Benchmarks / Artificial Analysis

Reported by Artificial Analysis

Artificial Analysis

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

Last updated 20 Oct 2026

Results dated
20 Oct 2026
Results
413 configurations of 249 models
Unit
index score
Licence
Artificial Analysis commercial data licence

Artificial Analysis Intelligence Index: DeepSeek-V4.1-Flash-1017

Top 15 of 413 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 Opus 5.5 (extra-high reasoning)Anthropic 56.0
  3. 2 Claude Sonnet 5.5 (max reasoning)Anthropic 56.0
  4. 4 Claude Opus 5.5 (high reasoning)Anthropic 53.6
  5. 5 Claude Fable 5.1 (max reasoning)Anthropic 53.4
  6. 6 Claude Fable 5.1 (extra-high reasoning)Anthropic 53.2
  7. 7 GPT-6 Astra (max reasoning)OpenAI 52.7
  8. 8 Gemini 4 Argon (high reasoning)Google 52.6
  9. 9 Muse Wonder (max reasoning)Meta 52.4
  10. 9 GPT-6 Astra (extra-high reasoning)OpenAI 52.4
  11. 11 Claude Sonnet 5.5 (extra-high reasoning)Anthropic 51.9
  12. 12 GPT-6.1 Sol (max reasoning)OpenAI 51.8
  13. 13 Claude Fable 5.1 (high reasoning)Anthropic 51.2
  14. 13 Claude Opus 5.5 (medium reasoning)Anthropic 51.2
  15. 15 GPT-6.1 Sol (extra-high reasoning)OpenAI 51.0
  16. 35 DeepSeek-V4.1-Flash-1017 (max reasoning)DeepSeek 45.1

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
57.6
$4 / $20
2 Claude Opus 5.5 (extra-high reasoning)Anthropic
56.0
$4 / $20
2 Claude Sonnet 5.5 (max reasoning)Anthropic
56.0
$2 / $10
4 Claude Opus 5.5 (high reasoning)Anthropic
53.6
$4 / $20
5 Claude Fable 5.1 (max reasoning)Anthropic
53.4
$10 / $50
6 Claude Fable 5.1 (extra-high reasoning)Anthropic
53.2
$10 / $50
7 GPT-6 Astra (max reasoning)OpenAI
52.7
$10 / $50
8 Gemini 4 Argon (high reasoning)Google
52.6
$2 / $10
9 Muse Wonder (max reasoning)Meta
52.4
$4 / $20
9 GPT-6 Astra (extra-high reasoning)OpenAI
52.4
$10 / $50
11 Claude Sonnet 5.5 (extra-high reasoning)Anthropic
51.9
$2 / $10
12 GPT-6.1 Sol (max reasoning)OpenAI
51.8
$2 / $10
13 Claude Fable 5.1 (high reasoning)Anthropic
51.2
$10 / $50
13 Claude Opus 5.5 (medium reasoning)Anthropic
51.2
$4 / $20
15 GPT-6.1 Sol (extra-high reasoning)OpenAI
51.0
$2 / $10
16 GPT-6 Astra (high reasoning)OpenAI
50.9
$10 / $50
17 Claude Opus 5 (max reasoning)Anthropic
50.8
$5 / $25
18 GPT-6.1 Sol (high reasoning)OpenAI
50.2
$2 / $10
19 Claude Opus 5 (extra-high reasoning)Anthropic
49.7
$5 / $25
20 Claude Fable 5 (max reasoning)Anthropic
49.6
$10 / $50
20 GPT-6 Astra (medium reasoning)OpenAI
49.6
$10 / $50
22 Claude Fable 5.1 (medium reasoning)Anthropic
48.9
$10 / $50
23 Claude Opus 5 (high reasoning)Anthropic
48.1
$5 / $25
23 Muse Spark 1.3 (max reasoning)Meta
48.1
$1.25 / $4.25
25 GPT-6.1 Sol (medium reasoning)OpenAI
47.8
$2 / $10
26 GPT-6 Sol (max reasoning)OpenAI
47.6
$2 / $10
27 GPT-5.6 Sol (max reasoning)OpenAI
47.0
$4 / $20
28 Claude Fable 5.1 (low reasoning)Anthropic
46.8
$10 / $50
28 Claude Sonnet 5.5 (high reasoning)Anthropic
