Agentic · tools

AA-AnalystAgent leaderboard

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

As of 2026-10-07, the highest measured score on AA-AnalystAgent is 60.0% by Gemini 3.7 Flash. 131 more models have estimated scores, calibrated from the benchmarks they were measured on.

Measured scores: benchlm.ai.

#	Model	Score	Source
1	Gemini 3.7 Flash	60.0%	measured
2	Claude Fable 5.1	57.5%	measured
3	Claude Sonnet 5.5	57.5%	measured
4	Claude Opus 5.5	56.3%	measured
5	DeepSeek V4.1 Flash	55.6%	estimated ± 2.5 pp, medium confidence
6	GLM-5.3	55.1%	estimated ± 2.5 pp, medium confidence
7	Gemini 4 Argon	54.4%	estimated ± 5.5 pp, medium confidence
8	Muse Spark 1.3	54.4%	estimated ± 5.5 pp, medium confidence
9	GPT-6 Sol	54.4%	estimated ± 5.5 pp, medium confidence
10	Gemini 3.8 Flash	54.4%	estimated ± 5.5 pp, medium confidence
11	GPT-5.6 Terra	54.4%	estimated ± 5.5 pp, medium confidence
12	GPT-5.6 Luna	54.4%	estimated ± 5.5 pp, medium confidence
13	Claude Opus 4.8	54.1%	estimated ± 5.5 pp, medium confidence
14	Qwen3.8-Flash-Next	53.9%	estimated ± 5.5 pp, medium confidence
15	DeepSeek V4 Pro 0813	53.9%	estimated ± 2.5 pp, medium confidence
16	Claude Opus 5	53.8%	measured
17	Claude Opus 4.7 (Adaptive)	53.7%	estimated ± 5.5 pp, medium confidence
18	GLM-5.2	52.7%	estimated ± 8.5 pp, low confidence
19	Muse Spark 1.1	51.7%	estimated ± 5.5 pp, medium confidence
20	Claude Haiku 5.5	51.5%	estimated ± 2.5 pp, medium confidence
21	Claude Sonnet 5	51.5%	estimated ± 2.5 pp, medium confidence
22	Claude Opus 4.7	51.4%	estimated ± 5.5 pp, medium confidence
23	GPT-6 Astra	51.2%	measured
24	Qwen3.8 Max Preview	50.6%	estimated ± 12.0 pp, low confidence
25	GPT-6 Luna	50.1%	estimated ± 6.5 pp, medium confidence
26	GPT-5.5	50.0%	measured
27	GPT-6.1 Sol	50.0%	measured
28	Qwen3.8 Max	49.8%	estimated ± 2.5 pp, medium confidence
29	Apodex 1.1	49.6%	estimated ± 2.5 pp, medium confidence
30	Ornith-1.5-397B	49.6%	estimated ± 2.5 pp, medium confidence
31	Claude Fable 5	48.8%	measured
32	Hy4 preview	48.4%	estimated ± 2.5 pp, medium confidence
33	GLM-5.3-Flash	48.2%	estimated ± 2.5 pp, medium confidence
34	Ling 3.1 Flash	47.6%	estimated ± 12.0 pp, low confidence
35	GPT-5.6 Sol	47.5%	measured
36	Atria Dawn Preview	47.4%	estimated ± 12.5 pp, low confidence
37	Grok 4.7	46.7%	estimated ± 6.5 pp, medium confidence
38	MiMo-V2.6-Pro	45.3%	estimated ± 6.5 pp, medium confidence
39	Gemini 3.5 Flash	45.2%	estimated ± 3.6 pp, medium confidence
40	Qwen3.7 Max	44.3%	estimated ± 2.5 pp, medium confidence
41	Mistral Large 4	44.0%	estimated ± 6.5 pp, medium confidence
42	GPT-5.5 Pro	43.2%	estimated ± 12.5 pp, low confidence
43	MiMo-V2.6-Flash	42.5%	estimated ± 6.7 pp, low confidence
44	dots3-note Preview	41.9%	estimated ± 2.5 pp, medium confidence
45	Grok 4.6	41.8%	estimated ± 3.6 pp, medium confidence
46	GPT-5.4 Pro	41.8%	estimated ± 12.5 pp, low confidence
47	Claude Mythos 5	39.6%	estimated ± 12.5 pp, low confidence
48	Muse Spark 1.2	39.5%	estimated ± 12.0 pp, low confidence
