Coding

LiveCodeBench leaderboard

Name: benchgap: LLM benchmark scores, measured and estimated
Creator: benchgap

As of 2026-10-07, the highest measured score on LiveCodeBench is 91.6% by Qwen3.7 Max. 140 more models have estimated scores, calibrated from the benchmarks they were measured on.

Measured scores: benchlm.ai.

#	Model	Score	Source
1	Apodex 1.1	100.0%	estimated ± 8.9 pp, low confidence
2	Apodex 1.1 Mini	100.0%	estimated ± 8.9 pp, low confidence
3	Claude Fable 5	100.0%	estimated ± 8.9 pp, low confidence
4	Claude Fable 5.1	100.0%	estimated ± 8.9 pp, low confidence
5	Claude Opus 4.7 (Adaptive)	100.0%	estimated ± 8.9 pp, low confidence
6	Claude Opus 4.8	100.0%	estimated ± 8.9 pp, low confidence
7	Claude Opus 5	100.0%	estimated ± 8.9 pp, low confidence
8	Claude Sonnet 5	100.0%	estimated ± 8.9 pp, low confidence
9	DeepSeek V4 Flash 0731	100.0%	estimated ± 8.9 pp, low confidence
10	DeepSeek V4 Pro 0813	100.0%	estimated ± 8.9 pp, low confidence
11	Gemini 3.1 Pro	100.0%	estimated ± 8.9 pp, low confidence
12	Gemini 3.5 Flash	100.0%	estimated ± 8.9 pp, low confidence
13	Gemini 3.6 Flash	100.0%	estimated ± 8.9 pp, low confidence
14	Gemini 3.7 Flash	100.0%	estimated ± 8.9 pp, low confidence
15	Gemini 3.8 Flash	100.0%	estimated ± 8.9 pp, low confidence
16	GLM-5.1	100.0%	estimated ± 8.9 pp, low confidence
17	GLM-5.2	100.0%	estimated ± 8.9 pp, low confidence
18	GLM-5.3	100.0%	estimated ± 8.9 pp, low confidence
19	GPT-5.4	100.0%	estimated ± 8.9 pp, low confidence
20	GPT-5.4 mini	100.0%	estimated ± 8.9 pp, low confidence
21	GPT-5.4 nano	100.0%	estimated ± 8.9 pp, low confidence
22	GPT-5.5	100.0%	estimated ± 8.9 pp, low confidence
23	GPT-5.6 Luna	100.0%	estimated ± 8.9 pp, low confidence
24	GPT-5.6 Sol	100.0%	estimated ± 8.9 pp, low confidence
25	GPT-5.6 Terra	100.0%	estimated ± 8.9 pp, low confidence
26	GPT-6 Astra	100.0%	estimated ± 8.9 pp, low confidence
27	Grok 4.5	100.0%	estimated ± 8.9 pp, low confidence
28	Grok 4.6	100.0%	estimated ± 8.9 pp, low confidence
29	Hy3	100.0%	estimated ± 8.9 pp, low confidence
30	Hy3 Preview	100.0%	estimated ± 8.9 pp, low confidence
31	Inkling	100.0%	estimated ± 8.9 pp, low confidence
32	Inkling-Small	100.0%	estimated ± 8.9 pp, low confidence
33	Kimi K2.6	100.0%	estimated ± 8.9 pp, low confidence
34	Kimi K2.7 Code	100.0%	estimated ± 8.9 pp, low confidence
35	Kimi K3	100.0%	estimated ± 8.9 pp, low confidence
36	Ling 3.0 Flash	100.0%	estimated ± 8.9 pp, low confidence
37	Ling 3.0 Flash FP8	100.0%	estimated ± 8.9 pp, low confidence
38	MiMo-V2.5-Pro	100.0%	estimated ± 8.9 pp, low confidence
39	MiniMax M2.7	100.0%	estimated ± 8.9 pp, low confidence
40	MiniMax M3	100.0%	estimated ± 8.9 pp, low confidence
41	Muse Spark	100.0%	estimated ± 8.9 pp, low confidence
42	Muse Spark 1.1	100.0%	estimated ± 8.9 pp, low confidence
43	Muse Spark 1.2	100.0%	estimated ± 8.9 pp, low confidence
44	Muse Spark 1.3	100.0%	estimated ± 8.9 pp, low confidence
45	Quasar 438B	100.0%	estimated ± 8.9 pp, low confidence
46	Qwen3.6 Plus	100.0%	estimated ± 8.9 pp, low confidence