46.8
$2 / $10
30 Grok 4.7 (extra-high reasoning)xAI
46.4
$2 / $6
31 Grok 4.7 (high reasoning)xAI
46.3
$2 / $6
31 MiMo-V2.6-ProXiaomi
46.3
$0.43 / $0.87
33 GPT-6 Astra (low reasoning)OpenAI
45.8
$10 / $50
34 Qwen3.8-Max (0902)Alibaba
45.4
$2 / $6
35 DeepSeek-V4.1-Flash-1017 (max reasoning)DeepSeek
45.1
$0.30 / $1.20
35 Muse Spark 1.3 (extra-high reasoning)Meta
45.1
$1.25 / $4.25
37 Claude Opus 5 (medium reasoning)Anthropic
44.8
$5 / $25
37 GLM-5.3 (max reasoning)Z.ai
44.8
$1.40 / $4.40
39 Grok 4.6 (high reasoning)xAI
44.3
$2 / $6
40 GPT-6 Sol (extra-high reasoning)OpenAI
44.2
$2 / $10
40 Grok 4.6 (extra-high reasoning)xAI
44.2
$2 / $6
42 GPT-5.6 Sol (extra-high reasoning)OpenAI
44.0
$4 / $20
43 Kimi K3 (max reasoning)Moonshot AI
43.6
$3 / $15
44 Claude Haiku 5.5 (max reasoning)Anthropic
43.4
$0.10 / $0.50
45 Grok 4.6 (medium reasoning)xAI
42.8
$2 / $6
46 MiniMax M3.1 FlashMiniMax
42.4
$0.15 / $0.60
46 GPT-6 Sol (high reasoning)OpenAI
42.4
$2 / $10
48 Claude Opus 5.5 (low reasoning)Anthropic
42.3
$4 / $20
48 GPT-5.6 Sol (high reasoning)OpenAI
42.3
$4 / $20
50 Grok 4.7 (low reasoning)xAI
42.2
$2 / $6
51 GPT-5.6 Terra (max reasoning)OpenAI
42.1
$2 / $12
51 GPT-6.1 Sol (low reasoning)OpenAI
42.1
$2 / $10
53 Claude Opus 4.8 (max reasoning)Anthropic
41.8
$5 / $25
53 GLM-5.3-FlashZ.ai
41.8
$0.15 / $0.50
55 Claude Haiku 5.5 (extra-high reasoning)Anthropic
41.2
$0.10 / $0.50
56 Gemini 3.8 Flash (high reasoning)Google
40.9
$1.50 / $7.50
57 Claude Sonnet 5.5 (medium reasoning)Anthropic
40.8
$2 / $10
58 Claude Opus 4.7 (max reasoning)Anthropic
40.7
$5 / $25
59 Qwen3.8-Max (0803)Alibaba
40.2
–
60 Qwen3.8-2.4T-A95BAlibaba
39.9
$2 / $6
61 Qwen3.8-Flash-NextAlibaba
39.8
–
61 Gemini 3.8 Flash (medium reasoning)Google
39.8
$1.50 / $7.50
61 GPT-6 Sol (medium reasoning)OpenAI
39.8
$2 / $10
64 Gemini 3.7 Flash (medium reasoning)Google
39.6
$1.50 / $7.50
64 Muse Spark 1.2 (extra-high reasoning)Meta
39.6
$1.25 / $4.25
66 DeepSeek-V4.1-Flash (max reasoning)DeepSeek
39.5
$0.30 / $1.20
67 Claude Opus 5 (low reasoning)Anthropic
39.4
$5 / $25
68 GPT-5.6 Sol (medium reasoning)OpenAI
39.2
$4 / $20
69 Gemini 3.7 Flash (high reasoning)Google
39.1
$1.50 / $7.50
70 GPT-5.4 (extra-high reasoning)OpenAI
39.0
$2.50 / $15
71 Muse Spark Open (extra-high reasoning)Meta
38.9
–
72 Grok 4.5 (high reasoning)xAI
38.8
$2 / $6
73 Mistral Large 4Mistral AI
38.4
$1.36 / $4.18
73 GPT-5.5 (extra-high reasoning)OpenAI
38.4
$5 / $30
75 Claude Sonnet 5 (max reasoning)Anthropic
38.2
$2 / $10
76 GPT-6 Luna (max reasoning)OpenAI
38.1
$0.10 / $0.50
77 GPT-5.6 Terra (extra-high reasoning)OpenAI
38.0
$2 / $12
78 MiMo-V2.6-FlashXiaomi
37.9
$0.14 / $0.28
79 Claude Haiku 5.5 (high reasoning)Anthropic
37.8
$0.10 / $0.50
80 GPT-5.6 Luna (max reasoning)OpenAI
37.3
$0.20 / $1.20
81 GPT-5.5 (high reasoning)OpenAI
37.0
$5 / $30
82 Gemini 3.7 Flash (low reasoning)Google
36.9
$1.50 / $7.50
