIDIA-Nemotron-Nano-9B-v2	nvidia/NVIDIA-Nemotron-Nano-9B-v2	unsloth	96.3	medium	MATH500
11	NVIDIA-Nemotron-3-Nano-4B-BF16	nvidia/NVIDIA-Nemotron-Nano-9B-v2	nvidia	95.4	medium	MATH500
12	NVIDIA-Nemotron-3-Nano-4B-FP8	nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16	nvidia	95.4	medium	MATH500
13	NVIDIA-Nemotron-3-Nano-4B	nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16	unsloth	95.4	medium	MATH500
14	NVIDIA-Nemotron-3-Nano-4B-GGUF	nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16	unsloth	95.4	medium	MATH500
15	NVIDIA-Nemotron-3-Nano-4B-FP8	nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16	unsloth	95.4	medium	MATH500
16	Qwen3-8B-DMS-8x	Qwen/Qwen3-8B	nvidia	95.1	medium	MATH-500
17	Nemotron-H-8B-Reasoning-128K	nvidia/Nemotron-H-8B-Reasoning-128K	nvidia	94.8	medium	MATH500
18	Nemotron-H-8B-Reasoning-128K-FP8	nvidia/Nemotron-H-8B-Reasoning-128K	nvidia	94.8	medium	MATH500
19	Rubicon-Preview	inclusionAI/Rubicon-Preview	inclusionAI	94.75	low
20	DeepSeek-R1-Distill-Llama-70B	deepseek-ai/DeepSeek-R1-Distill-Llama-70B	deepseek-ai	94.5	high
21	DeepSeek-R1-Distill-Llama-70B-GGUF	deepseek-ai/DeepSeek-R1-Distill-Llama-70B	unsloth	94.5	high
22	r1-1776-distill-llama-70b-GGUF	perplexity-ai/r1-1776-distill-llama-70b	unsloth	94.5	medium	MATH-500
23	DeepSeek-R1-Distill-Llama-70B-bnb-4bit	deepseek-ai/DeepSeek-R1-Distill-Llama-70B	unsloth	94.5	high
24	DeepSeek-R1-Distill-Llama-70B-GGUF	deepseek-ai/DeepSeek-R1-Distill-Llama-70B	Mungert	94.5	high
25	DeepSeek-R1-Distill-Llama-70B-unsloth-bnb-4bit	deepseek-ai/DeepSeek-R1-Distill-Llama-70B	unsloth	94.5	high
26	DeepSeek-R1-Distill-Llama-70B	deepseek-ai/DeepSeek-R1-Distill-Llama-70B	unsloth	94.5	high
27	DeepSeek-R1-Distill-Qwen-32B	deepseek-ai/DeepSeek-R1-Distill-Qwen-32B	deepseek-ai	94.3	high
28	DeepSeek-R1-Distill-Qwen-32B-GGUF	deepseek-ai/DeepSeek-R1-Distill-Qwen-32B	unsloth	94.3	high
29	DeepSeek-R1-Distill-Qwen-32B-bnb-4bit	deepseek-ai/DeepSeek-R1-Distill-Qwen-32B	unsloth	94.3	high
30	DeepSeek-R1-Distill-Qwen-32B	deepseek-ai/DeepSeek-R1-Distill-Qwen-32B	unsloth	94.3	high
31	DeepSeek-R1-Distill-Qwen-32B-unsloth-bnb-4bit	deepseek-ai/DeepSeek-R1-Distill-Qwen-32B	unsloth	94.3	high
32	DeepSeek-R1-Distill-Qwen-32B-GGUF	deepseek-ai/DeepSeek-R1-Distill-Qwen-32B	Mungert	94.3	high
33	DeepSeek-V3-0324-NVFP4	deepseek-ai/DeepSeek-V3-0324	nvidia	94.0	medium	MATH-500
