Confirm Action

Are you sure you want to proceed?

Artificial Analysis · Intelligence Index v4.1

Results through 2026-07-30

Artificial Analysis Intelligence Index benchmark: model scores and methodology

A composite index of language-model performance across agentic work, coding, scientific reasoning, knowledge, and long-context reasoning.

Current published leader
Claude Opus 5 · Adaptive Reasoning, Max Effort
Top score
61
Primary metric
Intelligence Index · higher is better
Evaluation subject
Model configuration in Artificial Analysis's evaluation system
See model scores How scoring works Official methodology ↗

Artificial Analysis public leaderboard snapshot

All current Artificial Analysis Intelligence Index model scores

249 configurations · 181 model entries

This reviewed Artificial Analysis snapshot · 30 July 2026 contains 249 current configurations with a reported Artificial Analysis Intelligence Index score. Figures are the rounded values displayed by Artificial Analysis; underlying source precision is retained in SQLite.

Leading models on Artificial Analysis Intelligence Index

The chart shows the 20 highest current configurations in this one Artificial Analysis snapshot. One mark per model, at its strongest published configuration. Score labels reproduce Artificial Analysis's rounded display value.

  1. Claude Opus 5 61
  2. Claude Fable 5 Adaptive Reasoning, Max Effort, Opus 4.8 Fallback 60
  3. GPT-5.6 Sol 59
  4. Kimi K3 57
  5. GPT-5.6 Terra 55
  6. Grok 4.5 54
  7. Claude Sonnet 5 Adaptive Reasoning, Max Effort 53
  8. GPT-5.6 Luna 51
  9. GLM-5.2 max 51
  10. Muse Spark 1.1 xhigh 51
  11. Gemini 3.5 Flash high 50
  12. Gemini 3.6 Flash high 50
  13. Gemini 3.1 Pro (Preview) 46
  14. Qwen3.7 Max 46
  15. MiniMax-M3 44
  16. DeepSeek V4 Pro Reasoning, Max Effort 44
  17. GPT-5.3 Codex xhigh 44*
  18. Motif 3 Beta 44
  19. Muse Spark 43
  20. MiMo-V2.5-Pro 42
0.0 30.3 60.7

Intelligence Index · higher is better

Current configurations with a reported Artificial Analysis Intelligence Index value; missing values are omitted.

How to interpret the result

What do Artificial Analysis Intelligence Index results mean?

Treat each row as a result for the named model configuration inside Artificial Analysis's evaluation setup, not as a property of bare model weights.

1. Read the displayed figure

Higher intelligence index is better. The public table rounds the displayed score, while Springprompt retains the source precision.

2. Check the evaluated system

The score depends on the model configuration, Artificial Analysis harness, tools, task budget, repeats, and scoring protocol.

3. Compare within one contract

Use rows from this same field and snapshot for the cleanest comparison. Do not merge vendor-reported or differently harnessed scores into this table.

The leaderboard is decision evidence, not a universal model ranking: match the benchmark contract to the work you actually need done.

Read Artificial Analysis Intelligence Index as a result of Artificial Analysis's evaluated model configuration and methodology—not as a context-free model property.

Every row comes from Artificial Analysis snapshot · 30 July 2026, recorded 30 Jul 2026.