83 DeepSeek-V4-Pro (0813, max reasoning)DeepSeek
36.0
$1.32 / $3.96
84 Claude Sonnet 5.5 (low reasoning)Anthropic
35.9
$2 / $10
85 Grok 4.6 (low reasoning)xAI
35.1
$2 / $6
86 DeepSeek-V4-Flash-Vision-Exp (max reasoning)DeepSeek
34.8
$0.44 / $1.32
87 GPT-5.6 Luna (extra-high reasoning)OpenAI
34.6
$0.20 / $1.20
87 GPT-6 Luna (extra-high reasoning)OpenAI
34.6
$0.10 / $0.50
89 Claude Haiku 5.5 (medium reasoning)Anthropic
34.5
$0.10 / $0.50
90 Claude Sonnet 5 (extra-high reasoning)Anthropic
34.4
$2 / $10
91 DeepSeek-V4-Flash (0731, max reasoning)DeepSeek
34.3
$0.14 / $0.28
91 GLM-5.3 (low reasoning)Z.ai
34.3
$1.40 / $4.40
93 GPT-5.6 Terra (high reasoning)OpenAI
34.2
$2 / $12
93 GPT-6 Sol (low reasoning)OpenAI
34.2
$2 / $10
95 Gemini 3.6 Flash (high reasoning)Google
34.0
$1.50 / $7.50
96 GPT-5.5 (medium reasoning)OpenAI
33.8
$5 / $30
97 Qwen3.8-27B (extra-high reasoning)Alibaba
33.7
$0.50 / $3
97 Muse Spark 1.1 (extra-high reasoning)Meta
33.7
$1.25 / $4.25
97 GLM-5.2 (max reasoning)Z.ai
33.7
$1.40 / $4.40
100 Gemini 3.5 Flash (medium reasoning)Google
33.6
$1.50 / $9
101 Gemini 3.8 Flash (low reasoning)Google
33.5
$1.50 / $7.50
101 GPT-5.6 Sol (low reasoning)OpenAI
33.5
$4 / $20
103 GPT-6 Luna (high reasoning)OpenAI
32.9
$0.10 / $0.50
104 Gemini 3.5 Flash (high reasoning)Google
32.6
$1.50 / $9
105 GPT-5.3-Codex (extra-high reasoning)OpenAI
32.5
$1.75 / $14
106 GPT-5.6 Luna (high reasoning)OpenAI
32.1
$0.20 / $1.20
107 Claude Opus 4.6 (max reasoning)Anthropic
31.9
$5 / $25
108 Claude Sonnet 5 (high reasoning)Anthropic
31.7
$2 / $10
109 Muse SparkMeta
31.3
–
110 Claude Opus 4.7 (no reasoning)Anthropic
30.9
$5 / $25
111 GPT-5.5 (low reasoning)OpenAI
30.7
$5 / $30
112 DeepSeek-V4-Pro (0423, max reasoning)DeepSeek
30.4
$1.42 / $2.83
112 GPT-5.2 (extra-high reasoning)OpenAI
30.4
$1.75 / $14
114 Beam 1.0 501B A23BReflection
30.3
–
115 Claude Sonnet 4.6 (max reasoning)Anthropic
30.1
$3 / $15
115 DeepSeek-V4-Pro (0423, high reasoning)DeepSeek
30.1
$1.42 / $2.83
115 Kimi K3 (low reasoning)Moonshot AI
30.1
$3 / $15
115 GPT-5.6 Terra (medium reasoning)OpenAI
30.1
$2 / $12
119 GPT-6 Luna (medium reasoning)OpenAI
29.9
$0.10 / $0.50
120 Gemini 3.1 Pro PreviewGoogle
29.7
$2 / $12
121 Qwen3.7-MaxAlibaba
29.5
$1.48 / $4.42
121 Claude Haiku 5.5 (low reasoning)Anthropic
29.5
$0.10 / $0.50
123 MiniMax-M3MiniMax
29.2
$0.30 / $1.20
124 Claude Opus 4.5 (reasoning on)Anthropic
29.1
$5 / $25
125 GPT-5.2-Codex (extra-high reasoning)OpenAI
28.5
$1.75 / $14
125 GPT-6 Sol (no reasoning)OpenAI
28.5
$2 / $10
127 Qwen3.6-Max-PreviewAlibaba
28.4
$1.03 / $6.16
128 GPT-5.6 Sol (no reasoning)OpenAI
28.3
$4 / $20
129 Claude Sonnet 5 (medium reasoning)Anthropic
28.1
$2 / $10
130 Gemini 3 Pro Preview (high reasoning)Google
28.0
–
131 GLM-5Z.ai
27.9
$0.95 / $2.55
132 Qwen3.8-27B (medium reasoning)Alibaba
27.6
$0.50 / $3
132 GPT-5.4 (low reasoning)OpenAI
27.6
$2.50 / $15
134 GPT-5.6 Terra (low reasoning)OpenAI
