Coding

FrontierCode 1.1 Main leaderboard

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

As of 2026-10-07, the highest measured score on FrontierCode 1.1 Main is 54.4% by Claude Opus 5.5. 190 more models have estimated scores, calibrated from the benchmarks they were measured on.

Measured scores: benchlm.ai.

#	Model	Score	Source
1	Claude Fable 5.1	57.9%	estimated ± 1.6 pp, low confidence
2	Muse Spark 1.3	54.9%	estimated ± 3.7 pp, low confidence
3	Grok 4.6	54.7%	estimated ± 1.6 pp, low confidence
4	Claude Opus 5.5	54.4%	measured
5	Gemini 4 Argon	53.8%	estimated ± 2.8 pp, medium confidence
6	DeepSeek V4.1 Flash	53.5%	estimated ± 3.7 pp, low confidence
7	Claude Fable 5	53.5%	measured
8	Claude Opus 5	53.4%	measured
9	GPT-6 Astra	53.3%	measured
10	Pareto 26.9	53.3%	estimated ± 3.7 pp, low confidence
11	Claude Mythos 5	53.2%	estimated ± 2.7 pp, medium confidence
12	Gemini 3.8 Flash	52.8%	estimated ± 1.6 pp, medium confidence
13	Ember-1	51.6%	estimated ± 2.7 pp, medium confidence
14	GPT-6.1 Sol	50.9%	estimated ± 3.7 pp, low confidence
15	MiMo-V2.6-Pro	50.9%	estimated ± 3.7 pp, low confidence
16	GPT-5.6 Sol	50.5%	estimated ± 1.6 pp, medium confidence
17	SWE-2	50.0%	measured
18	Grok 4.7	49.9%	estimated ± 3.7 pp, low confidence
19	Grok 4.5	49.9%	estimated ± 1.6 pp, medium confidence
20	Pareto 26.10 Preview	48.8%	estimated ± 3.7 pp, low confidence
21	GPT-5.6 Terra	47.9%	estimated ± 1.6 pp, medium confidence
22	Mistral Large 4	47.7%	estimated ± 4.3 pp, low confidence
23	GPT-6 Sol	47.6%	estimated ± 3.7 pp, low confidence
24	Sakana Fugu-Ultra	47.1%	estimated ± 5.5 pp, medium confidence
25	MiMo-V2.6-Flash	46.6%	estimated ± 3.7 pp, low confidence
26	Claude Opus 4.8	46.5%	measured
27	Step 5 Preview	46.4%	estimated ± 3.7 pp, low confidence
28	Claude Haiku 5.5	46.4%	measured
29	Claude Opus 4.7 (Adaptive)	46.3%	estimated ± 2.7 pp, medium confidence
30	Claude Sonnet 5.5	46.2%	measured
31	GLM-5.3	45.6%	estimated ± 3.7 pp, low confidence
32	GPT-6 Luna	45.3%	estimated ± 3.7 pp, low confidence
33	GPT-5.6 Luna	43.9%	estimated ± 1.6 pp, medium confidence
34	Gemini 3.7 Flash	43.6%	measured
35	Kimi K3	43.6%	estimated ± 1.6 pp, medium confidence
36	Ornith-1.5-397B	43.1%	estimated ± 2.7 pp, medium confidence
37	Hy4 preview	43.0%	estimated ± 3.7 pp, low confidence
38	GPT-5.5	43.0%	measured
39	Claude Sonnet 5	42.7%	measured
40	Ling 3.1 Flash	42.7%	estimated ± 6.6 pp, medium confidence
41	Qwen3.8 Max Preview	42.6%	estimated ± 3.8 pp, high confidence
42	SWE-1.7	42.3%	measured
43	GLM-5.3-Flash	42.1%	estimated ± 3.7 pp, low confidence
44	Gemini 3.1 Pro	40.7%	estimated ± 2.8 pp, low confidence
45	GPT-5.4	40.7%	estimated ± 2.8 pp, low confidence
46	GPT-5.3 Codex	40.7%	estimated ± 2.7 pp, medium confidence
47	Atria Dawn Preview	39.9%	estimated ± 5.5 pp, medium confidence
48	Sakana Fugu	39.6%	estimated ± 5.5 pp, medium confidence
49	Composer 2.5	38.9%	estimated ± 1.6 pp, low confidence
50	Claude Opus 4.7	38.5%	measured
51	Muse Spark 1.2	38.2%	estimated ± 3.7 pp, low confidence
52	GLM-5.2	37.9%	estimated ± 1.6 pp, low confidence
53	Qwen3.8-Flash-Next	37.7%	estimated ± 3.7 pp, low confidence
