Benchmarks / Artificial Analysis

Reported by Artificial Analysis

Artificial Analysis

Artificial Analysis's blend of its reasoning, knowledge, coding and agent evaluations.

Last updated 8 Oct 2026

Results dated
8 Oct 2026
Results
407 configurations of 243 models
Unit
index score
Licence
Artificial Analysis commercial data licence

Artificial Analysis Intelligence Index:

Top 15 of 243 results · index score, higher is better. Choose a model to highlight it.Clear highlight

  1. 1 Claude Opus 5.5 (max reasoning)Anthropic 57.6
  2. 2 Claude Sonnet 5.5 (max reasoning)Anthropic 56.0
  3. 3 Claude Fable 5.1 (max reasoning)Anthropic 53.4
  4. 4 GPT-6 Astra (max reasoning)OpenAI 52.7
  5. 5 Gemini 4 Argon (high reasoning)Google 52.6
  6. 6 GPT-6.1 Sol (max reasoning)OpenAI 51.8
  7. 7 Claude Opus 5 (max reasoning)Anthropic 50.8
  8. 8 Claude Fable 5 (max reasoning)Anthropic 49.6
  9. 9 Muse Spark 1.3 (max reasoning)Meta 48.1
  10. 10 GPT-6 Sol (max reasoning)OpenAI 47.6
  11. 11 GPT-5.6 Sol (max reasoning)OpenAI 47.0
  12. 12 Grok 4.7 (extra-high reasoning)xAI 46.4
  13. 13 MiMo-V2.6-ProXiaomi 46.3
  14. 14 Qwen3.8-Max (0902)Alibaba 45.4
  15. 15 GLM-5.3 (max reasoning)Z.ai 44.8