#ModelConfigurationIntelligence Index
1 Claude Opus 5Leader Adaptive Reasoning, Max Effort 61
2 Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) Adaptive Reasoning, Xhigh Effort 60
3 Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) Adaptive Reasoning, Max Effort, Opus 4.8 Fallback 60
4 GPT-5.6 Sol max 59
5 Claude Opus 5 (Adaptive Reasoning, High Effort) Adaptive Reasoning, High Effort 59
6 GPT-5.6 Sol (xhigh) xhigh 58
7 Kimi K3 Published configuration 57
8 Claude Opus 5 (Adaptive Reasoning, Medium Effort) Adaptive Reasoning, Medium Effort 56
9 GPT-5.6 Sol (high) high 56
10 GPT-5.6 Terra max 55
11 Grok 4.5 high 54
12 GPT-5.6 Sol (medium) medium 54
13 Claude Sonnet 5 (Adaptive Reasoning, Max Effort) Adaptive Reasoning, Max Effort 53
14 GPT-5.6 Terra (xhigh) xhigh 52
15 GPT-5.6 Luna max 51
16 GLM-5.2 (max) max 51
17 Muse Spark 1.1 (xhigh) xhigh 51
18 Claude Opus 5 (Adaptive Reasoning, Low Effort) Adaptive Reasoning, Low Effort 51
19 Gemini 3.5 Flash (high) high 50
20 Gemini 3.6 Flash (high) high 50
21 GPT-5.6 Sol (low) low 49
22 GPT-5.6 Luna (xhigh) xhigh 49
23 GPT-5.6 Terra (high) high 49
24 Gemini 3.1 Pro (Preview) Published configuration 46
25 GPT-5.6 Luna (high) high 46
Show the remaining 224 configurations
#ModelConfigurationIntelligence Index
26 Qwen3.7 Max Published configuration 46
27 GPT-5.6 Terra (medium) medium 46
28 Gemini 3.5 Flash (medium)AA estimate medium 45*
29 MiniMax-M3 Published configuration 44
30 DeepSeek V4 Pro (Reasoning, Max Effort) Reasoning, Max Effort 44
31 GPT-5.3 Codex (xhigh)AA estimate xhigh 44*
32 Motif 3 (Beta) Beta 44
33 DeepSeek V4 Pro (Reasoning, High Effort) Reasoning, High Effort 43
34 Muse Spark Published configuration 43
35 MiMo-V2.5-Pro Published configuration 42
36 Kimi K2.7 Code Published configuration 42
37 Claude Sonnet 5 (Non-reasoning, High Effort) Non-reasoning, High Effort 42
38 Hy3 Published configuration 41
39 GPT-5.6 Sol (Non-reasoning) Non-reasoning 41
40 Nex-N2-Pro Published configuration 41
41 Inkling (xhigh) xhigh 41
42 GPT-5.6 Terra (low) low 40
43 DeepSeek V4 Flash (Reasoning, Max Effort) Reasoning, Max Effort 40
44 Qwen3.6 Plus Published configuration 40
45 Qwen3.7 Plus Published configuration 39
46 JT-4.1 Flash 236B A21B Published configuration 39
47 Agnes 2.5 Pro Alpha Published configuration 39
48 GPT-5.6 Luna (medium) medium 38
49 Nemotron 3 Ultra 550B A55B (Reasoning) Reasoning 38
50 DeepSeek V4 Flash (Reasoning, High Effort) Reasoning, High Effort 37
51 MiMo-V2.5 Published configuration 37
52 Qwen3.6 27B (Reasoning) Reasoning 37
53 Gemini 3.5 Flash-Lite Published configuration 36
54 MiMo-V2-Omni-0327AA estimate Published configuration 36*
55 Grok 4.3 (medium)AA estimate medium 36*
56 Grok 4.3 (low)AA estimate low 35*
57 MiMo-V2-OmniAA estimate Published configuration 35*
58 Gemini 3.5 Flash (minimal)AA estimate minimal 35*
59 Kimi K2.6 (Non-reasoning)AA estimate Non-reasoning 35*
60 Claude Sonnet 4.6 (Non-reasoning, Low Effort)AA estimate Non-reasoning, Low Effort 34*
61 GLM-5.2 (Non-reasoning) Non-reasoning 34
62 GPT-5.6 Terra (Non-reasoning) Non-reasoning 34
63 KAT Coder Pro V2 Published configuration 34
64 Qwen3.5 397B A17B (Reasoning) Reasoning 34
65 Hy3-preview (Reasoning)AA estimate Reasoning 34*
66 LongCat 2.0 Published configuration 33
67 GPT-5.6 Luna (low) low 33