54	Qwen3.8-Omni-Flash	36.9%	estimated ± 3.7 pp, low confidence
55	Gemini 3.6 Flash	36.5%	estimated ± 1.6 pp, low confidence
56	Qwen3.8 Max	35.8%	estimated ± 3.7 pp, low confidence
57	Ornith-1.0-397B	33.1%	estimated ± 2.7 pp, medium confidence
58	Kimi K2.7 Code	33.0%	estimated ± 1.6 pp, low confidence
59	Muse Spark 1.1	33.0%	estimated ± 3.7 pp, low confidence
60	Gemini 3.5 Flash	32.2%	estimated ± 1.6 pp, low confidence
61	Quasar 438B	30.4%	estimated ± 3.8 pp, high confidence
62	Apodex 1.1 Mini	30.0%	estimated ± 3.8 pp, high confidence
63	MiMo-V2.5-Pro	29.4%	estimated ± 3.8 pp, high confidence
64	Hy3	28.2%	estimated ± 3.8 pp, high confidence
65	Claude Opus 4.5	28.1%	estimated ± 2.7 pp, medium confidence
66	Beam	28.1%	estimated ± 2.7 pp, medium confidence
67	Qwen 3.6 Max (preview)	27.6%	estimated ± 5.2 pp, low confidence
68	DeepSeek V4 Pro 0813	27.1%	estimated ± 2.7 pp, medium confidence
69	Claude Opus 4.6 (Adaptive)	27.0%	estimated ± 4.3 pp, medium confidence
70	GPT-5.4 mini	27.0%	measured
71	Claude Opus 4.6	26.9%	measured
72	MiniMax M3	26.8%	estimated ± 2.7 pp, medium confidence
73	Qwen3.7 Max	26.5%	estimated ± 2.7 pp, medium confidence
74	GPT-5.4 nano	25.8%	estimated ± 3.8 pp, medium confidence
75	Inkling-Small	25.8%	estimated ± 2.7 pp, medium confidence
76	Kimi K2.6	25.8%	estimated ± 2.7 pp, medium confidence
77	GLM-5.1	25.6%	estimated ± 3.8 pp, medium confidence
78	MiMo-V2.5	25.1%	estimated ± 5.2 pp, low confidence
79	GPT-5.2	25.1%	estimated ± 2.7 pp, medium confidence
80	Claude Sonnet 4.6	24.3%	measured
81	Qwen3.8-27B	24.3%	estimated ± 3.7 pp, low confidence
82	MiniMax M2.7	23.1%	estimated ± 3.8 pp, medium confidence
83	Laguna S 2.1	23.0%	estimated ± 3.7 pp, low confidence
84	DeepSeek V4 Flash 0731	21.8%	estimated ± 2.7 pp, low confidence
85	Ornith-1.5-35B-A3B	21.8%	estimated ± 2.7 pp, low confidence
86	Ling 3.0 Flash	21.6%	estimated ± 3.8 pp, medium confidence
87	Ling 3.0 Flash FP8	21.6%	estimated ± 3.8 pp, medium confidence
88	Qwen3.6 Plus	21.1%	estimated ± 2.7 pp, low confidence
89	GPT-5.1	20.8%	estimated ± 3.8 pp, medium confidence
90	Gemini 3.5 Flash-Lite	20.7%	estimated ± 3.8 pp, medium confidence
91	BTL-4	19.9%	estimated ± 2.7 pp, low confidence
92	dots3-note Preview	19.9%	estimated ± 2.7 pp, low confidence
93	MiMo-V2-Pro	18.6%	estimated ± 2.7 pp, low confidence
94	GLM-5	18.0%	estimated ± 2.7 pp, low confidence
95	Apodex 1.1	17.7%	estimated ± 2.7 pp, low confidence
96	Qwen3.7 Plus	17.7%	estimated ± 2.7 pp, low confidence
97	Inkling	17.4%	estimated ± 2.7 pp, low confidence
98	Mistral Medium 3.5 128B	17.4%	estimated ± 2.7 pp, low confidence
99	GPT-5.2-Codex	17.3%	estimated ± 4.3 pp, low confidence
100	Gemma 4 31B	16.9%	estimated ± 3.8 pp, medium confidence
101	Muse Spark	16.8%	estimated ± 2.7 pp, low confidence
102	Qwen3.5 Flash	16.6%	estimated ± 5.2 pp, low confidence
103	Claude Sonnet 4.5	16.3%	estimated ± 2.7 pp, low confidence
104	Qwen3.6-27B	16.3%	estimated ± 2.7 pp, low confidence
105	Grok 4.3	16.2%	estimated ± 3.8 pp, medium confidence
106	Kimi K2.5	15.2%	estimated ± 2.7 pp, low confidence
107	Kimi K2.5 (Reasoning)	15.2%	estimated ± 2.7 pp, low confidence