Full results

Artificial Analysis: Artificial Analysis Intelligence Index, index score, higher is better
#ModelArtificial Analysis Intelligence Index
index score, higher is better		Price
$ per million tokens, in / out
1 Claude Opus 5.5 (max reasoning)Anthropic · best of 5 settings
57.6
$4 / $20
2 Claude Sonnet 5.5 (max reasoning)Anthropic · best of 5 settings
56.0
$2 / $10
3 Claude Fable 5.1 (max reasoning)Anthropic · best of 5 settings
53.4
$10 / $50
4 GPT-6 Astra (max reasoning)OpenAI · best of 5 settings
52.7
$10 / $50
5 Gemini 4 Argon (high reasoning)Google
52.6
–
6 GPT-6.1 Sol (max reasoning)OpenAI · best of 5 settings
51.8
$2 / $10
7 Claude Opus 5 (max reasoning)Anthropic · best of 5 settings
50.8
$5 / $25
8 Claude Fable 5 (max reasoning)Anthropic
49.6
$10 / $50
9 Muse Spark 1.3 (max reasoning)Meta · best of 2 settings
48.1
$1.25 / $4.25
10 GPT-6 Sol (max reasoning)OpenAI · best of 6 settings
47.6
$2 / $10
11 GPT-5.6 Sol (max reasoning)OpenAI · best of 6 settings
47.0
$4 / $20
12 Grok 4.7 (extra-high reasoning)xAI · best of 3 settings
46.4
$2 / $6
13 MiMo-V2.6-ProXiaomi
46.3
$0.43 / $0.87
14 Qwen3.8-Max (0902)Alibaba
45.4
$2 / $6
15 GLM-5.3 (max reasoning)Z.ai · best of 2 settings
44.8
$1.40 / $4.40
16 Grok 4.6 (high reasoning)xAI · best of 4 settings
44.3
$2 / $6
17 Kimi K3 (max reasoning)Moonshot AI · best of 2 settings
43.6
$3 / $15
18 Claude Haiku 5.5 (max reasoning)Anthropic · best of 5 settings
43.4
$0.10 / $0.50
19 GPT-5.6 Terra (max reasoning)OpenAI · best of 6 settings
42.1
$2 / $12
20 Claude Opus 4.8 (max reasoning)Anthropic
41.8
$5 / $25
20 GLM-5.3-FlashZ.ai
41.8
$0.15 / $0.50
22 Gemini 3.8 Flash (high reasoning)Google · best of 3 settings
40.9
$1.50 / $7.50
23 Claude Opus 4.7 (max reasoning)Anthropic · best of 2 settings
40.7
$5 / $25
24 Qwen3.8-Max (0803)Alibaba
40.2
–
25 Qwen3.8-2.4T-A95BAlibaba
39.9
$2 / $6
26 Qwen3.8-Flash-NextAlibaba
39.8
–
27 Gemini 3.7 Flash (medium reasoning)Google · best of 3 settings
39.6
$1.50 / $7.50
27 Muse Spark 1.2 (extra-high reasoning)Meta
39.6
$1.25 / $4.25
29 DeepSeek-V4.1-Flash (max reasoning)DeepSeek · best of 2 settings
39.5
$0.30 / $1.20
30 GPT-5.4 (extra-high reasoning)OpenAI · best of 3 settings
39.0
$2.50 / $15
31 Grok 4.5 (high reasoning)xAI
38.8
$2 / $6
32 Mistral Large 4Mistral AI
38.4
$1.36 / $4.18
32 GPT-5.5 (extra-high reasoning)OpenAI · best of 5 settings
38.4
$5 / $30
34 Claude Sonnet 5 (max reasoning)Anthropic · best of 6 settings
38.2
$2 / $10
35 GPT-6 Luna (max reasoning)OpenAI · best of 6 settings
38.1
$0.10 / $0.50
36 MiMo-V2.6-FlashXiaomi
37.9
$0.14 / $0.28
37 GPT-5.6 Luna (max reasoning)OpenAI · best of 6 settings
37.3
$0.20 / $1.20
38 DeepSeek-V4-Pro (0813, max reasoning)DeepSeek · best of 2 settings
36.0
$1.32 / $3.96
39 DeepSeek-V4-Flash-Vision-Exp (max reasoning)DeepSeek
34.8
$0.44 / $1.32
40 DeepSeek-V4-Flash (0731, max reasoning)DeepSeek
34.3
$0.14 / $0.28
41 Gemini 3.6 Flash (high reasoning)Google
34.0
$1.50 / $7.50
42 Qwen3.8-27B (extra-high reasoning)Alibaba · best of 4 settings
33.7
$0.50 / $3
42 Muse Spark 1.1 (extra-high reasoning)Meta
33.7
$1.25 / $4.25
42 GLM-5.2 (max reasoning)Z.ai · best of 2 settings
33.7
$1.40 / $4.40
45 Gemini 3.5 Flash (medium reasoning)Google · best of 3 settings
33.6
$1.50 / $9
46 GPT-5.3-Codex (extra-high reasoning)OpenAI
32.5
$1.75 / $14
47 Claude Opus 4.6 (max reasoning)Anthropic · best of 2 settings
31.9
$5 / $25
48 Muse SparkMeta
31.3
–
49 DeepSeek-V4-Pro (0423, max reasoning)DeepSeek · best of 3 settings
30.4
$1.42 / $2.83