34	DeepSeek-R1-Distill-Qwen-14B	deepseek-ai/DeepSeek-R1-Distill-Qwen-14B	deepseek-ai	93.9	high
35	DeepSeek-R1-Distill-Qwen-14B-GGUF	deepseek-ai/DeepSeek-R1-Distill-Qwen-14B	unsloth	93.9	high
36	DeepSeek-R1-Distill-Qwen-14B-unsloth-bnb-4bit	deepseek-ai/DeepSeek-R1-Distill-Qwen-14B	unsloth	93.9	high
37	DeepSeek-R1-Distill-Qwen-14B-bnb-4bit	deepseek-ai/DeepSeek-R1-Distill-Qwen-14B	unsloth	93.9	high
38	DeepSeek-R1-Distill-Qwen-14B	deepseek-ai/DeepSeek-R1-Distill-Qwen-14B	unsloth	93.9	high
39	DeepSeek-R1-Distill-Qwen-14B-GGUF	deepseek-ai/DeepSeek-R1-Distill-Qwen-14B	Mungert	93.9	high
40	Ring-lite-linear-preview	inclusionAI/Ling-lite	inclusionAI	93.8	high
41	Ring-lite-distill-preview	inclusionAI/Ling-lite	inclusionAI	93.7	high
42	DeepSeek-R1-Distill-Qwen-7B	deepseek-ai/DeepSeek-R1-Distill-Qwen-7B	deepseek-ai	92.8	high
43	DeepSeek-R1-Distill-Qwen-7B-GGUF	deepseek-ai/DeepSeek-R1-Distill-Qwen-7B	unsloth	92.8	high
44	DeepSeek-R1-Distill-Qwen-7B-unsloth-bnb-4bit	deepseek-ai/DeepSeek-R1-Distill-Qwen-7B	unsloth	92.8	high
45	DeepSeek-R1-Distill-Qwen-7B-bnb-4bit	deepseek-ai/DeepSeek-R1-Distill-Qwen-7B	unsloth	92.8	high
46	DeepSeek-R1-Distill-Qwen-7B	deepseek-ai/DeepSeek-R1-Distill-Qwen-7B	unsloth	92.8	high
47	DeepSeek-R1-Distill-Qwen-7B-GGUF	deepseek-ai/DeepSeek-R1-Distill-Qwen-7B	Mungert	92.8	high
48	AceMath-RL-Nemotron-7B	nvidia/AceMath-RL-Nemotron-7B	nvidia	92.8	low
49	DistilQwen2.5-R1-3B	alibaba-pai/DistilQwen2.5-R1-3B	alibaba-pai	92.8	low
50	AceMath-RL-Nemotron-7B-GGUF	nvidia/AceMath-RL-Nemotron-7B	Mungert	92.8	low
51	Phi-4-mini-reasoning	microsoft/Phi-4-mini-reasoning	microsoft	90.0	low
52	Phi-4-mini-reasoning-GGUF	microsoft/Phi-4-mini-reasoning	unsloth	90.0	low
53	Phi-4-mini-reasoning-unsloth-bnb-4bit	microsoft/Phi-4-mini-reasoning	unsloth	90.0	low
54	Phi-4-mini-reasoning	microsoft/Phi-4-mini-reasoning	unsloth	90.0	low
55	Phi-4-mini-reasoning-GGUF	microsoft/Phi-4-mini-reasoning	Mungert	90.0	low
56	Phi-4-mini-reasoning-bnb-4bit	microsoft/Phi-4-mini-reasoning	unsloth	90.0	low
57	DeepSeek-R1-Distill-Llama-8B	deepseek-ai/DeepSeek-R1-Distill-Llama-8B	deepseek-ai	89.1	high
58	DeepSeek-R1-Distill-Llama-8B-GGUF	deepseek-ai/DeepSeek-R1-Distill-Llama-8B	unsloth	89.1	high
59	DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit	deepseek-ai/DeepSeek-R1-Distill-Llama-8B	unsloth	89.1	high
60	DeepSeek-R1-Distill-Llama-8B	deepseek-ai/DeepSeek-R1-Distill-Llama-8B	unsloth	89.1	high