27.5
$2 / $12
135 Grok Build 0.1xAI
27.2
$1 / $2
136 Qwen3.6-PlusAlibaba
27.0
$0.33 / $1.95
136 Kimi K2.6Moonshot AI
27.0
$0.95 / $4
138 Solar Pro 4Upstage
26.6
$0.09 / $0.36
138 GLM-5-TurboZ.ai
26.6
$1.20 / $4
140 Nemotron 3.5 Super VLNVIDIA
26.5
–
140 GPT-5.2 (medium reasoning)OpenAI
26.5
$1.75 / $14
142 Claude Opus 4.6 (no reasoning)Anthropic
26.4
$5 / $25
143 Gemini 3 Flash Preview (reasoning on)Google
26.3
$0.50 / $3
144 Qwen3.8-27B (low reasoning)Alibaba
26.2
$0.50 / $3
145 GLM-5.1Z.ai
26.1
$1.38 / $4.40
146 GPT-5.5 Instant (2026-06-26)OpenAI
26.0
–
146 MiMo-V2.5-Pro (reasoning on)Xiaomi
26.0
$0.43 / $0.87
148 Kimi K2.7 CodeMoonshot AI
25.8
$0.95 / $4
149 Inkling SmallThinking Machines
25.7
$0.45 / $1.20
149 Grok 4.20xAI
25.7
$1.25 / $2.50
151 Hy3Tencent
25.3
$0.14 / $0.58
152 Qwen3.7-PlusAlibaba
25.2
$0.32 / $1.28
152 Grok 4.20 (0309, reasoning)xAI
25.2
–
154 GPT-5.6 Luna (medium reasoning)OpenAI
25.0
$0.20 / $1.20
154 Inkling (extra-high reasoning)Thinking Machines
25.0
$0.95 / $4.05
156 GPT-5-Codex (high reasoning)OpenAI
24.9
–
156 Grok 4.3 (high reasoning)xAI
24.9
$1.25 / $2.50
158 Grok 4.3 (medium reasoning)xAI
24.8
$1.25 / $2.50
159 Claude Sonnet 4.6 (no reasoning)Anthropic
24.7
$3 / $15
159 DeepSeek-V4.1-Flash (no reasoning)DeepSeek
24.7
$0.30 / $1.20
159 GPT-5.1 (high reasoning)OpenAI
24.7
$1.25 / $10
162 DeepSeek-V4-Flash (0423, high reasoning)DeepSeek
24.4
$0.14 / $0.28
163 Claude Sonnet 5 (low reasoning)Anthropic
24.3
$2 / $10
163 Grok 4.3 (low reasoning)xAI
24.3
$1.25 / $2.50
165 DeepSeek-V4-Flash (0423, max reasoning)DeepSeek
24.2
$0.14 / $0.28
165 GLM-5.1 (no reasoning)Z.ai
24.2
$1.38 / $4.40
167 GPT-5.4 mini (extra-high reasoning)OpenAI
24.1
$0.75 / $4.50
168 Gemini 3.5 Flash (minimal reasoning)Google
23.8
$1.50 / $9
169 Claude Opus 4.5 (no reasoning)Anthropic
23.7
$5 / $25
169 GPT-5.1-Codex (high reasoning)OpenAI
23.7
$1.25 / $10
171 Kimi K2.6 (no reasoning)Moonshot AI
23.6
$0.95 / $4
172 Kimi K2.5Moonshot AI
23.5
$0.57 / $2.85
172 GLM-5V-TurboZ.ai
23.5
$1.20 / $4
174 Claude Sonnet 5 (no reasoning)Anthropic
23.2
$2 / $10
174 GPT-5.5 (no reasoning)OpenAI
23.2
$5 / $30
176 GPT-5 (high reasoning)OpenAI
23.0
$1.25 / $10
177 Qwen3.5-27BAlibaba
22.9
$0.27 / $2.16
177 GPT-5 (medium reasoning)OpenAI
22.9
$1.25 / $10
179 Claude Opus 4.1 (reasoning on)Anthropic
22.8
$15 / $75
179 MiniMax-M2.5MiniMax
22.8
$0.30 / $1.20
179 MiniMax-M2.7MiniMax
22.8
$0.30 / $1.20
182 GPT-5.5 Instant (2026-05-26)OpenAI
22.7
–
182 Hy3 Preview (reasoning on)Tencent
22.7
$0.18 / $0.60
184 Grok 4xAI
22.5
–
185 GLM-5.2 (no reasoning)Z.ai
22.4
$1.40 / $4.40
186 Gemini 3 Pro Preview (low reasoning)Google
22.3
–
187 Gemini 3.5 Flash-LiteGoogle
22.2
$0.30 / $2.50
187 GLM-4.7Z.ai
22.2
$0.54 / $1.98
189 Kimi K2 ThinkingMoonshot AI
22.0
$0.60 / $2.50
190 o3-proOpenAI
21.9
$20 / $80
191 MiMo-V2.5Xiaomi
21.8
$0.17 / $0.34
191 GLM-5 (no reasoning)Z.ai