68 MiMo-V2-Flash (Feb 2026)AA estimate Feb 2026 33*
69 Qwen3.5 122B A10B (Reasoning) Reasoning 32
70 Qwen3.5 397B A17B (Non-reasoning)AA estimate Non-reasoning 32*
71 Qwen3.6 35B A3B (Reasoning) Reasoning 32
72 DeepSeek V4 Pro (Non-reasoning)AA estimate Non-reasoning 31*
73 Qwen3.5 Omni PlusAA estimate Published configuration 31*
74 Ring-2.6-1T Published configuration 31
75 Qwen3.6 27B (Non-reasoning) Non-reasoning 30
76 o3AA estimate Published configuration 30*
77 Step 3.7 Flash Published configuration 30
78 Mistral Medium 3.5 Published configuration 30
79 Claude 4.5 Haiku (Reasoning) Reasoning 30
80 Gemma 4 31B (Reasoning) Reasoning 29
81 GPT-5.5 Instant (June 2026) June 2026 29
82 DeepSeek V4 Flash (Non-reasoning)AA estimate Non-reasoning 29*
83 JT-35B-FlashAA estimate Published configuration 28*
84 KAT-Coder-Pro V1AA estimate Published configuration 28*
85 MiMo-V2.5-Pro (Non-reasoning)AA estimate Non-reasoning 28*
86 Qwen3.5 122B A10B (Non-reasoning) Non-reasoning 28
87 GPT-5.6 Luna (Non-reasoning) Non-reasoning 27
88 Hy3-preview (Non-reasoning)AA estimate Non-reasoning 26*
89 Ling-2.6-1TAA estimate Published configuration 26*
90 Doubao Seed CodeAA estimate Published configuration 26*
91 Gemini 2.5 Pro Published configuration 26
92 Gemma 4 26B A4B (Reasoning) Reasoning 26
93 NVIDIA Nemotron 3 Super 120B A12B (Reasoning) Reasoning 25
94 Gemini 3.1 Flash-Lite Published configuration 25
95 Grok 4.3 (Non-reasoning) Non-reasoning 25
96 MiMo-V2-Flash (Non-reasoning) Non-reasoning 25
97 Qwen3.6 35B A3B (Non-reasoning) Non-reasoning 24
98 Qwen3.5 35B A3B (Non-reasoning) Non-reasoning 24
99 gpt-oss-120b (high) high 24
100 Claude 4.5 Haiku (Non-reasoning)AA estimate Non-reasoning 24*
101 Command A+ Published configuration 23
102 K-EXAONE (Reasoning) Reasoning 22
103 ERNIE 5.0 Thinking PreviewAA estimate Published configuration 22*
104 Gemma 4 12B (Reasoning) Reasoning 22
105 Gemma 4 31B (Non-reasoning) Non-reasoning 22
106 Nova 2.0 Pro Preview (medium) medium 22
107 Qwen3.5 9B (Reasoning) Reasoning 21
108 Mercury 2 Published configuration 21
109 Qwen3 Coder Next Published configuration 21
110 Nova 2.0 Omni (medium)AA estimate medium 21*
111 Apriel-v1.6-15B-ThinkerAA estimate Published configuration 21*
112 Qwen3.5 9B (Non-reasoning)AA estimate Non-reasoning 20*
113 EXAONE 4.5 33B Published configuration 20
114 Gemma 4 26B A4B (Non-reasoning)AA estimate Non-reasoning 20*
115 Qwen3.5 4B (Reasoning)AA estimate Reasoning 20*
116 North Mini Code Published configuration 20
117 Nova 2.0 Pro Preview (low) low 20
118 Mistral Small 4 (Reasoning) Reasoning 20
119 Devstral 2 Published configuration 19
120 Nova 2.0 Lite (medium)AA estimate medium 19*
121 Qwen3.5 Omni FlashAA estimate Published configuration 19*
122 JT-MINIAA estimate Published configuration 19*
123 Nova 2.0 Lite (high) high 18
124 Trinity Large Thinking Published configuration 18
125 Magistral Medium 1.2 Published configuration 18
126 Nova 2.0 Lite (low)AA estimate low 18*
127 HyperNova 60B 2605 Published configuration 18
128 Nemotron Cascade 2 30B A3B Published configuration 18
129 Devstral Small 2 Published configuration 17
130 K2 Think V2 Published configuration 17
131 LongCat Flash LiteAA estimate Published configuration 17*
132 HyperCLOVA X SEED Think (32B)AA estimate 32B 17*
133 K-EXAONE (Non-reasoning)AA estimate Non-reasoning 17*