49	Kimi K3	38.8%	measured
50	Step 5 Preview	35.0%	measured
51	Grok 4.5	34.9%	estimated ± 12.0 pp, low confidence
52	Qwen3.8-27B	34.2%	estimated ± 3.6 pp, medium confidence
53	Claude Opus 4.6	32.5%	estimated ± 12.5 pp, low confidence
54	Gemini 3.6 Flash	29.9%	estimated ± 12.0 pp, low confidence
55	GPT-5.4	28.1%	estimated ± 12.0 pp, low confidence
56	Claude Sonnet 4.6	26.7%	estimated ± 5.5 pp, medium confidence
57	Hy3 Preview	26.6%	estimated ± 12.0 pp, low confidence
58	Apodex 1.1 Mini	25.7%	estimated ± 12.0 pp, low confidence
59	Ling 3.0 Flash	25.6%	estimated ± 9.1 pp, low confidence
60	Quasar 438B	25.2%	estimated ± 12.0 pp, low confidence
61	Agents-A1	25.2%	estimated ± 2.5 pp, medium confidence
62	Ling 3.0 Flash VL	24.3%	estimated ± 12.0 pp, low confidence
63	Step 3.7 Flash	23.8%	estimated ± 2.5 pp, medium confidence
64	Inkling	23.8%	measured
65	Beam	23.5%	estimated ± 12.5 pp, low confidence
66	MiMo-V2.5-Pro	22.6%	estimated ± 12.0 pp, low confidence
67	GLM-5.1	22.4%	estimated ± 12.0 pp, low confidence
68	Solar Pro 4	22.0%	estimated ± 12.0 pp, low confidence
69	Grok 4.3	20.9%	estimated ± 12.0 pp, low confidence
70	Hy3	20.1%	estimated ± 12.0 pp, low confidence
71	Kimi K2.7 Code	19.1%	estimated ± 12.0 pp, low confidence
72	GLM-4.7	18.1%	estimated ± 12.0 pp, low confidence
73	GPT-5.4 mini	18.1%	estimated ± 12.0 pp, low confidence
74	MiniMax M2.7	18.0%	estimated ± 12.0 pp, low confidence
75	Muse Spark	17.5%	estimated ± 12.0 pp, low confidence
76	DeepSeek V4 Flash 0731	17.5%	estimated ± 2.5 pp, medium confidence
77	Qwen3.6 Plus	17.2%	estimated ± 12.0 pp, low confidence
78	Qwen3.6-27B	17.0%	estimated ± 12.0 pp, low confidence
79	Gemini 3.5 Flash-Lite	16.9%	estimated ± 12.0 pp, low confidence
80	Muse Glimmer 30B	16.4%	estimated ± 3.6 pp, medium confidence
81	A.X K2	16.0%	estimated ± 12.0 pp, low confidence
82	GPT-5.4 nano	15.5%	estimated ± 12.0 pp, low confidence
83	Ling 3.0 Flash FP8	15.4%	estimated ± 12.0 pp, low confidence
84	GPT-5 (high)	14.3%	estimated ± 12.0 pp, low confidence
85	Qwen3.6-35B-A3B	13.4%	estimated ± 12.0 pp, low confidence
86	Agents-A1-4B	12.7%	estimated ± 12.5 pp, low confidence
87	GPT-5.2	12.0%	estimated ± 12.5 pp, low confidence
88	Kimi K2.5	11.5%	estimated ± 12.0 pp, low confidence
89	Kimi K2.5 (Reasoning)	11.5%	estimated ± 12.0 pp, low confidence
90	GPT-5.1	11.0%	estimated ± 12.0 pp, low confidence
91	Qwen3.5-122B-A10B	10.5%	estimated ± 12.0 pp, low confidence
92	MiniMax M3	10.0%	measured
93	Kimi K2.6	10.0%	estimated ± 5.5 pp, medium confidence
94	Inkling-Small	9.8%	estimated ± 6.7 pp, low confidence
95	Gemini 3.1 Pro	9.7%	estimated ± 12.0 pp, low confidence
96	Qwen3.5 397B	9.5%	estimated ± 12.5 pp, low confidence
97	Qwen3.7 Plus	9.2%	estimated ± 5.5 pp, low confidence
98	Qwen3.5-27B	9.0%	estimated ± 12.5 pp, low confidence
99	Qwen3.5-35B-A3B	9.0%	estimated ± 12.5 pp, low confidence
100	Mistral Medium 3.5 128B	8.6%	estimated ± 12.0 pp, low confidence