49 GPT-5.2 (extra-high reasoning)OpenAI · best of 3 settings
30.4
$1.75 / $14
51 Claude Sonnet 4.6 (max reasoning)Anthropic · best of 2 settings
30.1
$3 / $15
52 Gemini 3.1 Pro PreviewGoogle
29.7
$2 / $12
53 Qwen3.7-MaxAlibaba
29.5
$1.48 / $4.42
54 MiniMax-M3MiniMax
29.2
$0.30 / $1.20
55 Claude Opus 4.5 (reasoning on)Anthropic · best of 2 settings
29.1
$5 / $25
56 GPT-5.2-Codex (extra-high reasoning)OpenAI
28.5
$1.75 / $14
57 Qwen3.6-Max-PreviewAlibaba
28.4
$1.03 / $6.16
58 Solar Pro 4Upstage
28.2
$0.09 / $0.36
59 Gemini 3 Pro Preview (high reasoning)Google · best of 2 settings
28.0
–
60 GLM-5Z.ai · best of 2 settings
27.9
$0.95 / $2.55
61 Grok Build 0.1xAI
27.2
$1 / $2
62 Qwen3.6-PlusAlibaba
27.0
$0.33 / $1.95
62 Kimi K2.6Moonshot AI · best of 2 settings
27.0
$0.95 / $4
64 GLM-5-TurboZ.ai
26.6
$1.20 / $4
65 Gemini 3 Flash Preview (reasoning on)Google · best of 2 settings
26.3
$0.50 / $3
66 GLM-5.1Z.ai · best of 2 settings
26.1
$1.38 / $4.40
67 GPT-5.5 Instant (2026-06-26)OpenAI · best of 2 settings
26.0
–
67 MiMo-V2.5-Pro (reasoning on)Xiaomi · best of 2 settings
26.0
$0.43 / $0.87
69 Kimi K2.7 CodeMoonshot AI
25.8
$0.95 / $4
70 Inkling SmallThinking Machines
25.7
$0.45 / $1.20
70 Grok 4.20xAI · best of 2 settings
25.7
$1.25 / $2.50
72 Hy3Tencent
25.3
$0.14 / $0.58
73 Qwen3.7-PlusAlibaba
25.2
$0.32 / $1.28
73 Grok 4.20 (0309, reasoning)xAI
25.2
–
73 MiMo-V2.5Xiaomi
25.2
$0.17 / $0.34
76 Inkling (extra-high reasoning)Thinking Machines
25.0
$0.95 / $4.05
77 GPT-5-Codex (high reasoning)OpenAI
24.9
–
77 Grok 4.3 (high reasoning)xAI · best of 4 settings
24.9
$1.25 / $2.50
79 GPT-5.1 (high reasoning)OpenAI · best of 2 settings
24.7
$1.25 / $10
80 DeepSeek-V4-Flash (0423, high reasoning)DeepSeek · best of 3 settings
24.4
$0.14 / $0.28
81 GPT-5.4 mini (extra-high reasoning)OpenAI · best of 3 settings
24.1
$0.75 / $4.50
82 GPT-5.1-Codex (high reasoning)OpenAI
23.7
$1.25 / $10
83 Kimi K2.5Moonshot AI · best of 2 settings
23.5
$0.57 / $2.85
83 GLM-5V-TurboZ.ai
23.5
$1.20 / $4
85 GPT-5 (high reasoning)OpenAI · best of 4 settings
23.0
$1.25 / $10
86 Qwen3.5-27BAlibaba · best of 2 settings
22.9
$0.27 / $2.16
87 Claude Opus 4.1 (reasoning on)Anthropic · best of 2 settings
22.8
$15 / $75
87 MiniMax-M2.5MiniMax
22.8
$0.30 / $1.20
87 MiniMax-M2.7MiniMax
22.8
$0.30 / $1.20
90 Hy3 Preview (reasoning on)Tencent · best of 2 settings
22.7
$0.18 / $0.60
91 Grok 4xAI
22.5
–
92 Gemini 3.5 Flash-LiteGoogle
22.2
$0.30 / $2.50
92 GLM-4.7Z.ai · best of 2 settings
22.2
$0.54 / $1.98
94 Kimi K2 ThinkingMoonshot AI
22.0
$0.60 / $2.50
95 o3-proOpenAI
21.9
$20 / $80
96 DeepSeek-V3.2 (reasoning on)DeepSeek · best of 2 settings
21.5
$0.30 / $0.96
97 Qwen3.5-397B-A17B (no reasoning)Alibaba · best of 2 settings
21.4
$0.55 / $3.50
97 Qwen3.6-27BAlibaba · best of 2 settings
21.4
$0.30 / $3.20
99 Qwen3-Max-ThinkingAlibaba
21.3
$0.78 / $3.90
100 MiniMax-M2.1MiniMax
20.9
$0.30 / $1.20
101 Claude Sonnet 4.5 (reasoning on)Anthropic · best of 2 settings
20.7
$3 / $15
101 GPT-5.4 nano (extra-high reasoning)OpenAI · best of 3 settings
20.7
$0.20 / $1.25
103 GPT-5 mini (medium reasoning)OpenAI · best of 3 settings
20.6
$0.25 / $2
104 Qwen3.5-Omni-PlusAlibaba
20.4
–
104 GPT-5.1-Codex-Mini (high reasoning)OpenAI
20.4
$0.25 / $2
104 Grok 4.1 Fast (reasoning)xAI
20.4
–
107 o3OpenAI
20.2
$2 / $8
108 Qwen3.5-35B-A3BAlibaba · best of 2 settings
19.3
$0.16 / $1.30
109 Claude Sonnet 4 (reasoning on)Anthropic · best of 2 settings
18.9
$3 / $15
110 MiniMax-M2MiniMax
18.6
$0.30 / $1.20
