Leaderboard

LLM Intelligence

Artificial Analysis Intelligence Index — a blended measure of reasoning, knowledge, and coding across open-weight and proprietary language models.

Source: Artificial Analysis · Updated Aug 3, 2026 · 20 models

#	Model	Intelligence	Coding	t/s	$/M
1	Kimi K3 Moonshot AI	57.1	76.2	34	6
2	GLM-5.2 Zhipu AI	51.1	68.8	194	2.15
3	DeepSeek V4 Flash 0731 DeepSeek	49.9	69.1	102	0.18
4	DeepSeek V4 Pro DeepSeek	44.3	59.4	60	0.54
5	Kimi K2.6 Moonshot AI	44.2	61.8	—	1.71
6	Kimi K2.7 Code Moonshot AI	41.9	60.8	39	1.71
7	DeepSeek V4 Flash DeepSeek	40.3	56.2	—	0.17
8	GLM-5.1 Zhipu AI	40.2	55.8	—	2.13
9	GLM-5 Zhipu AI	39.5	—	—	1.55
10	Nemotron 3 Ultra 550B A55B NVIDIA	37.8	49.3	146	1.18
11	Qwen3.6 27B Qwen · Alibaba	37.1	53.7	57	1.35
12	Kimi K2.5 Moonshot AI	35.4	46.8	—	1.2
13	Qwen3.5 27B Qwen · Alibaba	33.8	—	—	0.83
14	Qwen3.5 397B A17B Qwen · Alibaba	33.7	48.2	64	1.35
15	GLM-4.7 Zhipu AI	33.7	45.3	—	1
16	Kimi K2 Thinking Moonshot AI	32.7	—	—	1.08
17	Qwen3.5 122B A10B Qwen · Alibaba	32.3	45.7	138	1.1
18	DeepSeek V3.2 DeepSeek	32.0	44.2	—	0.32
19	Qwen3.6 35B A3B Qwen · Alibaba	31.6	41.9	130	0.56
20	DeepSeek V3.1 Terminus DeepSeek	30.4	43.5	—	1.91

Leaderboard data is cached from Artificial Analysis and refreshed every 12 hours. Scores shown are for reference; see the source for full methodology.

Leaderboard

LLM Intelligence

Artificial Analysis Intelligence Index — a blended measure of reasoning, knowledge, and coding across open-weight and proprietary language models.

Source: Artificial Analysis · Updated Aug 3, 2026 · 20 models

#	Model	Intelligence	Coding	t/s	$/M
1	Kimi K3 Moonshot AI	57.1	76.2	34	6
2	GLM-5.2 Zhipu AI	51.1	68.8	194	2.15
3	DeepSeek V4 Flash 0731 DeepSeek	49.9	69.1	102	0.18
4	DeepSeek V4 Pro DeepSeek	44.3	59.4	60	0.54
5	Kimi K2.6 Moonshot AI	44.2	61.8	—	1.71
6	Kimi K2.7 Code Moonshot AI	41.9	60.8	39	1.71
7	DeepSeek V4 Flash DeepSeek	40.3	56.2	—	0.17
8	GLM-5.1 Zhipu AI	40.2	55.8	—	2.13
9	GLM-5 Zhipu AI	39.5	—	—	1.55
10	Nemotron 3 Ultra 550B A55B NVIDIA	37.8	49.3	146	1.18
11	Qwen3.6 27B Qwen · Alibaba	37.1	53.7	57	1.35
12	Kimi K2.5 Moonshot AI	35.4	46.8	—	1.2
13	Qwen3.5 27B Qwen · Alibaba	33.8	—	—	0.83
14	Qwen3.5 397B A17B Qwen · Alibaba	33.7	48.2	64	1.35
15	GLM-4.7 Zhipu AI	33.7	45.3	—	1
16	Kimi K2 Thinking Moonshot AI	32.7	—	—	1.08
17	Qwen3.5 122B A10B Qwen · Alibaba	32.3	45.7	138	1.1
18	DeepSeek V3.2 DeepSeek	32.0	44.2	—	0.32
19	Qwen3.6 35B A3B Qwen · Alibaba	31.6	41.9	130	0.56
20	DeepSeek V3.1 Terminus DeepSeek	30.4	43.5	—	1.91

Leaderboard data is cached from Artificial Analysis and refreshed every 12 hours. Scores shown are for reference; see the source for full methodology.