VECTOR WIREAI INTELLIGENCE
NVDA$1,847+3.2%MSFT$512+1.1%GOOGL$199-0.4%META$728+2.7%AMD$184-1.2%TSM$212+0.6%PLTR$98+4.1%AI IDX4,821+1.9%
PKT
SEEDRefresh Models Deals Regulatory Sources

ARC-AGI-2

86 models tracked

ARC-AGI-2 — raws fold in 'arc_agi_2'/'ArcAGI V2' aliases; distinct version from v1/v3

#ModelVendorBest scoreRunsLast seen
1GPT-5.6 SolOpenAI92.522026-07-24
2Opus 5Anthropic90.432026-07-25
3Claude Fable 5 (Extra High)Anthropic88.312026-08-06
4GPT-5.5OpenAI8542026-08-23
5Gemini 3 Deep ThinkGoogle84.622026-05-10
6GPT-5.5 ProOpenAI84.212026-05-10
7GPT-5.6 TerraOpenAI83.912026-07-10
8GPT-5.4 ProOpenAI83.332026-06-21
9Gemini 3.1 ProGoogle77.172026-08-24
10Claude Fable 5Anthropic76.812026-08-06
11Claude Opus 4.7Anthropic75.882026-07-24
12GPT-5.4OpenAI7462026-08-23
13GPT-5.2 (Refine.)OpenAI72.912026-05-10
14Gemini 3.5 FlashGoogle72.152026-08-24
15Claude Opus 4.8Anthropic72.122026-07-24
16Claude Opus 4.6Anthropic68.852026-08-23
17Grok 4.20SpaceXAI65.112026-05-10
18Claude Sonnet 4.6Anthropic60.462026-08-23
19GPT-5.6 LunaOpenAI59.672026-08-11
20GPT-5.2 ProOpenAI54.222026-08-23
21Gemini 3 ProGoogle5432026-08-23
22Gemini 3.7 FlashGoogle52.912026-08-21
23GPT-5.2OpenAI52.962026-08-23
24DeepSeek-V4-FlashDeepSeek4622026-08-10
25Muse SparkMeta42.512026-08-23
26Inkling-SmallThinking Machines40.142026-08-24
27Claude Opus 4.5Anthropic37.642026-08-23
28InklingThinking Machines36.512026-07-18
29Gemini 3 Flash PreviewGoogle33.672026-08-23
30Grok4.5SpaceXAI33.112026-07-24
31Grok 4 (Refine.)SpaceXAI29.412026-05-10
32Grok 4.6SpaceXAI27.612026-08-14
33GLM-5.2 Full Open SourceZ.ai22.822026-07-13
34GPT-5 ProOpenAI18.312026-05-10
35GPT-5.1OpenAI17.642026-06-20
36Grok 4SpaceXAI1622026-08-23
37Claude Sonnet 4Anthropic13.622026-05-10
38Claude Sonnet 4.5Anthropic13.622026-05-10
39GPT-5.4 miniOpenAI13.222026-05-15
40Kimi K3Moonshot12.412026-08-01
41Kimi K2.5Moonshot11.812026-05-10
42Claude 4 OpusAnthropic8.632026-08-23
43GPT-5OpenAI7.542026-05-10
44o3OpenAI6.522026-08-23
45Tiny Recursion Model (TRM)Bespoke6.312026-05-10
46o4-miniOpenAI6.132026-05-10
47Grok 4 FastSpaceXAI5.312026-05-15
48Gemini 2.5 ProGoogle4.932026-08-23
49GLM-5Z.ai4.912026-05-10
50MiniMax M2.5MiniMax4.912026-05-10
51o3-proOpenAI4.912026-05-10
52GPT-5 miniOpenAI442026-05-15
53Claude Haiku 4.5Anthropic412026-05-10
54DeepSeek-V3.2DeepSeek412026-05-10
55o3-miniOpenAI322026-05-10
56Gemini 3.6 FlashGoogle2.612026-08-07
57Gemini 2.5 FlashGoogle2.522026-05-10
58Hierarchical Reasoning Model (HRM)Bespoke212026-05-10
59GPT-5.4 nanoOpenAI1.922026-05-10
60Seed Oss 36B InstructByteDance1.412026-06-15
61DeepSeek-R1DeepSeek1.322026-05-10
62Gemini 2.0 Flash (Non-Reasoning)Google1.312026-05-10
63Gemini 2.0 Flash (Reasoning)Google1.312026-06-24
64Codex MiniOpenAI1.312026-05-10
65Qwen3 235B A22B Instruct 2507Alibaba1.322026-06-19
66Claude 3.7Anthropic0.912026-07-14
67GPT-5 nanoOpenAI0.932026-05-10
68Qwen3 30B A3BAlibaba0.912026-06-15
69Gemini 3.5 Flash LiteGoogle0.812026-08-07
70OpenAI o1-miniOpenAI0.812026-05-10
71GPT-4.5 PreviewOpenAI0.812026-05-10
72Gemini 1.5 ProGoogle0.812026-05-15
73GPT-4.1OpenAI0.412026-05-10
74Grok 3 Mini ReasoningSpaceXAI0.412026-05-10
75GPT-4o miniOpenAI012026-05-10
76Magistral SmallMistral012026-05-10
77GPT-4.1 miniOpenAI022026-06-19
78Llama 4 ScoutMeta022026-06-19
79MagistralMistral012026-08-03
80Magistral Medium 1Mistral022026-05-10
81Llama 4 MaverickMeta012026-05-10
82Claude 3.7 SonnetAnthropic012026-05-10
83Qwen3 32BAlibaba012026-06-15
84Grok 3SpaceXAI022026-06-19
85GPT-4.1 nanoOpenAI022026-06-19
86GPT-4oOpenAI012026-05-10

Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.