111 GLM-4.6 (reasoning on)Z.ai · best of 2 settings
18.5
$0.50 / $2
112 Qwen3.6-35B-A3BAlibaba · best of 2 settings
18.2
$0.10 / $1
113 Grok 4 Fast (reasoning)xAI
17.9
–
114 Qwen3.5-122B-A10B (no reasoning)Alibaba · best of 2 settings
17.7
$0.26 / $2.08
115 Muse Glimmer (high reasoning)Meta
17.5
–
116 Claude Haiku 4.5 (reasoning on)Anthropic · best of 2 settings
16.9
$1 / $5
117 Gemma 4 26B A4BGoogle · best of 2 settings
16.7
$0.10 / $0.30
117 o4-mini (high reasoning)OpenAI
16.7
$1.10 / $4.40
119 DeepSeek-V3.2-Exp (reasoning on)DeepSeek · best of 2 settings
16.6
$0.27 / $0.41
119 Step 3.5 FlashStepFun
16.6
$0.10 / $0.30
121 Qwen3-Max-Thinking-PreviewAlibaba
16.3
–
122 Gemini 2.5 ProGoogle
16.1
$1.25 / $10
123 Qwen3-MaxAlibaba
15.6
$0.78 / $3.90
123 Gemini 3.1 Flash-Lite PreviewGoogle
15.6
$0.25 / $1.50
125 Gemini 2.5 Flash Preview (09-2025, reasoning on)Google · best of 2 settings
15.5
–
126 Kimi K2 (0905)Moonshot AI
15.3
$0.60 / $2.50
127 o1OpenAI
15.2
$15 / $60
128 GLM-4.7-FlashZ.ai · best of 2 settings
14.9
$0.06 / $0.40
129 DeepSeek-V3.1-Terminus (reasoning on)DeepSeek · best of 2 settings
14.8
$0.27 / $1
130 Gemma 4 31BGoogle · best of 2 settings
14.7
$0.14 / $0.40
131 Grok 4.20 (0309, non-reasoning, no reasoning)xAI
14.6
–
132 DeepSeek-V3.2-SpecialeDeepSeek
14.5
–
133 Gemma 4 12BGoogle · best of 2 settings
14.2
–
133 Mistral Medium 3.5Mistral AI
14.2
$1.50 / $7.50
135 Grok Code Fast 1xAI
14.1
–
136 Mercury 2Inception
13.8
$0.25 / $0.75
137 DeepSeek-V3.1 (no reasoning)DeepSeek · best of 2 settings
13.7
$0.55 / $1.65
138 Qwen3-VL-235B-A22B-ThinkingAlibaba
13.4
$0.40 / $4
138 Nova 2 Lite (high reasoning)Amazon · best of 4 settings
13.4
$0.30 / $2.50
140 Qwen3.5-9B (no reasoning)Alibaba · best of 2 settings
13.3
$0.10 / $0.15
141 Qwen3.5-4B (reasoning on)Alibaba · best of 2 settings
13.1
–
141 DeepSeek-R1-0528DeepSeek
13.1
$0.50 / $2.18
141 Gemini 2.5 Flash (reasoning on)Google · best of 2 settings
13.1
$0.30 / $2.50
144 GPT-5 nano (high reasoning)OpenAI · best of 3 settings
13.0
$0.05 / $0.40
145 Nemotron 3 Super 120B A12BNVIDIA
12.8
$0.085 / $0.40
145 GLM-4.5Z.ai
12.8
$0.60 / $2.20
147 Qwen3-235B-A22B-Thinking-2507Alibaba
12.7
$0.30 / $3
147 Kimi K2 (0711)Moonshot AI
12.7
$0.57 / $2.30
147 GPT-4.1OpenAI
12.7
$2 / $8
150 Qwen3-Max-PreviewAlibaba
12.6
–
151 Qwen3.5-Omni-FlashAlibaba
12.5
–
151 o3-miniOpenAI · best of 2 settings
12.5
$1.10 / $4.40
153 Qwen3-235B-A22B-Instruct-2507Alibaba
12.0
$0.15 / $0.75
154 Qwen3-Coder-480B-A35BAlibaba
11.9
$0.35 / $1.50
154 Qwen3-VL-32B-ThinkingAlibaba
11.9
–
156 Magistral Medium 1.2Mistral AI
11.8
–
157 gpt-oss-120b (high reasoning)OpenAI · best of 2 settings
11.6
$0.15 / $0.60
158 DeepSeek-R1DeepSeek
11.4
$0.70 / $2.50
159 Mistral Small 4Mistral AI · best of 2 settings
11.3
$0.15 / $0.60
159 Grok 4.1 Fast (non-reasoning, no reasoning)xAI
11.3
–
161 Qwen3-Next-80B-A3B-ThinkingAlibaba
11.2
$0.15 / $1.20
161 GLM-4.6V (reasoning on)Z.ai · best of 2 settings
11.2
$0.30 / $0.90
163 Granite 4.2 8BIBM
11.1
$0.06 / $0.25
163 Grok 4 Fast (non-reasoning, no reasoning)xAI
11.1
–
163 GLM-4.5-AirZ.ai
11.1
$0.14 / $0.86
166 Trinity Large ThinkingArcee AI
10.8
$0.25 / $0.80
167 Gemini 2.5 Flash-Lite Preview (09-2025, reasoning on)Google · best of 2 settings
10.4
–
167 GPT-5 ChatOpenAI
10.4
–
169 GPT-4.1 miniOpenAI
10.2
$0.40 / $1.60
170 Llama 4 MaverickMeta
10.0
$0.27 / $0.85
170 gpt-oss-20b (low reasoning)OpenAI · best of 2 settings
10.0
$0.03 / $0.15
172 Qwen3-VL-235B-A22B-InstructAlibaba
9.9
$0.30 / $1.50
173 Qwen3-30B-A3B-Thinking-2507Alibaba
