LiveCodeBench V6

LiveCodeBench V6 - Benchmark Leaderboard & Model Performance | AI Stats

Models Using This Benchmark

Organisation	Model	Reported	Top Score	Info	Self Reported	Source
ByteDance	Seed 2.0 Pro	14 Feb 2026	87.80%	-	Yes	Source
Qwen	Qwen 3.6 Plus	01 Apr 2026	87.10%	-	Yes	Source
StepFun	Step 3.5 Flash	-	86.40%	-	Yes	Source
Moonshot	Kimi K2.5	27 Jan 2026	85%	-	Yes	Source
z.AI	GLM 4.7	22 Dec 2025	84.90%	-	Yes	Source
Qwen	Qwen 3.5 397B A17B	16 Feb 2026	83.60%	-	Yes	Source
Moonshot	Kimi K2 Thinking	06 Nov 2025	83.10%	inferred alias from kimi-k2-thinking-0905	Yes	Source
z.AI	GLM 4.6	30 Sept 2025	82.80%	-	Yes	Source
ByteDance	Seed 2.0 Lite	14 Feb 2026	81.70%	Seed2 official benchmark table \| LiveCodeBench (v6)	Yes	Source
LG	K EXAONE	31 Dec 2025	80.70%	inferred modality/version alias from k-exaone-236b-a23b	Yes	Source
Qwen	Qwen 3.5 27B	24 Feb 2026	80.70%	-	Yes	Source
Qwen	Qwen 3.5 Flash	23 Feb 2026	80.70%	inferred family alias from qwen3.5-27b (score=0.4147; benches=81)	Yes	Source
Xiaomi	MiMo V2 Flash	16 Dec 2025	80.60%	-	Yes	Source
Google	Gemma 4 31B	02 Apr 2026	80%	-	Yes	Source
Qwen	Qwen 3.5 122B A10B	24 Feb 2026	78.90%	-	Yes	Source
Google	Gemma 4 26B A4B	02 Apr 2026	77.10%	-	Yes	Source
Qwen	Qwen 3.5 35B A3B	24 Feb 2026	74.60%	-	Yes	Source
Qwen	Qwen 3 235B A22B Thinking 2507	-	74.10%	-	Yes	Source
Qwen	Qwen 3 VL 235B A22B Thinking	-	70.10%	-	Yes	-
Qwen	Qwen 3 14B	-	69%	inferred family alias from qwen3-max (score=0.3333; benches=6)	Yes	Source
Qwen	Qwen 3 TTS (2025-11-27)	-	69%	inferred family alias from qwen3-max (score=0.3833; benches=6)	Yes	Source
Qwen	Qwen 3 Max Thinking	26 Jan 2026	69%	inferred alias from qwen3-max	Yes	Source
Qwen	Qwen 3 Next 80B A3B Thinking	-	68.70%	-	Yes	Source
Nvidia	Nemotron Nano 3 30B A3B	15 Dec 2025	68.30%	-	Yes	Source
LG	EXAONE 4.0 32B	15 Jul 2025	66.70%	Reasoning	Yes	Source
Qwen	Qwen 3 VL 32B Thinking	-	65.60%	-	Yes	-
Qwen	Qwen 3.5 9B	02 Mar 2026	65.60%	-	Yes	Source
Qwen	Qwen 3 VL 30B A3B Thinking	-	64.20%	-	Yes	-
ByteDance	Seed 2.0 Mini	14 Feb 2026	64.10%	Seed2 official benchmark table \| LiveCodeBench (v6)	Yes	Source
Qwen	Qwen 3 8B	-	58.60%	inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.4600; benches=50)	Yes	-
Qwen	Qwen 3 Guard Stream 8B	-	58.60%	inferred family alias from qwen3-vl-8b-thinking (score=0.3371; benches=50)	Yes	-
Qwen	Qwen 3 VL Reranker 8B	-	58.60%	inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5275; benches=50)	Yes	-
Qwen	Qwen 3 Embedding 8B	-	58.60%	inferred family alias from qwen3-vl-8b-thinking (score=0.3850; benches=50)	Yes	-
Qwen	Qwen 3 Guard Gen 8B	-	58.60%	inferred family alias from qwen3-vl-8b-thinking (score=0.3400; benches=50)	Yes	-
Qwen	Qwen 3 Reranker 8B	-	58.60%	inferred family alias from qwen3-vl-8b-thinking (score=0.3850; benches=50)	Yes	-
Qwen	Qwen 3 VL Embedding 8B	-	58.60%	inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5232; benches=50)	Yes	-
Qwen	Qwen 3 VL 8B Thinking	-	58.60%	-	Yes	-
Qwen	Qwen 3 Next 80B A3B Instruct	-	56.60%	-	Yes	Source
Qwen	Qwen 3.5 4B	02 Mar 2026	55.80%	-	Yes	Source
Qwen	Qwen 3 VL 235B A22B Instruct	-	54.30%	-	Yes	-
Moonshot	Kimi K2 (2025-09-05)	05 Sept 2025	53.70%	Pass@1, Aug 24 - May 25	Yes	Source
Qwen	Qwen 3 A235 A22B Instruct 2507	-	51.80%	-	Yes	Source
Qwen	Qwen 3 Guard Gen 4B	-	51.30%	inferred family alias from qwen3-vl-4b-thinking (score=0.3400; benches=48)	Yes	-
Qwen	Qwen 3 Reranker 4B	-	51.30%	inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48)	Yes	-
Qwen	Qwen 3 4B SafeRL	-	51.30%	inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48)	Yes	-
Qwen	Qwen 3 VL 4B Thinking	-	51.30%	-	Yes	-
Qwen	Qwen 3 Guard Stream 4B	-	51.30%	inferred family alias from qwen3-vl-4b-thinking (score=0.3371; benches=48)	Yes	-
Qwen	Qwen 3 Embedding 4B	-	51.30%	inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48)	Yes	-
Qwen	Qwen 3 4B Thinking 2507	-	51.30%	inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48)	Yes	-
Qwen	Qwen 3 4B Instruct 2507	-	51.30%	inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48)	Yes	-
LG	EXAONE 4.0 1.2B	15 Jul 2025	45.30%	Reasoning	Yes	Source
Qwen	Qwen 3 VL 32B Instruct	-	43.80%	-	Yes	-
Qwen	Qwen 3 VL 30B A3B Instruct	-	42.60%	-	Yes	-
Qwen	Qwen 3 VL 8B Instruct	-	39.30%	-	Yes	-
Qwen	Qwen 3 VL 4B Instruct	-	37.90%	-	Yes	-
Moonshot	Kimi K2 (2025-07-11)	11 Jul 2025	26.30%	Pass@1	Yes	Source

Recorded Results

Average Score

Score Range

Leading Model

Models Using This Benchmark