21.8
$0.95 / $2.55
193 DeepSeek-V3.2 (reasoning on)DeepSeek
21.5
$0.30 / $0.96
193 GPT-6 Luna (low reasoning)OpenAI
21.5
$0.10 / $0.50
195 Qwen3.5-397B-A17B (no reasoning)Alibaba
21.4
$0.55 / $3.50
195 Qwen3.6-27BAlibaba
21.4
$0.30 / $3.20
197 Qwen3-Max-ThinkingAlibaba
21.3
$0.78 / $3.90
198 GPT-5.6 Luna (low reasoning)OpenAI
21.0
$0.20 / $1.20
199 MiniMax-M2.1MiniMax
20.9
$0.30 / $1.20
200 DeepSeek-V4-Pro (0423, no reasoning)DeepSeek
20.8
$1.42 / $2.83
200 GPT-5.6 Terra (no reasoning)OpenAI
20.8
$2 / $12
200 GPT-5 (low reasoning)OpenAI
20.8
$1.25 / $10
203 Claude Sonnet 4.5 (reasoning on)Anthropic
20.7
$3 / $15
203 GPT-5.4 nano (extra-high reasoning)OpenAI
20.7
$0.20 / $1.25
205 GPT-5 mini (medium reasoning)OpenAI
20.6
$0.25 / $2
206 Qwen3.5-Omni-PlusAlibaba
20.4
–
206 DeepSeek-V4-Pro (0813, no reasoning)DeepSeek
20.4
$1.32 / $3.96
206 GPT-5.1-Codex-Mini (high reasoning)OpenAI
20.4
$0.25 / $2
206 Grok 4.1 Fast (reasoning)xAI
20.4
–
210 Qwen3.8-27B (no reasoning)Alibaba
20.2
$0.50 / $3
210 o3OpenAI
20.2
$2 / $8
212 GPT-5.4 nano (medium reasoning)OpenAI
20.0
$0.20 / $1.25
213 Qwen3.6-27B (no reasoning)Alibaba
19.8
$0.30 / $3.20
214 GPT-5.4 mini (medium reasoning)OpenAI
19.7
$0.75 / $4.50
215 Qwen3.5-27B (no reasoning)Alibaba
19.4
$0.27 / $2.16
215 Kimi K2.5 (no reasoning)Moonshot AI
19.4
$0.57 / $2.85
217 Qwen3.5-35B-A3BAlibaba
19.3
$0.16 / $1.30
217 Claude Sonnet 4.5 (no reasoning)Anthropic
19.3
$3 / $15
219 Claude Sonnet 4 (reasoning on)Anthropic
18.9
$3 / $15
219 DeepSeek-V4-Flash (0423, no reasoning)DeepSeek
18.9
$0.14 / $0.28
221 Claude Opus 4.1 (no reasoning)Anthropic
18.6
$15 / $75
221 MiniMax-M2MiniMax
18.6
$0.30 / $1.20
223 GPT-6 Luna (no reasoning)OpenAI
18.5
$0.10 / $0.50
223 GLM-4.6 (reasoning on)Z.ai
18.5
$0.50 / $2
225 Qwen3.5-397B-A17BAlibaba
18.4
$0.55 / $3.50
226 MiMo-V2.5-Pro (no reasoning)Xiaomi
18.3
$0.43 / $0.87
227 Qwen3.6-35B-A3BAlibaba
18.2
$0.10 / $1
227 GPT-5.4 (no reasoning)OpenAI
18.2
$2.50 / $15
229 Gemini 3 Flash Preview (no reasoning)Google
17.9
$0.50 / $3
229 Grok 4 Fast (reasoning)xAI
17.9
–
231 Qwen3.5-122B-A10B (no reasoning)Alibaba
17.7
$0.26 / $2.08
232 Muse Glimmer (high reasoning)Meta
17.5
–
233 GLM-4.7 (no reasoning)Z.ai
17.4
$0.54 / $1.98
234 GPT-5.2 (no reasoning)OpenAI
17.0
$1.75 / $14
234 Hy3 Preview (no reasoning)Tencent
17.0
$0.18 / $0.60
236 Claude Haiku 4.5 (reasoning on)Anthropic
16.9
$1 / $5
237 GPT-5 mini (high reasoning)OpenAI
16.8
$0.25 / $2
238 Gemma 4 26B A4BGoogle
16.7
$0.10 / $0.30
238 o4-mini (high reasoning)OpenAI
16.7
$1.10 / $4.40
240 Claude Sonnet 4 (no reasoning)Anthropic
16.6
$3 / $15
240 DeepSeek-V3.2-Exp (reasoning on)DeepSeek
16.6
$0.27 / $0.41
240 Step 3.5 FlashStepFun
16.6
$0.10 / $0.30
243 Qwen3-Max-Thinking-PreviewAlibaba
16.3
–
244 Gemini 2.5 ProGoogle
16.1
$1.25 / $10
245 DeepSeek-V3.2 (no reasoning)DeepSeek
16.0
$0.30 / $0.96
246 Qwen3.5-122B-A10BAlibaba
15.6
$0.26 / $2.08
