Note: Overall leaderboard rankings may not reflect true model quality — individual benchmarks give a clearer picture. ARC-Challenge MMLU GPQA GSM8K Artificial Analysis Intelligence Index v4.0
← Back to leaderboard

Artificial Analysis Intelligence Index v4.0 (Maximum Reasoning)

156 models

Index, calculated on GDPval-AA, T2-Bench Telecom, Terminal Bench Hard, SciCode, AA-LCR, AA-Omniscience, IFBench, Humanity's Last Exam, GPQA Diamond, CritPt.

Top 10 Models Performance

anthropic/claude-opus-4.8 ######################################## 61.4
openai/gpt-5.5 ####################################### 60.2
anthropic/claude-opus-4.7 ##################################### 57.3
google/gemini-3.1-pro-preview ##################################### 57.2
openai/gpt-5.4 ##################################### 56.8
qwen/qwen3.7-max ##################################### 56.6
google/gemini-3.5-flash #################################### 55.3
moonshotai/kimi-k2.6 ################################### 53.9
xiaomi/mimo-v2.5-pro ################################### 53.8
openai/gpt-5.3-codex ################################### 53.6
– 68.8K – 862.0B
Rank Model Score
🥇 anthropic/claude-opus-4.8 61.4
🥈 openai/gpt-5.5 60.2
🥉 anthropic/claude-opus-4.7 57.3
4 google/gemini-3.1-pro-preview 57.2
5 openai/gpt-5.4 56.8
6 qwen/qwen3.7-max 56.6
7 google/gemini-3.5-flash 55.3
8 moonshotai/kimi-k2.6 53.9
9 xiaomi/mimo-v2.5-pro 53.8
10 openai/gpt-5.3-codex 53.6
11 x-ai/grok-4.3 53.2
12 meta/muse-spark 52.2
13 qwen/qwen3.6-max 51.8
14 anthropic/claude-sonnet-4.6 51.7
15 deepseek-ai/deepseek-v4-pro 51.5
16 zai-org/glm-5.1 51.4
17 openai/gpt-5.2 51.3
18 zai-org/glm-5 49.8
19 minimaxai/minimax-m2.7 49.6
20 xiaomi/mimo-v2-pro 49.2
21 xiaomi/mimo-v2.5 49
22 openai/gpt-5.2-codex 49
23 x-ai/grok-4.20-0309 48.5
24 google/gemini-3-pro-preview 48.4
25 moonshotai/kimi-k2.5 46.8
26 qwen/qwen3.5-397b-a17b 45
27 openai/gpt-5 44.6
28 kwaipilot/kat-coder-pro-v2 43.8
29 anthropic/claude-4.5-sonnet 43
30 zai-org/glm-4.7 42.1
31 qwen/qwen3.5-27b 42.1
32 tencent/hy3-preview 41.9
33 deepseek-ai/deepseek-v3.2 41.7
34 qwen/qwen3.5-122b-a10b 41.6
35 x-ai/grok-4 41.5
36 moonshotai/kimi-k2-thinking 40.9
37 google/gemma-4-31b-it 39.2
38 mistralai/mistral-medium-3.5-128b 39.2
39 x-ai/grok-4.1-fast 38.6
40 inclusionai/ring-2.6-1t 38.5
41 stepfun-ai/step-3.5-flash 37.8
42 coherelabs/command-a-plus-05-2026-bf16 37.2
43 anthropic/claude-4.5-haiku 37.1
44 qwen/qwen3.5-35b-a3b 37.1
45 nvidia/nvidia-nemotron-3-super-120b-a12b 36
46 kwaipilot/kat-coder-pro-v1 36
47 amazon/nova-2.0-pro 35.7
48 x-ai/grok-4-fast 35.1
49 openai/gpt-oss-120b 33.3
50 deepseek-ai/deepseek-v3.2-exp 32.9
51 inception/mercury-2 32.8
52 qwen/qwen3.5-4b 32.5
53 qwen/qwen3.5-9b 32.4
54 lgai-exaone/k-exaone-236b-a23b 32.1
55 x-ai/grok-3-mini 32.1
56 arcee-ai/trinity-large-thinking 31.9
57 google/gemma-4-26b-a4b-it 31.2
58 openai/o1 30.7
59 xiaomi/mimo-v2-flash 30.3
60 zai-org/glm-4.7-flash 30.1
61 deepseek-ai/deepseek-v3.2-speciale 29.4
62 baidu/ernie-5.0-thinking 29.1
63 x-ai/grok-code-fast-1 28.7
64 mistralai/mistral-small-4-119b-2603 27.8
65 upstage/solar-pro-3 25.9
66 x-ai/grok-3 25.2
67 bytedance-seed/seed-oss-36b-instruct 25.2
