LiveCodeBench

LiveCodeBench - Benchmark Leaderboard & Model Performance | AI Stats

Models Using This Benchmark

Organisation	Model	Reported	Top Score	Info	Self Reported	Source
DeepSeek	DeepSeek V3.2 Speciale	01 Dec 2025	88.70%	-	Yes	Source
MiniMax	MiniMax M2 Her	24 Jan 2026	83%	inferred modality/version alias from minimax-m2	Yes	-
MiniMax	MiniMax M2	27 Oct 2025	83%	-	Yes	-
Nvidia	Nemotron 3 Super	11 Mar 2026	81.19%	-	Yes	Source
xAI	Grok 3 Mini	18 Apr 2025	80.40%	-	Yes	Source
xAI	Grok 4 Heavy	10 Jul 2025	79.40%	-	Yes	Source
xAI	Grok 3	18 Apr 2025	79.40%	-	Yes	Source
xAI	Grok 4	10 Jul 2025	79%	-	Yes	Source
MiniMax	MiniMax M2.1	23 Dec 2025	78%	-	Yes	Source
DeepSeek	Deepseek V3.2 Exp	29 Sept 2025	74.10%	-	Yes	Source
DeepSeek	DeepSeek OCR 2	-	74.10%	inferred family alias from deepseek-v3.2-exp (score=0.3809; benches=14)	Yes	Source
z.AI	GLM 4.5	28 Jul 2025	72.90%	-	Yes	Source
Google	Gemini 3.1 Flash Lite Preview	03 Mar 2026	72%	-	Yes	Source
Nvidia	Nvidia Nemotron Nano 9B V2	-	71.10%	-	Yes	Source
Nvidia	Nvidia Nemotron Nano 12B V2	-	71.10%	inferred high-confidence family alias from nvidia-nemotron-nano-9b-v2 (score=0.4889; benches=6)	Yes	Source
Qwen	Qwen 3 235B A22B	-	70.70%	-	Yes	Source
z.AI	GLM 4.5 Air	28 Jul 2025	70.70%	-	Yes	Source
Google	Gemini 2.5 Pro Preview TTS (2025-05-20)	20 May 2025	69%	inferred family alias from gemini-2.5-pro-preview-06-05 (score=0.4243; benches=13)	Yes	Source
Inception	Mercury 2	24 Feb 2026	67%	-	Yes	Source
Nvidia	Llama 3.1 Nemotron Ultra 253B v1	07 Apr 2025	66.31%	-	Yes	Source
Qwen	Qwen 3 32B	-	65.70%	-	Yes	Source
MiniMax	MiniMax M1 80K	16 Jun 2025	65%	-	Yes	-
Mistral	Ministral 3.0 14B	02 Dec 2025	64.60%	-	Yes	Source
Mistral	Mistral Small 1.0	26 Feb 2024	63.60%	inferred family alias from mistral-small-latest (score=0.3650; benches=9)	Yes	Source
Mistral	Mistral Small 2.0	17 Sept 2024	63.60%	inferred family alias from mistral-small-latest (score=0.3650; benches=9)	Yes	Source
Mistral	Mistral Small Creative	16 Dec 2025	63.60%	inferred family alias from mistral-small-latest (score=0.4273; benches=9)	Yes	Source
Mistral	Mistral Small 4	16 Mar 2026	63.60%	-	Yes	Source
Qwen	QwQ 32B	-	63.40%	-	Yes	Source
Qwen	Qwen 3 30B A3B Thinking 2507	-	62.60%	inferred version-family alias from qwen3-30b-a3b	Yes	Source
Qwen	Qwen 3 Omni 30B A3B Captioner	-	62.60%	inferred family alias from qwen3-30b-a3b (score=0.4129; benches=8)	Yes	Source
Qwen	Qwen 3 30B A3B Instruct 2507	-	62.60%	inferred version-family alias from qwen3-30b-a3b	Yes	Source
Qwen	Qwen 3 Omni 30B A3B Thinking	-	62.60%	inferred high-confidence family alias from qwen3-30b-a3b (score=0.4819; benches=8)	Yes	Source
Qwen	Qwen 3 Coder 30B A3B Instruct	-	62.60%	inferred high-confidence family alias from qwen3-30b-a3b (score=0.5007; benches=8)	Yes	Source
Qwen	Qwen 3 Omni 30B A3B Instruct	-	62.60%	inferred high-confidence family alias from qwen3-30b-a3b (score=0.4819; benches=8)	Yes	Source
Qwen	Qwen 3 30B A3B	-	62.60%	-	Yes	Source
MiniMax	Minimax M1 40K	16 Jun 2025	62.30%	-	Yes	-
