SimpleBench · Open Analysis

#	Model	Effort	Score	Cost / task	Harness
1	Opus 5.5	max	88.4%	–	–
2	Fable 5.1	max	86.6%	–	–
3	GPT-6 Astra Pro	max	86.5%	–	–
4	GPT-6 Astra	max	83.6%	–	–
5	GPT-6.1 Sol	max	82.9%	–	–
6	Gemini 3.8 Flash	max	82.4%	–	–
7	Fable 5	max	81.9%	–	–
8	Muse Spark 1.3	max	81.8%	–	–
9	Opus 5	max	80.6%	–	–
10	Gemini 3.1 Pro	high	79.6%	–	–
11	GPT-5.5 Pro	xhigh	76.9%	–	–
12	Gemini 3.5 Flash	xhigh	76.7%	–	–
13	Gemini 3 Pro	high	76.4%	–	–
14	Grok 4.6	max	75.9%	–	–
15	Sonnet 5.5	max	75.9%	–	–
16	Muse Spark 1.2	max	74.5%	–	–
17	GPT-6 Sol	max	73.1%	–	–
18	GPT-5.6 Sol Pro	xhigh	71.7%	–	–
19	Qwen 3.7 Max	max	70.4%	–	–
20	Grok 4.5	max	70.0%	–	–
21	GPT-5.5	xhigh	69.0%	–	–
22	Opus 4.6	max	67.6%	–	–
23	DeepSeek V4.1 Flash	max	66.7%	–	–
24	GLM 5.3	max	66.2%	–	–
25	Opus 4.8	max	64.8%	–	–
26	GPT-5.6 Sol	xhigh	64.8%	–	–
27	Qwen 3.6 Max	max	63.0%	–	–
28	Qwen 3.8 2.4T-A95B	–	62.5%	–	–
29	Gemini 2.5 Pro	high	62.4%	–	–
30	Opus 4.5	high	62.0%	–	–
31	Opus 4.7	max	61.7%	–	–
32	GPT-5 Pro	high	61.6%	–	–
33	Gemini 3 Flash	high	61.1%	–	–
34	DeepSeek V4 Flash	max	61.1%	–	–
35	Kimi K3	max	60.7%	–	–
36	Sonnet 5	max	60.6%	–	–
37	Grok 4	high	60.5%	–	–
38	Qwen 3.8 27B	max	60.2%	–	–
39	Opus 4.1	high	60.0%	–	–
40	Opus 4	medium	58.8%	–	–
41	GLM 5.2	max	58.8%	–	–
42	Kimi K2.7 Code	max	57.9%	–	–
43	GPT-5.2 Pro	xhigh	57.4%	–	–
44	GPT-5	high	56.7%	–	–
45	Grok 4.1 Fast	high	56.0%	–	–
46	GLM 5.1	max	55.1%	–	–
47	Sonnet 4.5	high	54.3%	–	–
48	GPT-5.1	high	53.2%	–	–
49	GLM 5	high	53.2%	–	–
50	o3	high	53.1%	–	–
51	DeepSeek V3.2	high	52.6%	–	–
52	DeepSeek V4 Pro	max	50.9%	–	–
53	Inkling	max	50.0%	–	–
54	GPT-5.6 Terra	xhigh	48.9%	–	–
55	GLM 4.7	none	47.7%	–	–
56	Kimi K2.5	max	46.8%	–	–
57	GPT-5.6 Luna	xhigh	46.8%	–	–
58	Sonnet 3.7	medium	46.4%	–	–
59	GPT-5.2	high	45.8%	–	–
60	MiniMax M3	max	45.8%	–	–
61	Sonnet 4	high	45.5%	–	–
62	o1	high	41.7%	–	–
63	Nemotron 3 Ultra 550B A55B	max	41.7%	–	–
64	Sonnet 10.22	–	41.4%	–	–
65	Gemini 2.5 Flash	medium	41.2%	–	–
66	DeepSeek R1	xhigh	40.8%	–	–
67	DeepSeek V3.1	none	40.0%	–	–
68	Kimi K2	medium	39.6%	–	–
69	o4 mini	high	38.7%	–	–
70	Grok 3	none	36.1%	–	–
71	Qwen 3.6 Flash	max	35.2%	–	–
72	MiniMax M2.1	–	34.7%	–	–
73	GPT-4.5	none	34.5%	–	–
74	Gemini 1206	–	31.1%	–	–
75	Qwen 3 235B-A22B	xhigh	31.0%	–	–
76	Gemini 2.0 Flash	medium	30.7%	–	–
77	Llama 4 Maverick	medium	27.7%	–	–
78	Sonnet 06.20	–	27.5%	–	–
79	DeepSeek V3	none	27.2%	–	–
80	Gemini 1.5 Pro	none	27.1%	–	–
81	GPT-4.1	high	27.0%	–	–
82	GPT-4	high	25.1%	–	–
83	MiniMax M2	–	25.0%	–	–
84	Opus 3	none	23.5%	–	–
85	Llama 3.1 405b	none	23.0%	–	–
86	o3 mini	high	22.8%	–	–
87	Grok 2	none	22.7%	–	–
88	Mistral Large	none	22.5%	–	–
89	gpt-oss-120b	high	22.1%	–	–
90	Mistral Large 3	none	20.4%	–	–
91	Llama 3.3 70b	none	19.9%	–	–
92	o1 mini	high	18.1%	–	–
93	GPT-4o	high	17.8%	–	–
94	Command-R+ (Apr '24)	none	17.4%	–	–
95	GPT-4o mini	high	10.7%	–	–
96	GPT-3.5	high	8.0%	–	–