246 Qwen3-MaxAlibaba
15.6
$0.78 / $3.90
246 Gemini 3.1 Flash-Lite PreviewGoogle
15.6
$0.25 / $1.50
249 Gemini 2.5 Flash Preview (09-2025, reasoning on)Google
15.5
–
249 GPT-5.6 Luna (no reasoning)OpenAI
15.5
$0.20 / $1.20
251 Claude Haiku 4.5 (no reasoning)Anthropic
15.4
$1 / $5
252 Kimi K2 (0905)Moonshot AI
15.3
$0.60 / $2.50
253 Qwen3.6-35B-A3B (no reasoning)Alibaba
15.2
$0.10 / $1
253 o1OpenAI
15.2
$15 / $60
255 Qwen3.5-35B-A3B (no reasoning)Alibaba
15.1
$0.16 / $1.30
256 GLM-4.6 (no reasoning)Z.ai
14.9
$0.50 / $2
256 GLM-4.7-FlashZ.ai
14.9
$0.06 / $0.40
258 DeepSeek-V3.1-Terminus (reasoning on)DeepSeek
14.8
$0.27 / $1
259 Gemma 4 31BGoogle
14.7
$0.14 / $0.40
260 Grok 4.20 (0309, non-reasoning, no reasoning)xAI
14.6
–
261 DeepSeek-V3.2-SpecialeDeepSeek
14.5
–
262 Gemma 4 12BGoogle
14.2
–
262 Mistral Medium 3.5Mistral AI
14.2
$1.50 / $7.50
262 Grok 4.20 (no reasoning)xAI
14.2
$1.25 / $2.50
265 Grok Code Fast 1xAI
14.1
–
266 Grok 4.3 (no reasoning)xAI
14.0
$1.25 / $2.50
267 DeepSeek-V3.1-Terminus (no reasoning)DeepSeek
13.9
$0.27 / $1
267 DeepSeek-V3.2-Exp (no reasoning)DeepSeek
13.9
$0.27 / $0.41
267 Gemma 4 31B (no reasoning)Google
13.9
$0.14 / $0.40
270 DeepSeek-V3.1 (no reasoning)DeepSeek
13.7
$0.55 / $1.65
271 DeepSeek-V3.1 (reasoning on)DeepSeek
13.5
$0.55 / $1.65
272 Qwen3-VL-235B-A22B-ThinkingAlibaba
13.4
$0.40 / $4
272 Nova 2 Lite (high reasoning)Amazon
13.4
$0.30 / $2.50
274 Qwen3.5-9B (no reasoning)Alibaba
13.3
$0.10 / $0.15
274 GPT-5.1 (no reasoning)OpenAI
13.3
$1.25 / $10
276 Qwen3.5-4B (reasoning on)Alibaba
13.1
–
276 DeepSeek-R1-0528DeepSeek
13.1
$0.50 / $2.18
276 Gemini 2.5 Flash (reasoning on)Google
13.1
$0.30 / $2.50
276 Gemma 4 26B A4B (no reasoning)Google
13.1
$0.10 / $0.30
280 GPT-5 nano (high reasoning)OpenAI
13.0
$0.05 / $0.40
281 Nemotron 3 Super 120B A12BNVIDIA
12.8
$0.085 / $0.40
281 GLM-4.5Z.ai
12.8
$0.60 / $2.20
283 Qwen3-235B-A22B-Thinking-2507Alibaba
12.7
$0.30 / $3
283 Kimi K2 (0711)Moonshot AI
12.7
$0.57 / $2.30
283 GPT-4.1OpenAI
12.7
$2 / $8
286 Qwen3-Max-PreviewAlibaba
12.6
–
287 Qwen3.5-Omni-FlashAlibaba
12.5
–
287 Nova 2 Lite (medium reasoning)Amazon
12.5
$0.30 / $2.50
287 GPT-5 nano (medium reasoning)OpenAI
12.5
$0.05 / $0.40
287 o3-miniOpenAI
12.5
$1.10 / $4.40
291 Gemini 2.5 Flash Preview (09-2025, no reasoning)Google
12.4
–
292 Qwen3-235B-A22B-Instruct-2507Alibaba
12.0
$0.15 / $0.75
293 Qwen3-Coder-480B-A35BAlibaba
11.9
$0.35 / $1.50
293 Qwen3-VL-32B-ThinkingAlibaba
11.9
–
295 Nova 2 Lite (low reasoning)Amazon
11.8
$0.30 / $2.50
295 Magistral Medium 1.2Mistral AI
11.8
–
297 GPT-5.4 nano (no reasoning)OpenAI
11.7
$0.20 / $1.25
298 gpt-oss-120b (high reasoning)OpenAI
11.6
$0.15 / $0.60
299 DeepSeek-R1DeepSeek
11.4
$0.70 / $2.50
299 GPT-5 (minimal reasoning)OpenAI
11.4
$1.25 / $10
301 Mistral Small 4Mistral AI
11.3
$0.15 / $0.60
301 Grok 4.1 Fast (non-reasoning, no reasoning)xAI
11.3
–
303 Qwen3.5-9BAlibaba