61	DeepSeek-R1-Distill-Llama-8B-bnb-4bit	deepseek-ai/DeepSeek-R1-Distill-Llama-8B	unsloth	89.1	high
62	DeepSeek-R1-Distill-Llama-8B-GGUF	deepseek-ai/DeepSeek-R1-Distill-Llama-8B	Mungert	89.1	high
63	LFM2.5-8B-A1B-GGUF	LiquidAI/LFM2.5-8B-A1B	unsloth	88.76	high
64	LFM2.5-8B-A1B	LiquidAI/LFM2.5-8B-A1B	unsloth	88.76	high
65	LFM2.5-8B-A1B-GGUF	LiquidAI/LFM2.5-8B-A1B-Base	Mungert	88.76	high
66	Sky-T1-32B-Flash	Qwen/Qwen2.5-32B-Instruct	NovaSky-AI	88.6	medium	Math500
67	NFT-32B	Qwen/Qwen2.5-32B	nvidia	88.4	medium	MATH500
68	ZR1-1.5B-GGUF	deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B	Mungert	88.34	high
69	Youtu-LLM-2B-GGUF	tencent/Youtu-LLM-2B-Base	Mungert	84.8	medium	MATH-500
70	Phi-4-mini-flash-reasoning	microsoft/Phi-4-mini-flash-reasoning	microsoft	84.5	low
71	Nemotron-Labs-TwoTower-30B-A3B-Base-BF16	nvidia/Nemotron-Labs-TwoTower-30B-A3B-Base-BF16	nvidia	84.4	medium	MATH-500 (4-shot)
72	DeepSeek-R1-Distill-Qwen-1.5B	deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B	deepseek-ai	83.9	high
73	DeepSeek-R1-Distill-Qwen-1.5B-GGUF	deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B	unsloth	83.9	high
74	DeepSeek-R1-Distill-Qwen-1.5B-unsloth-bnb-4bit	deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B	unsloth	83.9	high
75	DeepSeek-R1-Distill-Qwen-1.5B-bnb-4bit	deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B	unsloth	83.9	high
76	DeepSeek-R1-Distill-Qwen-1.5B	deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B	unsloth	83.9	high
77	DeepSeek-R1-Distill-Qwen-1.5B-GGUF	deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B	Mungert	83.9	high
78	Falcon-H1-34B-Instruct	tiiuae/Falcon-H1-34B-Base	tiiuae	83.8	medium	MATH-500
79	Falcon-H1-34B-Instruct-GGUF	tiiuae/Falcon-H1-34B-Instruct	tiiuae	83.8	medium	MATH-500
80	Falcon-H1-34B-Instruct-GGUF	tiiuae/Falcon-H1-34B-Instruct	unsloth	83.8	medium	MATH-500
81	Falcon-H1-34B-Instruct-GPTQ-Int4	tiiuae/Falcon-H1-34B-Instruct	tiiuae	83.8	medium	MATH-500
82	NFT-7B	Qwen/Qwen2.5-Math-7B	nvidia	83.2	medium	MATH500
83	AceMath-7B-RM	nvidia/AceMath-7B-RM	nvidia	83.11	low
84	AceMath-72B-RM	nvidia/AceMath-72B-RM	nvidia	83.11	low
85	OpenThinker3-7B-GGUF	Qwen/Qwen2.5-7B-Instruct	Mungert	82.8	low
86	SmallThinker-21BA3B-Instruct-GGUF	—	Mungert	82.4	low
87	Sky-T1-32B-Preview	Qwen/Qwen2.5-32B-Instruct	NovaSky-AI	82.4	medium	Math500