101	MiniCPM5-2B	6.8%	estimated ± 12.0 pp, low confidence
102	Nemotron 3 Ultra	6.3%	measured
103	Laguna S 2.1	5.9%	estimated ± 6.7 pp, low confidence
104	LongCat-Flash-Lite-Sparse	5.0%	estimated ± 12.5 pp, low confidence
105	Ornith-1.5-35B-A3B	4.9%	estimated ± 2.5 pp, low confidence
106	Ornith-1.5-9B	4.5%	estimated ± 2.5 pp, low confidence
107	Nemotron 3.5 Lightning 30B A3B NVFP4	4.4%	estimated ± 12.0 pp, low confidence
108	MiMo-V2-Flash	4.2%	estimated ± 12.0 pp, low confidence
109	Gemma 4 31B	3.8%	estimated ± 12.0 pp, low confidence
110	GPT-OSS 120B	3.5%	estimated ± 12.0 pp, low confidence
111	Granite 4.2 30B	2.4%	estimated ± 12.0 pp, low confidence
112	Gemma 4 26B A4B	2.1%	estimated ± 12.0 pp, low confidence
113	Ling 3.0 Tiny	2.0%	estimated ± 12.0 pp, low confidence
114	Command A+	0.6%	estimated ± 12.0 pp, low confidence
115	Celeris-1	0.0%	estimated ± 12.0 pp, low confidence
116	DeepSeek V3	0.0%	estimated ± 12.0 pp, low confidence
117	DeepSeek V3 0324	0.0%	estimated ± 12.0 pp, low confidence
118	Gemini 2.5 Pro	0.0%	estimated ± 12.0 pp, low confidence
119	Gemma 3 27B	0.0%	estimated ± 12.0 pp, low confidence
120	Gemma 4 12B	0.0%	estimated ± 12.0 pp, low confidence
121	Gemma 4 E2B	0.0%	estimated ± 12.0 pp, low confidence
122	Gemma 4 E4B	0.0%	estimated ± 12.0 pp, low confidence
123	GPT-4.1 mini	0.0%	estimated ± 12.0 pp, low confidence
124	GPT-4.1 nano	0.0%	estimated ± 12.0 pp, low confidence
125	GPT-4o	0.0%	estimated ± 12.0 pp, low confidence
126	GPT-4o mini	0.0%	estimated ± 12.0 pp, low confidence
127	GPT-OSS 20B	0.0%	estimated ± 12.0 pp, low confidence
128	Granite 4.2 3B	0.0%	estimated ± 12.0 pp, low confidence
129	Granite 4.2 8B	0.0%	estimated ± 12.0 pp, low confidence
130	K-Exaone	0.0%	estimated ± 12.0 pp, low confidence
131	LFM2.5-2.6B	0.0%	estimated ± 12.0 pp, low confidence
132	Ling 2.6 Flash	0.0%	estimated ± 12.0 pp, low confidence
133	Llama 4 Maverick	0.0%	estimated ± 12.0 pp, low confidence
134	Llama 4 Scout	0.0%	estimated ± 12.0 pp, low confidence
135	Mercury 2.5	0.0%	estimated ± 12.0 pp, low confidence
136	Mistral Large 3	0.0%	estimated ± 12.0 pp, low confidence
137	Mistral Small 4	0.0%	estimated ± 12.0 pp, low confidence
138	Mistral Small 4 (Reasoning)	0.0%	estimated ± 12.0 pp, low confidence
139	Nemotron 3 Nano 30B	0.0%	estimated ± 12.0 pp, low confidence
140	Nemotron 3 Nano Omni 30B A3B	0.0%	estimated ± 12.0 pp, low confidence
141	Nemotron 3 Super 100B	0.0%	estimated ± 12.0 pp, low confidence
142	North Mini Code	0.0%	estimated ± 12.0 pp, low confidence
143	Solar Pro 3	0.0%	estimated ± 12.0 pp, low confidence
144	Trinity-Large-Preview	0.0%	estimated ± 12.0 pp, low confidence
145	Trinity-Large-Thinking	0.0%	estimated ± 12.0 pp, low confidence
146	Ultravox v0.6 Llama 3.3 70B	0.0%	estimated ± 12.0 pp, low confidence

AA-AnalystAgent leaderboard

All leaderboards

Agentic · terminal

Agentic · tools

Coding

Math

Knowledge & reasoning

Instruction following

Multilingual

Vision & documents

Long context

General