11.2
$0.10 / $0.15
303 Qwen3-Next-80B-A3B-ThinkingAlibaba
11.2
$0.15 / $1.20
303 GLM-4.6V (reasoning on)Z.ai
11.2
$0.30 / $0.90
306 Granite 4.2 8BIBM
11.1
$0.06 / $0.25
306 GPT-5.4 mini (no reasoning)OpenAI
11.1
$0.75 / $4.50
306 Grok 4 Fast (non-reasoning, no reasoning)xAI
11.1
–
306 GLM-4.5-AirZ.ai
11.1
$0.14 / $0.86
310 o3-mini (high reasoning)OpenAI
11.0
$1.10 / $4.40
311 Qwen3.5-4B (no reasoning)Alibaba
10.8
–
311 Trinity Large ThinkingArcee AI
10.8
$0.25 / $0.80
311 Mercury 2Inception
10.8
$0.25 / $0.75
314 GLM-4.7-Flash (no reasoning)Z.ai
10.6
$0.06 / $0.40
315 Gemini 2.5 Flash-Lite Preview (09-2025, reasoning on)Google
10.4
–
315 GPT-5 ChatOpenAI
10.4
–
317 GPT-4.1 miniOpenAI
10.2
$0.40 / $1.60
317 gpt-oss-120b (low reasoning)OpenAI
10.2
$0.15 / $0.60
319 gpt-oss-20b (low reasoning)OpenAI
10.0
$0.03 / $0.15
320 Qwen3-VL-235B-A22B-InstructAlibaba
9.9
$0.30 / $1.50
320 Gemini 2.5 Flash (no reasoning)Google
9.9
$0.30 / $2.50
320 GPT-5 mini (minimal reasoning)OpenAI
9.9
$0.25 / $2
323 Qwen3-30B-A3B-Thinking-2507Alibaba
9.8
$0.20 / $2.40
324 DeepSeek-V3-0324DeepSeek
9.7
$0.25 / $1
325 Qwen3-Coder-30B-A3B-InstructAlibaba
9.6
$0.07 / $0.28
325 Qwen3-Next-80B-A3B-InstructAlibaba
9.6
$0.10 / $1.10
327 Qwen3-235B-A22B (reasoning on)Alibaba
9.5
$0.46 / $1.82
327 Qwen3-VL-30B-A3B-ThinkingAlibaba
9.5
$0.29 / $1
327 DiffusionGemma 26B A4BGoogle
9.5
–
330 Gemma 4 12B (no reasoning)Google
9.4
–
331 Gemini 2.5 Flash-Lite Preview (09-2025, no reasoning)Google
9.3
–
331 Llama 4 MaverickMeta
9.3
$0.27 / $0.85
331 Mistral Large 3Mistral AI
9.3
$0.50 / $1.50
334 Qwen3-Coder-NextAlibaba
9.2
$0.18 / $0.90
334 Mistral Medium 3.1Mistral AI
9.2
$0.40 / $2
336 Devstral MediumMistral AI
9.0
–
336 Mistral Medium 3Mistral AI
9.0
$0.40 / $2
336 Mistral Small 4 (no reasoning)Mistral AI
9.0
$0.15 / $0.60
336 gpt-oss-20b (high reasoning)OpenAI
9.0
$0.03 / $0.15
340 Gemma 4 E4BGoogle
8.9
–
340 Nemotron 3 Nano 30B A3B (reasoning on)NVIDIA
8.9
$0.05 / $0.20
342 Qwen3-4B-Thinking-2507Alibaba
8.8
–
343 Nova 2 Lite (no reasoning)Amazon
8.7
$0.30 / $2.50
344 Devstral 2Mistral AI
8.6
$0.40 / $2
344 Magistral Small 1.2Mistral AI
8.6
–
346 DeepSeek-V3DeepSeek
8.5
$0.26 / $1.03
346 Gemini 2.5 Flash-Lite (reasoning on)Google
8.5
$0.10 / $0.40
348 Qwen3-VL-32B-InstructAlibaba
8.4
$0.10 / $0.42
348 GLM-4.6V (no reasoning)Z.ai
8.4
$0.30 / $0.90
350 Qwen3-235B-A22B (no reasoning)Alibaba
8.3
$0.46 / $1.82
351 Qwen3-VL-8B-ThinkingAlibaba
8.2
$0.18 / $2.10
352 Qwen3-VL-30B-A3B-InstructAlibaba
7.9
$0.15 / $0.60
353 Qwen3-Omni-30B-A3B-ThinkingAlibaba
7.8
–
353 Gemma 4 E2BGoogle
7.8
–
353 GPT-4.1 nanoOpenAI
7.8
$0.10 / $0.40
353 Solar Pro 3Upstage
7.8
$0.15 / $0.60
357 Qwen2.5-72B-InstructAlibaba
7.7
$0.36 / $0.40
357 Llama 3.3 70B InstructMeta
7.7
$0.59 / $0.79
357 GPT-4o (2024-08-06)OpenAI
7.7
$2.50 / $10
360 Qwen3-30B-A3B (reasoning on)Alibaba
7.6
$0.12 / $0.50
360 Devstral Small 1.1Mistral AI