88	AReaL-1.5B-Preview-Stage-2	inclusionAI/AReaL-1.5B-Preview-Stage-2	inclusionAI	81.4	low
89	AReaL-1.5B-Preview-Stage-3	inclusionAI/AReaL-1.5B-Preview-Stage-3	inclusionAI	81.4	low
90	AReaL-1.5B-Preview-Stage-1	inclusionAI/AReaL-1.5B-Preview-Stage-1	inclusionAI	81.4	low
91	Llama-3_1-Nemotron-Ultra-253B-CPT-v1	nvidia/Llama-3_1-Nemotron-Ultra-253B-CPT-v1	nvidia	80.4	medium	MATH500
92	DeepScaleR-1.5B-Preview-unsloth-bnb-4bit	agentica-org/DeepScaleR-1.5B-Preview	unsloth	79.8	low
93	Falcon-H1-1.5B-Deep-Instruct	tiiuae/Falcon-H1-1.5B-Deep-Base	tiiuae	77.8	medium	MATH-500
94	Falcon-H1-1.5B-Deep-Instruct-GGUF	tiiuae/Falcon-H1-1.5B-Deep-Instruct	tiiuae	77.8	medium	MATH-500
95	Falcon-H1-1.5B-Deep-Instruct-GGUF	tiiuae/Falcon-H1-1.5B-Deep-Instruct	unsloth	77.8	medium	MATH-500
96	Falcon-H1-1.5B-Deep-Instruct	tiiuae/Falcon-H1-1.5B-Deep-Instruct	unsloth	77.8	medium	MATH-500
97	Falcon-H1-1.5B-Deep-Instruct-GPTQ-Int4	tiiuae/Falcon-H1-1.5B-Deep-Instruct	tiiuae	77.8	medium	MATH-500
98	Nemotron-H-4B-Instruct-128K	nvidia/Nemotron-H-4B-Base-8K	nvidia	76.4	low
99	LFM2.5-8B-A1B-GGUF	LiquidAI/LFM2.5-8B-A1B	unsloth	74.8	medium	MATH500
100	LFM2.5-8B-A1B	LiquidAI/LFM2.5-8B-A1B	unsloth	74.8	medium	MATH500
101	LFM2.5-8B-A1B-GGUF	LiquidAI/LFM2.5-8B-A1B-Base	Mungert	74.8	medium	MATH500
102	DeepSeek-R1	deepseek-ai/DeepSeek-R1	deepseek-ai	74.6	low
103	DeepSeek-R1-GGUF	deepseek-ai/DeepSeek-R1	unsloth	74.6	low
104	DeepSeek-R1-Zero	deepseek-ai/DeepSeek-R1-Zero	deepseek-ai	74.6	low
105	DeepSeek-R1-BF16	deepseek-ai/DeepSeek-R1	unsloth	74.6	low
106	DeepSeek-R1-GGUF-UD	deepseek-ai/DeepSeek-R1	unsloth	74.6	low
107	DeepSeek-R1-Zero-GGUF	deepseek-ai/DeepSeek-R1-Zero	unsloth	74.6	low
108	DeepSeek-R1	deepseek-ai/DeepSeek-R1	unsloth	74.6	low
109	Falcon-H1-3B-Instruct	tiiuae/Falcon-H1-3B-Base	tiiuae	74.2	medium	MATH-500
110	LFM2-8B-A1B-GGUF	LiquidAI/LFM2-8B-A1B	unsloth	74.2	low
111	Falcon-H1-3B-Instruct-GGUF	tiiuae/Falcon-H1-3B-Base	tiiuae	74.2	medium	MATH-500
112	Falcon-H1-3B-Instruct-GGUF	tiiuae/Falcon-H1-3B-Instruct	unsloth	74.2	medium	MATH-500
113	LFM2-8B-A1B	LiquidAI/LFM2-8B-A1B	unsloth	74.2	low
114	Falcon-H1-1.5B-Instruct	tiiuae/Falcon-H1-1.5B-Base	tiiuae	74.0	medium	MATH-500
115	Falcon-H1-1.5B-Instruct-GGUF	tiiuae/Falcon-H1-1.5B-Instruct	tiiuae	74.0	medium	MATH-500
116	Falcon-H1-1.5B-Instruct-GGUF	tiiuae/Falcon-H1-1.5B-Instruct	unsloth	74.0	medium	MATH-500