47	Qwen3.8-27B	100.0%	estimated ± 8.9 pp, low confidence
48	Qwen3.8-Flash-Next	100.0%	estimated ± 8.9 pp, low confidence
49	Qwen3.8 Max Preview	100.0%	estimated ± 8.9 pp, low confidence
50	MiMo-V2-Flash	98.4%	estimated ± 8.9 pp, low confidence
51	GPT-5.1	97.2%	estimated ± 8.9 pp, low confidence
52	Gemini 3.5 Flash-Lite	97.1%	estimated ± 8.9 pp, low confidence
53	Nemotron 3 Ultra	96.9%	estimated ± 8.9 pp, low confidence
54	Muse Glimmer 30B	96.2%	estimated ± 8.9 pp, low confidence
55	Claude Mythos 5	95.3%	estimated ± 10.2 pp, low confidence
56	Ember-1	93.5%	estimated ± 10.2 pp, low confidence
57	Qwen3.7 Max	91.6%	measured
58	Mistral Medium 3.5 128B	90.8%	estimated ± 8.9 pp, low confidence
59	Kimi K2.5	90.5%	estimated ± 8.9 pp, low confidence
60	Kimi K2.5 (Reasoning)	90.5%	estimated ± 8.9 pp, low confidence
61	Ornith-1.5-397B	90.1%	estimated ± 10.2 pp, low confidence
62	Qwen3.7 Plus	89.6%	measured
63	GPT-5.3 Codex	89.5%	estimated ± 10.2 pp, low confidence
64	Ornith-1.0-397B	87.9%	estimated ± 10.2 pp, low confidence
65	Solar Pro 4	87.8%	measured
66	Qwen3.5-122B-A10B	87.7%	estimated ± 8.9 pp, low confidence
67	Claude Opus 4.5	87.0%	estimated ± 10.2 pp, low confidence
68	Beam	87.0%	estimated ± 10.2 pp, low confidence
69	Claude Opus 4.6	87.0%	estimated ± 10.2 pp, low confidence
70	GPT-5.2	86.5%	estimated ± 10.2 pp, low confidence
71	Claude Sonnet 4.6	86.2%	estimated ± 10.2 pp, low confidence
72	Ornith-1.5-35B-A3B	85.9%	estimated ± 10.2 pp, low confidence
73	BTL-4	85.5%	estimated ± 10.2 pp, low confidence
74	dots3-note Preview	85.5%	estimated ± 10.2 pp, low confidence
75	MiMo-V2-Pro	85.2%	estimated ± 10.2 pp, low confidence
76	GLM-5	85.1%	estimated ± 10.2 pp, low confidence
77	GLM-4.7	84.9%	measured
78	Claude Sonnet 4.5	84.7%	estimated ± 10.2 pp, low confidence
79	Grok 4.20	84.4%	estimated ± 10.2 pp, low confidence
80	Qwen3.5 397B	84.1%	estimated ± 10.2 pp, low confidence
81	Qwen3.6-27B	83.9%	measured
82	Ornith-1.0-35B	83.7%	estimated ± 10.2 pp, low confidence
83	MiMo-V2-Omni	83.2%	estimated ± 10.2 pp, low confidence
84	Laguna M.1	83.1%	estimated ± 10.2 pp, low confidence
85	Claude 4.1 Opus	83.0%	estimated ± 10.2 pp, low confidence
86	MAI-Thinking-1	82.4%	estimated ± 10.2 pp, low confidence
87	Claude Haiku 4.5	82.2%	estimated ± 10.2 pp, low confidence
88	Gemma 4 31B	82.1%	estimated ± 8.9 pp, low confidence
89	Claude 4 Sonnet	81.8%	estimated ± 10.2 pp, low confidence
90	MAI-Code-1.1-Flash	81.8%	estimated ± 10.2 pp, low confidence
91	Qwen3.5-27B	81.6%	estimated ± 10.2 pp, low confidence
92	Laguna XS 2.1	80.6%	estimated ± 10.2 pp, low confidence
93	Grok Code Fast 1	80.5%	estimated ± 10.2 pp, low confidence
94	Ornith-1.5-9B	80.4%	estimated ± 10.2 pp, low confidence
95	Qwen3.6-35B-A3B	80.4%	measured
96	Solar Open 2	80.3%	estimated ± 10.2 pp, low confidence
97	Laguna XS.2	79.9%	estimated ± 10.2 pp, low confidence
98	Ornith-1.0-9B	79.6%	estimated ± 10.2 pp, low confidence
99	Qwen3.5-35B-A3B	79.4%	estimated ± 10.2 pp, low confidence
100	Grok 4.3	79.2%	estimated ± 8.9 pp, low confidence