7.6
–
360 GLM-4.5V (reasoning on)Z.ai
7.6
$0.60 / $1.80
363 Qwen3-30B-A3B-Instruct-2507Alibaba
7.5
$0.09 / $0.30
363 Gemma 4 E4B (no reasoning)Google
7.5
–
363 Devstral Small 2Mistral AI
7.5
–
366 Qwen3-32B (no reasoning)Alibaba
7.3
$0.14 / $0.40
366 Qwen3-VL-8B-InstructAlibaba
7.3
$0.12 / $0.46
366 Kimi Linear 48B A3B InstructMoonshot AI
7.3
–
366 GPT-4o (2024-05-13)OpenAI
7.3
$5 / $15
370 Qwen3-32B (reasoning on)Alibaba
7.2
$0.14 / $0.40
371 Mistral Small 3.1 24BMistral AI
7.1
$0.35 / $0.56
371 GPT-5 nano (minimal reasoning)OpenAI
7.1
$0.05 / $0.40
373 Qwen3-VL-4B-ThinkingAlibaba
7.0
–
373 Nova Pro 1.0Amazon
7.0
$0.80 / $3.20
373 Command ACohere
7.0
$2.50 / $10
373 Mistral Small 3.2 24BMistral AI
7.0
$0.094 / $0.25
377 Qwen3.5-2B (reasoning on)Alibaba
6.9
–
377 Llama 3.1 8B InstructMeta
6.9
$0.05 / $0.08
379 Mistral Large 2 (2407)Mistral AI
6.8
$2 / $6
379 Nemotron 3 Nano 30B A3B (no reasoning)NVIDIA
6.8
$0.05 / $0.20
381 Qwen2.5-Coder-32B-InstructAlibaba
6.7
$0.66 / $1
381 Qwen3-14B (no reasoning)Alibaba
6.7
$0.12 / $0.24
381 Qwen3-4B-Instruct-2507Alibaba
6.7
–
381 Nova Lite 1.0Amazon
6.7
$0.06 / $0.24
381 Gemini 2.5 Flash-Lite (no reasoning)Google
6.7
$0.10 / $0.40
381 Mistral Small 3Mistral AI
6.7
$0.05 / $0.08
381 GPT-4o mini (2024-07-18)OpenAI
6.7
$0.15 / $0.60
381 GLM-4.5V (no reasoning)Z.ai
6.7
$0.60 / $1.80
389 Qwen3-30B-A3B (no reasoning)Alibaba
6.6
$0.12 / $0.50
389 Llama 3.1 70B InstructMeta
6.6
$0.40 / $0.40
391 Gemma 4 E2B (no reasoning)Google
6.5
–
391 Llama 4 ScoutMeta
6.5
$0.18 / $0.59
393 Qwen3-14B (reasoning on)Alibaba
6.4
$0.12 / $0.24
394 Qwen3.5-2B (no reasoning)Alibaba
6.2
–
395 Qwen3.5-0.8B (reasoning on)Alibaba
6.1
–
396 Qwen3-8B (no reasoning)Alibaba
6.0
$0.12 / $0.46
396 Qwen3-Omni-30B-A3B-InstructAlibaba
6.0
–
396 Ministral 3 14BMistral AI
6.0
$0.20 / $0.20
399 Nova Micro 1.0Amazon
5.9
$0.035 / $0.14
399 Phi-4Microsoft
5.9
$0.07 / $0.14
401 Qwen3-VL-4B-InstructAlibaba
5.7
–
401 Llama 3.2 3B InstructMeta
5.7
$0.05 / $0.33
401 Mixtral 8x22B InstructMistral AI
5.7
$2 / $6
404 Reka Flash 3Reka AI
5.6
$0.10 / $0.20
405 Ministral 3 8BMistral AI
5.5
$0.15 / $0.15
406 Qwen3.5-0.8B (no reasoning)Alibaba
5.4
–
407 Qwen3-8B (reasoning on)Alibaba
5.2
$0.12 / $0.46
408 Gemma 3 270MGoogle
5.1
–
409 Gemma 3 27BGoogle
4.9
$0.12 / $0.20
410 Gemma 3 4BGoogle
4.8
$0.05 / $0.10
410 Llama 3.2 1B InstructMeta
4.8
$0.027 / $0.20
410 Ministral 3 3BMistral AI
4.8
$0.10 / $0.10
413 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. 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-proGPT-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; 19 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

285 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: 270
  • A different snapshot or variant from the model we list: 14
  • An unusual combination of settings: 1

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