117	Falcon-H1-1.5B-Instruct-GPTQ-Int4	tiiuae/Falcon-H1-1.5B-Instruct	tiiuae	74.0	medium	MATH-500
118	Falcon-H1-1.5B-Instruct-GPTQ-Int8	tiiuae/Falcon-H1-1.5B-Instruct	tiiuae	74.0	medium	MATH-500
119	Falcon-H1-7B-Instruct	tiiuae/Falcon-H1-7B-Base	tiiuae	73.4	medium	MATH-500
120	Falcon-H1-7B-Instruct-GPTQ-Int4	tiiuae/Falcon-H1-7B-Instruct	tiiuae	73.4	medium	MATH-500
121	Falcon-H1-7B-Instruct-GGUF	tiiuae/Falcon-H1-7B-Instruct	tiiuae	73.4	medium	MATH-500
122	Falcon-H1-7B-Instruct-GGUF	tiiuae/Falcon-H1-7B-Instruct	unsloth	73.4	medium	MATH-500
123	OREAL-7B	internlm/OREAL-7B-SFT	internlm	72.8	low
124	OREAL-32B	internlm/OREAL-32B-SFT	internlm	72.8	low
125	OREAL-7B-SFT	Qwen/Qwen2.5-7B	internlm	72.8	low
126	OREAL-DeepSeek-R1-Distill-Qwen-7B	deepseek-ai/DeepSeek-R1-Distill-Qwen-7B	internlm	72.8	low
127	GigaChat3-10B-A1.8B-GGUF	ai-sage/GigaChat3-10B-A1.8B-bf16	Mungert	70.0	medium	MATH_500_FOUR_SHOT
128	SynLogic-7B	Qwen/Qwen2.5-7B	MiniMaxAI	64.6	low
129	LFM2.5-1.2B-Thinking-GGUF	LiquidAI/LFM2.5-1.2B-Thinking	unsloth	63.2	low
130	LFM2.5-1.2B-Thinking-GGUF	LiquidAI/LFM2.5-1.2B-Base	Mungert	63.2	low
131	Falcon-H1-0.5B-Instruct	tiiuae/Falcon-H1-0.5B-Base	tiiuae	58.4	medium	MATH-500
132	Falcon-H1-0.5B-Instruct-GGUF	tiiuae/Falcon-H1-0.5B-Base	tiiuae	58.4	medium	MATH-500
133	Falcon-H1-0.5B-Instruct-GGUF	tiiuae/Falcon-H1-0.5B-Instruct	unsloth	58.4	medium	MATH-500
134	Nemotron-H-47B-Base-8K	nvidia/Nemotron-H-56B-Base-8K	nvidia	57.9	low	GSM8K 8-shot CoT \| MATH 4-shot CoT \| MATH-Lvl 5 4-shot CoT \| MATH-500 4-shot CoT
135	Nemotron-H-56B-Base-8K	nvidia/Nemotron-H-56B-Base-8K	nvidia	57.37	low	GSM8K 8-shot CoT \| MATH 4-shot CoT \| MATH-Lvl 5 4-shot CoT \| MATH-500 4-shot CoT
136	NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16	nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16	nvidia	55.08	medium	MATH-500 (4-shot, avg@32)
137	Nemotron-H-8B-Base-8K	nvidia/Nemotron-H-8B-Base-8K	nvidia	44.43	low	GSM8K 8-shot CoT \| MATH 4-shot CoT \| MATH-Lvl 5 4-shot CoT \| MATH-500 4-shot CoT
138	Llama-3.2-3B-F1-Reasoning-Instruct-GGUF	meta-llama/Llama-3.2-3B	Mungert	44.4	low
139	bitnet-b1.58-2B-4T-gguf	microsoft/bitnet-b1.58-2B-4T-bf16	microsoft	23.0	medium	MATH-500
140	bitnet-b1.58-2B-4T	microsoft/bitnet-b1.58-2B-4T	microsoft	23.0	medium	MATH-500
141	bitnet-b1.58-2B-4T-bf16	microsoft/bitnet-b1.58-2B-4T-bf16	microsoft	23.0	medium	MATH-500