108	Grok 4.20	14.9%	estimated ± 2.7 pp, low confidence
109	o1	14.8%	estimated ± 3.8 pp, medium confidence
110	Step 3.7 Flash	14.7%	estimated ± 3.8 pp, medium confidence
111	Gemma 4 26B A4B	14.6%	estimated ± 3.8 pp, medium confidence
112	GPT-5 (high)	13.8%	estimated ± 3.8 pp, medium confidence
113	Nemotron 3 Super 100B	13.8%	estimated ± 3.8 pp, medium confidence
114	Qwen3.5 397B	13.6%	estimated ± 2.7 pp, low confidence
115	GLM-4.5	13.3%	estimated ± 6.2 pp, low confidence
116	Muse Glimmer 30B	13.1%	estimated ± 2.7 pp, low confidence
117	Ornith-1.0-35B	12.1%	estimated ± 2.7 pp, low confidence
118	o1-preview	11.9%	estimated ± 3.8 pp, medium confidence
119	K-Exaone	11.0%	estimated ± 3.8 pp, medium confidence
120	Gemma 4 12B	10.5%	estimated ± 3.8 pp, medium confidence
121	MiMo-V2-Omni	10.4%	estimated ± 2.7 pp, low confidence
122	GPT-OSS 120B	10.3%	estimated ± 3.8 pp, medium confidence
123	Laguna M.1	9.9%	estimated ± 2.7 pp, low confidence
124	GLM-5 (Reasoning)	9.8%	estimated ± 4.3 pp, low confidence
125	Claude 4.1 Opus	9.7%	estimated ± 2.7 pp, low confidence
126	Hy3 Preview	9.5%	estimated ± 2.7 pp, low confidence
127	Claude Sonnet 4.5 Thinking	9.4%	estimated ± 4.3 pp, low confidence
128	GPT-5.1-Codex-Max	9.2%	estimated ± 4.3 pp, low confidence
129	Command A+	9.1%	estimated ± 3.8 pp, medium confidence
130	Mistral Small 4	8.6%	estimated ± 3.8 pp, medium confidence
131	Mistral Small 4 (Reasoning)	8.6%	estimated ± 3.8 pp, medium confidence
132	Claude Opus 4.5 Thinking	8.5%	estimated ± 4.3 pp, low confidence
133	GLM-4.7	8.4%	estimated ± 2.7 pp, low confidence
134	Gemini 3 Flash	8.3%	estimated ± 4.3 pp, low confidence
135	Trinity-Large-Preview	8.3%	estimated ± 3.8 pp, medium confidence
136	Trinity-Large-Thinking	8.3%	estimated ± 3.8 pp, medium confidence
137	Ling 2.6 Flash	8.1%	estimated ± 3.8 pp, medium confidence
138	MAI-Thinking-1	7.9%	estimated ± 2.7 pp, low confidence
139	MiMo-V2-Flash	7.7%	estimated ± 2.7 pp, low confidence
140	Qwen3.6-35B-A3B	7.7%	estimated ± 2.7 pp, low confidence
141	Claude Haiku 4.5	7.6%	estimated ± 2.7 pp, low confidence
142	Gemini 1.5 Pro	7.4%	estimated ± 3.8 pp, medium confidence
143	Claude 4 Sonnet	6.7%	estimated ± 2.7 pp, low confidence
144	GPT-4 Turbo	6.6%	estimated ± 3.8 pp, medium confidence
145	MAI-Code-1.1-Flash	6.5%	estimated ± 2.7 pp, low confidence
146	GPT-OSS 20B	6.3%	estimated ± 3.8 pp, medium confidence
147	Qwen3.5 Plus	6.3%	estimated ± 4.3 pp, low confidence
148	Qwen3.5-27B	6.2%	estimated ± 2.7 pp, low confidence
149	Mistral Large 3	6.1%	estimated ± 3.8 pp, medium confidence
150	MiniMax M2.5	5.9%	estimated ± 4.3 pp, low confidence
151	Claude 3 Opus	5.9%	estimated ± 3.8 pp, medium confidence
152	Qwen3.5-122B-A10B	5.7%	estimated ± 2.7 pp, low confidence
153	Gemini 3 Pro	5.7%	estimated ± 4.3 pp, low confidence
154	GPT-5 mini	5.6%	estimated ± 4.3 pp, low confidence
155	Nemotron 3 Ultra	5.6%	estimated ± 2.7 pp, low confidence
156	GPT-5.1-Codex	5.2%	estimated ± 4.3 pp, low confidence
157	Llama 4 Maverick	4.8%	estimated ± 3.8 pp, medium confidence
158	Claude Haiku 4.5 Thinking	4.5%	estimated ± 4.3 pp, low confidence