9.8
$0.20 / $2.40
174 DeepSeek-V3-0324DeepSeek
9.7
$0.25 / $1
175 Qwen3-Coder-30B-A3B-InstructAlibaba
9.6
$0.07 / $0.28
175 Qwen3-Next-80B-A3B-InstructAlibaba
9.6
$0.10 / $1.10
177 Qwen3-235B-A22B (reasoning on)Alibaba · best of 2 settings
9.5
$0.46 / $1.82
177 Qwen3-VL-30B-A3B-ThinkingAlibaba
9.5
$0.29 / $1
177 DiffusionGemma 26B A4BGoogle
9.5
–
180 Mistral Large 3Mistral AI
9.3
$0.50 / $1.50
181 Qwen3-Coder-NextAlibaba
9.2
$0.18 / $0.90
181 Mistral Medium 3.1Mistral AI
9.2
$0.40 / $2
183 Devstral MediumMistral AI
9.0
–
183 Mistral Medium 3Mistral AI
9.0
$0.40 / $2
185 Gemma 4 E4BGoogle · best of 2 settings
8.9
–
185 Nemotron 3 Nano 30B A3B (reasoning on)NVIDIA · best of 2 settings
8.9
$0.05 / $0.20
187 Qwen3-4B-Thinking-2507Alibaba
8.8
–
188 Qwen3-32B (reasoning on)Alibaba · best of 2 settings
8.6
$0.14 / $0.40
188 Devstral 2Mistral AI
8.6
$0.40 / $2
188 Magistral Small 1.2Mistral AI
8.6
–
191 DeepSeek-V3DeepSeek
8.5
$0.26 / $1.03
191 Gemini 2.5 Flash-Lite (reasoning on)Google · best of 2 settings
8.5
$0.10 / $0.40
193 Qwen3-VL-32B-InstructAlibaba
8.4
$0.10 / $0.42
194 Qwen3-14B (reasoning on)Alibaba · best of 2 settings
8.2
$0.12 / $0.24
194 Qwen3-VL-8B-ThinkingAlibaba
8.2
$0.18 / $2.10
194 Mistral Small 3.2 24BMistral AI
8.2
$0.094 / $0.25
197 Llama 4 ScoutMeta
8.1
$0.18 / $0.59
198 Qwen3-VL-30B-A3B-InstructAlibaba
7.9
$0.15 / $0.60
199 Qwen3-Omni-30B-A3B-ThinkingAlibaba
7.8
–
199 Gemma 4 E2BGoogle · best of 2 settings
7.8
–
199 GPT-4.1 nanoOpenAI
7.8
$0.10 / $0.40
199 Solar Pro 3Upstage
7.8
$0.15 / $0.60
203 Qwen2.5-72B-InstructAlibaba
7.7
$0.36 / $0.40
203 Llama 3.3 70B InstructMeta
7.7
$0.59 / $0.79
203 GPT-4o (2024-08-06)OpenAI
7.7
$2.50 / $10
206 Qwen3-30B-A3B (reasoning on)Alibaba · best of 2 settings
7.6
$0.12 / $0.50
206 Devstral Small 1.1Mistral AI
7.6
–
206 GLM-4.5V (reasoning on)Z.ai · best of 2 settings
7.6
$0.60 / $1.80
209 Qwen3-30B-A3B-Instruct-2507Alibaba
7.5
$0.09 / $0.30
209 Devstral Small 2Mistral AI
7.5
–
211 Qwen3-8B (reasoning on)Alibaba · best of 2 settings
7.3
$0.12 / $0.46
211 Qwen3-VL-8B-InstructAlibaba
7.3
$0.12 / $0.46
211 Kimi Linear 48B A3B InstructMoonshot AI
7.3
–
211 GPT-4o (2024-05-13)OpenAI
7.3
$5 / $15
215 Mistral Small 3.1 24BMistral AI
7.1
$0.35 / $0.56
216 Qwen3-VL-4B-ThinkingAlibaba
7.0
–
216 Nova Pro 1.0Amazon
7.0
$0.80 / $3.20
216 Command ACohere
7.0
$2.50 / $10
219 Qwen3.5-2B (reasoning on)Alibaba · best of 2 settings
6.9
–
219 Llama 3.1 8B InstructMeta
6.9
$0.05 / $0.08
221 Mistral Large 2 (2407)Mistral AI
6.8
$2 / $6
222 Qwen2.5-Coder-32B-InstructAlibaba
6.7
$0.66 / $1
222 Qwen3-4B-Instruct-2507Alibaba
6.7
–
222 Nova Lite 1.0Amazon
6.7
$0.06 / $0.24
222 Mistral Small 3Mistral AI
6.7
$0.05 / $0.08
222 GPT-4o mini (2024-07-18)OpenAI
6.7
$0.15 / $0.60
227 Llama 3.1 70B InstructMeta
6.6
$0.40 / $0.40
228 Qwen3.5-0.8B (reasoning on)Alibaba · best of 2 settings
6.1
–
229 Qwen3-Omni-30B-A3B-InstructAlibaba
6.0
–
229 Ministral 3 14BMistral AI
6.0
$0.20 / $0.20
231 Nova Micro 1.0Amazon
5.9
$0.035 / $0.14
231 Phi-4Microsoft
5.9
$0.07 / $0.14
233 Qwen3-VL-4B-InstructAlibaba
5.7
–
233 Llama 3.2 3B InstructMeta
5.7
$0.05 / $0.33
233 Mixtral 8x22B InstructMistral AI
5.7
$2 / $6
236 Reka Flash 3Reka AI
5.6
$0.10 / $0.20
237 Ministral 3 8BMistral AI
5.5
$0.15 / $0.15
238 Gemma 3 270MGoogle
5.1
–
239 Gemma 3 27BGoogle
4.9
$0.12 / $0.20
240 Gemma 3 4BGoogle
4.8
$0.05 / $0.10
240 Llama 3.2 1B InstructMeta
4.8
$0.027 / $0.20
240 Ministral 3 3BMistral AI
4.8
$0.10 / $0.10
243 Gemma 3 12BGoogle
3.8
$0.05 / $0.15