134 Qwen3 Next 80B A3B (Reasoning) Reasoning 17
135 Nova 2.0 Omni (low)AA estimate low 17*
136 Mi:dm K 2.5 ProAA estimate Published configuration 16*
137 G9v3-3B Published configuration 16
138 Qwen3.5 4B (Non-reasoning)AA estimate Non-reasoning 16*
139 Mistral Large 3 Published configuration 16
140 INTELLECT-3AA estimate Published configuration 16*
141 Solar Open 100B (Reasoning)AA estimate Reasoning 15*
142 Nemotron 3 Nano Omni 30B A3B ReasoningAA estimate Published configuration 15*
143 gpt-oss-120b (low) low 15
144 gpt-oss-20b (high) high 15
145 Nova 2.0 Pro Preview (Non-reasoning) Non-reasoning 14
146 gpt-oss-20b (low)AA estimate low 14*
147 Llama 4 Maverick Published configuration 14
148 K2-V2 (high)AA estimate high 14*
149 NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) Reasoning 14
150 Solar Pro 3 Published configuration 14
151 Ling 2.6 Flash Published configuration 14
152 Qwen3 Next 80B A3B InstructAA estimate Published configuration 14*
153 DiffusionGemma 26B A4B Published configuration 13
154 Gemma 4 12B (Non-reasoning)AA estimate Non-reasoning 13*
155 Motif-2-12.7B-ReasoningAA estimate Published configuration 13*
156 Nova PremierAA estimate Published configuration 13*
157 K2-V2 (medium)AA estimate medium 12*
158 Llama Nemotron Super 49B v1.5 (Reasoning)AA estimate Reasoning 12*
159 Mistral Small 4 (Non-reasoning)AA estimate Non-reasoning 12*
160 Tri-21B-ThinkAA estimate Published configuration 12*
161 MiniCPM5-1B (Reasoning)AA estimate Reasoning 12*
162 Sarvam 105B (high)AA estimate high 12*
163 Gemma 4 E4B (Reasoning) Reasoning 12
164 Nova 2.0 Lite (Non-reasoning)AA estimate Non-reasoning 12*
165 MiniCPM5-1B (Non-reasoning)AA estimate Non-reasoning 12*
166 Magistral Small 1.2 Published configuration 11
167 Nanbeige4.1-3B Published configuration 11
168 Ministral 3 14B Published configuration 11
169 EXAONE 4.0 32B (Reasoning)AA estimate Reasoning 11*
170 Nova 2.0 Omni (Non-reasoning)AA estimate Non-reasoning 11*
171 Llama 4 Scout Published configuration 10
172 Hermes 4 - Llama-3.1 70B (Reasoning)AA estimate Reasoning 10*
173 Falcon-H1R-7BAA estimate Published configuration 10*
174 Qwen3 Omni 30B A3B (Reasoning)AA estimate Reasoning 10*
175 Step3 VL 10BAA estimate Published configuration 9*
176 Gemma 4 E2B (Reasoning) Reasoning 9
177 Llama 3.3 Instruct 70B Published configuration 9
178 Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)AA estimate Reasoning 9*
179 ERNIE 4.5 300B A47BAA estimate Published configuration 9*
180 Hermes 4 - Llama-3.1 405B (Reasoning)AA estimate Reasoning 9*
181 NVIDIA Nemotron Nano 12B v2 VL (Reasoning)AA estimate Reasoning 9*
182 Ministral 3 8B Published configuration 9
183 Gemma 4 E4B (Non-reasoning)AA estimate Non-reasoning 9*
184 Granite 4.1 30B Published configuration 9
185 NVIDIA Nemotron Nano 9B V2 (Reasoning)AA estimate Reasoning 9*
186 Hermes 4 - Llama-3.1 405B (Non-reasoning)AA estimate Non-reasoning 9*
187 NVIDIA Nemotron 3 Nano 4B Published configuration 9
188 Llama Nemotron Super 49B v1.5 (Non-reasoning)AA estimate Non-reasoning 9*
189 K2-V2 (low)AA estimate low 9*
190 Kimi Linear 48B A3B InstructAA estimate Published configuration 9*
191 Llama 3.1 Instruct 405BAA estimate Published configuration 8*
192 LFM2.5-8B-A1BAA estimate Published configuration 8*
193 Ring-flash-2.0AA estimate Published configuration 8*