68 openai/gpt-oss-20b 24.5
69 nvidia/nvidia-nemotron-3-nano-30b-a3b 24.3
70 meituan-longcat/longcat-flash-lite 23.9
71 naver-hyperclovax/hyperclovax-seed-think-32b 23.7
72 zai-org/glm-4.5-air 23.2
73 qwen/qwen3.5-2b 23
74 primeintellect/intellect-3 22.2
75 upstage/solar-open-100b 21.7
76 qwen/qwq-32b 19.7
77 google/gemma-4-e4b-it 18.8
78 deepseek-ai/deepseek-r1 18.8
79 openai/gpt-4o 18.6
80 nousresearch/hermes-4-405b 18.6
81 meta-llama/llama-4-maverick-17b-128e-instruct 18.4
82 sarvamai/sarvam-105b 18.2
83 anthropic/claude-3-opus 18
84 meta-llama/llama-3.1-405b-instruct 17.4
85 deepseek-ai/deepseek-r1-distill-qwen-32b 17.2
86 qwen/qwen3-vl-8b-thinking 16.7
87 lgai-exaone/exaone-4.0-32b 16.7
88 deepseek-ai/deepseek-r1-distill-llama-70b 16
89 mistralai/ministral-3-14b-instruct-2512 16
90 nousresearch/hermes-4-70b 16
91 qwen/qwen3.5-0.8b 15.9
92 deepseek-ai/deepseek-r1-distill-qwen-14b 15.8
93 google/gemma-4-e2b-it 15.2
94 baidu/ernie-4.5-300b-a47b 15
95 upstage/solar-pro-2 14.9
96 mistralai/ministral-3-8b-instruct-2512 14.8
97 nvidia/nvidia-nemotron-nano-9b-v2 14.8
98 meta-llama/llama-3.3-70b-instruct 14.5
99 x-ai/grok-2 13.9
100 google/gemini-1.5-flash 13.8
101 qwen/qwen3-vl-4b-thinking 13.7
102 coherelabs/c4ai-command-a-03-2025 13.5
103 amazon/nova-pro-v1 13.5
104 qwen/qwen2.5-coder-32b-instruct 12.9
105 amazon/nova-lite-v1 12.7
106 anthropic/claude-3-haiku 12.3
107 deepseek-ai/deepseek-v2.5 12.3
108 sarvamai/sarvam-30b 12.3
109 deepseek-ai/deepseek-r1-distill-llama-8b 12.1
110 google/gemini-1.5-pro 12
111 rekaai/reka-flash 12
112 upstage/solar-mini 11.9
113 meta-llama/llama-3.1-8b-instruct 11.8
114 x-ai/grok-1 11.7
115 mistralai/ministral-3-3b-instruct-2512 11.2
116 nousresearch/deephermes-3-mistral-24b-preview 10.9
117 nousresearch/hermes-3-llama-3.1-70b 10.6
118 allenai/olmo-2-0325-32b-instruct 10.6
119 liquid/lfm-2-24b-a2b 10.5
120 microsoft/phi-4 10.4
121 anthropic/claude-3-sonnet 10.3
122 google/gemma-3-27b-it 10.3
123 amazon/nova-micro-v1 10.3
124 microsoft/phi-3-mini-4k-instruct 10.1
125 qwen/qwen2.5-coder-7b-instruct 10
126 meta-llama/llama-3.2-3b-instruct 9.7
127 meta-llama/llama-2-7b-chat 9.7
128 qwen/qwen1.5-110b-chat 9.5
129 rekaai/reka-flash-3 9.5
130 allenai/olmo-3-7b-think 9.4
131 allenai/olmo-2-1124-7b-instruct 9.3
132 deepseek-ai/deepseek-r1-distill-qwen-1.5b 9.1
133 openai/gpt-3.5-turbo 9
134 google/gemma-3-12b-it 8.8
135 liquid/lfm-40b 8.8
136 google/palm-2 8.6
137 google/gemini-1.0-pro 8.5
138 deepseek-ai/deepseek-coder-v2-lite-instruct 8.5
139 microsoft/phi-4-mini-instruct 8.4
140 deepseek-ai/deepseek-llm-67b-chat 8.4
141 coherelabs/c4ai-command-r-plus 8.3
142 lgai-exaone/exaone-4.0-1.2b 8.3
143 openchat/openchat_3.5 8.3
144 liquid/lfm-2.5-1.2b-thinking 8.1
145 allenai/olmo-3-7b-instruct 8.1
146 liquid/lfm-2.5-1.2b-instruct 8
147 google/gemma-3-270m-it 7.7
148 swiss-ai/apertus-70b-instruct-2509 7.7
149 coherelabs/c4ai-command-r7b-12-2024 7.4
150 allenai/molmo2-8b 7.3
151 qwen/qwen3-0.6b 6.5
152 google/gemma-3n-e4b-it 6.4
153 meta-llama/llama-3.2-1b-instruct 6.3
154 google/gemma-3-4b-it 6.3
155 swiss-ai/apertus-8b-instruct-2509 5.9
156 google/gemma-3-1b-it 5.6