Swipe the table sideways for more columns.

Ranks follow the score as shown, so equal numbers share a rank. Each model is shown at its best setting; show every setting. Results as published by Artificial Analysis; we do not re-run them.

Progress over time

Artificial Analysis Intelligence Index, plotted at each model's release date, higher is better. Each model counts once, at its best setting. Scores are today's, not launch day's. Hover or tap a mark for its model.

Best score so far

Every model at its release date. The line moves each time a new release beats every earlier one, and each new best is named where there is room.

020406080 Jul 20242025Jul2026Jul GPT-4o (2024-05-13)GPT-4o (2024-08-06)o1Gemini 2.5 Proo3o3-proGrok 4GPT-5GPT-5-CodexClaude Opus 4.5GPT-5.2GPT-5.3-CodexGPT-5.4Claude Opus 4.8Claude Fable 5Claude Opus 5Claude Fable 5.1Claude Opus 5.5

Best score by lab

Each lab's best so far, stepping whenever one of its releases beats its own earlier models. The 6 labs with the best scores today; 18 others not drawn.

AnthropicOpenAIGoogleMetaxAIXiaomi

020406080 Jul 20242025Jul2026Jul AnthropicOpenAIGoogleMetaxAIXiaomi

What it measures

Artificial Analysis's blend of its reasoning, knowledge, coding and agent evaluations.

What it does not measure

Not business work, and a blend: read the parts for any one task.

Source

Artificial Analysis · Methodology

282 results from Artificial Analysis not ranked here · show why

We rank a result only when we can tie it to a specific model you can use. These are left out:

  • Not on sale through the API providers we track: 268
  • A different snapshot or variant from the model we list: 13
  • An unusual combination of settings: 1

Data sourced from Artificial Analysis. Licence: Artificial Analysis commercial data licence.