194 Olmo 3.1 32B ThinkAA estimate Published configuration 8*
195 Command AAA estimate Published configuration 8*
196 Llama 3.1 Nemotron Instruct 70BAA estimate Published configuration 8*
197 NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)AA estimate Non-reasoning 7*
198 NVIDIA Nemotron Nano 9B V2 (Non-reasoning)AA estimate Non-reasoning 7*
199 Qwen3.5 2B (Reasoning) Reasoning 7
200 Hermes 4 - Llama-3.1 70B (Non-reasoning)AA estimate Non-reasoning 7*
201 Granite 4.1 8BAA estimate Published configuration 7*
202 Sarvam 30B (high)AA estimate high 7*
203 Olmo 3.1 32B InstructAA estimate Published configuration 6*
204 Gemma 4 E2B (Non-reasoning)AA estimate Non-reasoning 6*
205 R1 1776AA estimate Published configuration 6*
206 Ministral 3 3B Published configuration 6
207 Llama 3.2 Instruct 90B (Vision)AA estimate Vision 6*
208 Phi-4 Mini Instruct Published configuration 6
209 EXAONE 4.0 32B (Non-reasoning)AA estimate Non-reasoning 6*
210 Qwen3.5 2B (Non-reasoning) Non-reasoning 6
211 Qwen3.5 0.8B (Reasoning) Reasoning 5
212 DeepHermes 3 - Mistral 24B Preview (Non-reasoning)AA estimate Non-reasoning 5*
213 Jamba 1.7 LargeAA estimate Published configuration 5*
214 Granite 4.0 H SmallAA estimate Published configuration 5*
215 Qwen3 Omni 30B A3B InstructAA estimate Published configuration 5*
216 LFM2 24B A2BAA estimate Published configuration 5*
217 Phi-4AA estimate Published configuration 5*
218 Nova MicroAA estimate Published configuration 5*
219 Granite 4.1 3B Published configuration 5
220 NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)AA estimate Non-reasoning 5*
221 Phi-4 Multimodal InstructAA estimate Published configuration 5*
222 MiniCPM-V 4.6 1.3B Published configuration 4
223 Jamba Reasoning 3BAA estimate Published configuration 4*
224 Reka Flash 3AA estimate Published configuration 4*
225 Olmo 3 7B ThinkAA estimate Published configuration 4*
226 Molmo 7B-DAA estimate Published configuration 4*
227 Ling-mini-2.0AA estimate Published configuration 4*
228 Llama 3.2 Instruct 11B (Vision)AA estimate Vision 3*
229 Qwen3.5 0.8B (Non-reasoning) Non-reasoning 3
230 Exaone 4.0 1.2B (Reasoning)AA estimate Reasoning 3*
231 Olmo 3 7B InstructAA estimate Published configuration 3*
232 Exaone 4.0 1.2B (Non-reasoning)AA estimate Non-reasoning 3*
233 LFM2.5-1.2B-ThinkingAA estimate Published configuration 3*
234 Jamba 1.7 MiniAA estimate Published configuration 3*
235 LFM2 2.6BAA estimate Published configuration 3*
236 LFM2.5-1.2B-InstructAA estimate Published configuration 3*
237 Granite 4.0 H 1BAA estimate Published configuration 3*
238 Gemma 3 270MAA estimate Published configuration 2*
239 Apertus 70B InstructAA estimate Published configuration 2*
240 Granite 4.0 MicroAA estimate Published configuration 2*
241 DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)AA estimate Non-reasoning 2*
242 Granite 4.0 1BAA estimate Published configuration 2*
243 Molmo2-8BAA estimate Published configuration 2*
244 LFM2 8B A1BAA estimate Published configuration 2*
245 LFM2.5-VL-1.6BAA estimate Published configuration 1*
246 Apertus 8B InstructAA estimate Published configuration 1*
247 Granite 4.0 350MAA estimate Published configuration 1*
248 Granite 4.0 H 350MAA estimate Published configuration 1*
249 Tiny Aya GlobalAA estimate Published configuration 1*