159	Laguna XS 2.1	4.5%	estimated ± 2.7 pp, low confidence
160	Grok Code Fast 1	4.4%	estimated ± 2.7 pp, low confidence
161	Ornith-1.5-9B	4.2%	estimated ± 2.7 pp, low confidence
162	Solar Pro 4	4.2%	estimated ± 2.7 pp, low confidence
163	Celeris-1	4.2%	estimated ± 3.8 pp, medium confidence
164	Nemotron 3 Nano 30B	4.1%	estimated ± 3.8 pp, medium confidence
165	Solar Open 2	4.0%	estimated ± 2.7 pp, low confidence
166	Nemotron 3 Nano Omni 30B A3B	3.9%	estimated ± 3.8 pp, medium confidence
167	Laguna XS.2	3.5%	estimated ± 2.7 pp, low confidence
168	Ultravox v0.6 Llama 3.3 70B	3.4%	estimated ± 3.8 pp, medium confidence
169	GPT-4o mini	3.2%	estimated ± 3.8 pp, medium confidence
170	Ornith-1.0-9B	3.2%	estimated ± 2.7 pp, low confidence
171	GPT-4.1 nano	3.1%	estimated ± 3.8 pp, medium confidence
172	Qwen3.5-35B-A3B	3.0%	estimated ± 2.7 pp, low confidence
173	Gemma 3 27B	2.8%	estimated ± 3.8 pp, medium confidence
174	Gemma 4 E4B	2.6%	estimated ± 3.8 pp, medium confidence
175	K-EXAONE 2.0	2.4%	estimated ± 2.7 pp, low confidence
176	LongCat-Flash-Lite-Sparse	2.4%	estimated ± 2.7 pp, low confidence
177	Llama 4 Scout	2.2%	estimated ± 3.8 pp, medium confidence
178	LFM2.5-2.6B	2.1%	estimated ± 3.8 pp, medium confidence
179	Gemma 4 E2B	2.0%	estimated ± 3.8 pp, medium confidence
180	DeepSeek V3.2 (Thinking)	1.9%	estimated ± 4.3 pp, low confidence
181	Qwen3 Max	1.3%	estimated ± 4.3 pp, low confidence
182	GLM-4.6	1.2%	estimated ± 4.3 pp, low confidence
183	Gemini 2.5 Pro	0.8%	estimated ± 2.7 pp, low confidence
184	Grok 4.1 Fast (Reasoning)	0.4%	estimated ± 4.3 pp, low confidence
185	Ternary Bonsai 2 27B	0.4%	estimated ± 2.7 pp, low confidence
186	Granite 4.2 30B	0.2%	estimated ± 2.7 pp, low confidence
187	Ling 3.0 Flash VL	0.1%	estimated ± 6.6 pp, low confidence
188	GPT-4.1	0.1%	estimated ± 2.7 pp, low confidence
189	ZAYA1-74B-Preview	0.1%	estimated ± 2.7 pp, low confidence
190	Nemotron 3.5 Lightning 30B A3B NVFP4	0.1%	estimated ± 2.7 pp, low confidence
191	o3-mini	0.0%	estimated ± 2.7 pp, low confidence
192	LLaDA2.2-flash	0.0%	estimated ± 2.7 pp, low confidence
193	Claude 3.5 Sonnet	0.0%	estimated ± 2.7 pp, low confidence
194	Granite 4.2 8B	0.0%	estimated ± 2.7 pp, low confidence
195	A.X K2	0.0%	estimated ± 6.6 pp, low confidence
196	MiniCPM5-2B	0.0%	estimated ± 2.7 pp, low confidence
197	DeepSeek V3	0.0%	estimated ± 2.7 pp, low confidence
198	DeepSeek V3 0324	0.0%	estimated ± 6.6 pp, low confidence
199	North Mini Code	0.0%	estimated ± 6.6 pp, low confidence
200	Mercury 2.5	0.0%	estimated ± 6.6 pp, low confidence
201	Gemini 3.1 Flash-Lite	0.0%	estimated ± 4.3 pp, low confidence
202	GPT-4.1 mini	0.0%	estimated ± 2.7 pp, low confidence
203	Granite 4.2 3B	0.0%	estimated ± 6.6 pp, low confidence
204	Grok 4 Fast (Reasoning)	0.0%	estimated ± 4.3 pp, low confidence
205	Ling 3.0 Tiny	0.0%	estimated ± 6.6 pp, low confidence
206	Solar Pro 3	0.0%	estimated ± 6.6 pp, low confidence

FrontierCode 1.1 Main leaderboard

All leaderboards

Agentic · terminal

Agentic · tools

Coding

Math

Knowledge & reasoning

Instruction following

Multilingual

Vision & documents

Long context

General