101	K-EXAONE 2.0	78.8%	estimated ± 10.2 pp, low confidence
102	LongCat-Flash-Lite-Sparse	78.8%	estimated ± 10.2 pp, low confidence
103	Ternary Bonsai 2 27B	73.3%	estimated ± 10.2 pp, low confidence
104	o1	73.2%	estimated ± 8.9 pp, low confidence
105	Step 3.7 Flash	72.9%	estimated ± 8.9 pp, low confidence
106	Gemma 4 26B A4B	72.3%	estimated ± 8.9 pp, low confidence
107	Granite 4.2 30B	70.4%	estimated ± 10.2 pp, low confidence
108	GPT-5 (high)	68.7%	estimated ± 8.9 pp, low confidence
109	Nemotron 3 Super 100B	68.6%	estimated ± 8.9 pp, low confidence
110	GPT-4.1	68.4%	estimated ± 10.2 pp, low confidence
111	ZAYA1-74B-Preview	67.3%	estimated ± 10.2 pp, low confidence
112	o3-mini	63.9%	estimated ± 10.2 pp, low confidence
113	LLaDA2.2-flash	63.9%	estimated ± 10.2 pp, low confidence
114	Claude 3.5 Sonnet	63.6%	estimated ± 10.2 pp, low confidence
115	MiniCPM5-2B	61.3%	estimated ± 10.2 pp, low confidence
116	o1-preview	60.4%	estimated ± 8.9 pp, low confidence
117	Gemini 2.5 Pro	58.7%	estimated ± 8.9 pp, low confidence
118	K-Exaone	56.3%	estimated ± 8.9 pp, low confidence
119	Gemma 4 12B	53.8%	estimated ± 8.9 pp, low confidence
120	GPT-OSS 120B	52.7%	estimated ± 8.9 pp, low confidence
121	Command A+	47.4%	estimated ± 8.9 pp, low confidence
122	Nemotron 3.5 Lightning 30B A3B NVFP4	45.2%	estimated ± 8.9 pp, low confidence
123	Mistral Small 4	45.0%	estimated ± 8.9 pp, low confidence
124	Mistral Small 4 (Reasoning)	45.0%	estimated ± 8.9 pp, low confidence
125	Trinity-Large-Preview	43.3%	estimated ± 8.9 pp, low confidence
126	Trinity-Large-Thinking	43.3%	estimated ± 8.9 pp, low confidence
127	Ling 2.6 Flash	42.2%	estimated ± 8.9 pp, low confidence
128	Gemini 1.5 Pro	39.1%	estimated ± 8.9 pp, low confidence
129	DeepSeek V3	37.6%	measured
130	Granite 4.2 8B	36.7%	estimated ± 8.9 pp, low confidence
131	GPT-4 Turbo	35.0%	estimated ± 8.9 pp, low confidence
132	GPT-OSS 20B	33.5%	estimated ± 8.9 pp, low confidence
133	GPT-4.1 mini	32.6%	estimated ± 8.9 pp, low confidence
134	Mistral Large 3	32.3%	estimated ± 8.9 pp, low confidence
135	Claude 3 Opus	31.3%	estimated ± 8.9 pp, low confidence
136	Llama 4 Maverick	25.5%	estimated ± 8.9 pp, low confidence
137	Celeris-1	22.1%	estimated ± 8.9 pp, low confidence
138	Nemotron 3 Nano 30B	22.1%	estimated ± 8.9 pp, low confidence
139	Nemotron 3 Nano Omni 30B A3B	21.0%	estimated ± 8.9 pp, low confidence
140	Ultravox v0.6 Llama 3.3 70B	17.9%	estimated ± 8.9 pp, low confidence
141	GPT-4o mini	17.0%	estimated ± 8.9 pp, low confidence
142	GPT-4.1 nano	16.6%	estimated ± 8.9 pp, low confidence
143	Gemma 3 27B	14.7%	estimated ± 8.9 pp, low confidence
144	Gemma 4 E4B	13.6%	estimated ± 8.9 pp, low confidence
145	Llama 4 Scout	11.6%	estimated ± 8.9 pp, low confidence
146	LFM2.5-2.6B	10.9%	estimated ± 8.9 pp, low confidence
147	Gemma 4 E2B	10.1%	estimated ± 8.9 pp, low confidence

LiveCodeBench leaderboard

All leaderboards

Agentic · terminal

Agentic · tools

Coding

Math

Knowledge & reasoning

Instruction following

Multilingual

Vision & documents

Long context

General