Showing the top 25 of 249 published configurations.

What Artificial Analysis held constantPublished harness, scoring, and budget boundaries Open contract
Comparison source
Artificial Analysis public LLM leaderboard captured Artificial Analysis snapshot · 30 July 2026.
Harness
Artificial Analysis's independently operated benchmark implementation for this metric.
What varies
The published model configuration and provider-side implementation; reasoning variants remain separate rows.
Tools
Tool access follows the metric-specific Artificial Analysis methodology and is not assumed to be uniform across different benchmarks.
Budget
Task counts, repeats, turn limits, and timeouts follow the cited methodology; they are not equal-compute guarantees across model providers.
Comparison limit
Comparable within this source field and snapshot; not interchangeable with scores from another harness or protocol version.

What this benchmark tests

A composite index of language-model performance across agentic work, coding, scientific reasoning, knowledge, and long-context reasoning.

How to read the score

The published metric is Intelligence Index. Springprompt reproduces Artificial Analysis's rounded public-table figure and preserves its underlying numeric value for provenance.

A missing source value is not scored as zero: that configuration is omitted from this benchmark page.

Comparability policy

Why this is a system evaluation

A row identifies the model configuration, but the measured subject also includes the evaluator's prompts, harness, tools, budgets, repeats, and grader.

That is why Springprompt does not combine these figures with vendor claims or results from another implementation simply because the benchmark name looks similar.

What can be compared here

Every row on this page comes from the same Artificial Analysis snapshot · 30 July 2026 leaderboard payload and the same intelligenceIndex field.

Estimated Intelligence Index rows remain visible but carry an explicit estimate label. Missing fields and deprecated models are not manufactured into pages or zero scores.

Official Artificial Analysis Intelligence Index resources 2 links · show

Go deeper

Turn benchmark evidence into a model decision

Browse Spring Prompt’s task-level model evidence, compare the published configurations above, or join the product waitlist to build an evaluation around your own workflow.

Explore model evidence Browse benchmark explainers Build an evaluation

Sources and provenance

Spring Prompt stores a reviewed, content-addressed evidence manifest for every citation. The linked official source remains canonical.

  1. 1.Artificial Analysis public LLM leaderboard ↗Artificial Analysis · model scores and source display values · retrieved 2026-07-30 · evidence 4e8ccd3759d9
  2. 2.Artificial Analysis intelligence benchmarking methodology ↗Artificial Analysis · methodology and evaluation-contract interpretation · retrieved 2026-07-30 · evidence 45ccc8609f26

Read the official scoring methodology ↗