Mistral	Ministral 8B	09 Oct 2024	61.60%	inferred alias from ministral-8b-latest	Yes	Source
Mistral	Ministral 3.0 8B	02 Dec 2025	61.60%	-	Yes	Source
DeepSeek	DeepSeek V3.1	21 Aug 2025	56.40%	Non-thinking: 56.4%, Thinking: 74.8%	Yes	Source
DeepSeek	DeepSeek V3.1 Terminus	22 Sept 2025	56.40%	inferred alias from deepseek-v3.1	Yes	Source
Qwen	Qwen 72B	-	55.50%	inferred family alias from qwen-2.5-72b-instruct (score=0.3060; benches=14)	Yes	Source
Mistral	Ministral 3B	09 Oct 2024	54.80%	inferred alias from ministral-3b-latest	Yes	Source
Mistral	Ministral 3.0 3B	02 Dec 2025	54.80%	-	Yes	Source
Microsoft	Phi 4 Reasoning	30 Apr 2025	53.80%	-	Yes	Source
Microsoft	Phi 4 Reasoning Plus	30 Apr 2025	53.10%	-	Yes	Source
Mistral	Magistral Small 1.2	17 Sept 2025	51.30%	inferred version-family alias from magistral-small-2506	Yes	Source
Mistral	Magistral Small 1.1	24 Jul 2025	51.30%	inferred version-family alias from magistral-small-2506	Yes	Source
Mistral	Magistral Medium 1.2	17 Sept 2025	50.30%	inferred version-family alias from magistral-medium	Yes	Source
Mistral	Magistral Medium 1.1	24 Jul 2025	50.30%	inferred version-family alias from magistral-medium	Yes	Source
Qwen	QwQ 32B Preview	-	50%	-	Yes	Source
Meituan	Longcat Flash Cat	-	48.02%	inferred high-confidence family alias from longcat-flash-chat (score=0.4667; benches=16)	Yes	Source
Meta	Llama 4 Maverick	05 Apr 2025	43.40%	-	Yes	Source
DeepSeek	DeepSeek V2 (2024-06-28)	28 Jun 2024	37.60%	inferred family alias from deepseek-v3 (score=0.4159; benches=20)	Yes	Source
DeepSeek	DeepSeek OCR	20 Oct 2025	37.60%	inferred family alias from deepseek-v3 (score=0.3000; benches=20)	Yes	Source
DeepSeek	DeepSeek V4	-	37.60%	inferred high-confidence family alias from deepseek-v3 (score=0.5818; benches=20)	Yes	Source
Google	LearnLM 2.0 Flash Experimental	17 Apr 2025	35.10%	inferred family alias from gemini-2.0-flash (score=0.3700; benches=13)	Yes	Source
Google	Gemini 2.0 Flash Exp	-	35.10%	inferred alias from gemini-2.0-flash	Yes	Source
Google	Gemini 2.0 Pro Exp (2025-02-05)	05 Feb 2025	35.10%	inferred modality/version alias from gemini-2.0-flash	Yes	Source
Google	Gemini 2.0 Flash	05 Feb 2025	35.10%	-	Yes	Source
Mistral	Mistral Large 1.0	26 Feb 2024	34.40%	inferred family alias from mistral-large-latest (score=0.3650; benches=5)	Yes	Source
Google	Gemini 2.5 Flash Lite Preview (2025-09-25)	25 Sept 2025	33.70%	inferred alias from gemini-2.5-flash-lite	Yes	Source
Meta	Llama 4 Scout	05 Apr 2025	32.80%	-	Yes	Source
Google	Gemini Diffusion	20 May 2025	30.90%	-	Yes	Source
Qwen	Qwen 7B	-	28.70%	inferred family alias from qwen-2.5-7b-instruct (score=0.3083; benches=14)	Yes	Source
Qwen	Qwen 2 Math 7B	-	26.60%	inferred high-confidence family alias from qwen2-7b-instruct (score=0.4706; benches=14)	Yes	Source
Qwen	Qwen 2 Audio 7B	-	26.60%	inferred modality/version alias from qwen2-7b-instruct	Yes	Source

Recorded Results

Average Score

Score Range

Leading Model

Models Using This Benchmark