VECTOR WIREAI INTELLIGENCE
⌘K
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 —

scicode

100 models tracked

SciCode — Scientific coding bench; folds aa_scicode/no-tools raws at problem level. Distinct from subtask.

#ModelVendorBest scoreRunsLast seen
1Claude Fable 5Anthropic60.222026-07-27
2Gemini 3.1 ProGoogle5972026-08-24
3Kimi K3Moonshot58.742026-07-31
4Muse Spark 1.1Meta58.212026-07-11
5Gemini 3.7 FlashGoogle57.932026-08-14
6GPT-5.6 SolOpenAI56.972026-07-27
7GPT-5.4OpenAI56.642026-05-03
8GLM-5.3Z.ai56.512026-08-19
9Muse Spark 1.2Meta56.412026-08-06
10Gemini 3 ProGoogle56.162026-08-24
11GPT-5.5OpenAI56.162026-07-27
12Opus 5Anthropic55.752026-07-25
13GPT-5.2 CodexOpenAI54.612026-05-02
14Grok 4.6SpaceXAI54.642026-08-22
15Claude Opus 4.7Anthropic54.522026-06-01
16Grok4.5SpaceXAI54.112026-07-09
17GPT-5.6 TerraOpenAI53.962026-07-10
18Claude Sonnet 5Anthropic53.622026-07-02
19Qwen3.7 MaxAlibaba53.522026-08-23
20Claude Opus 4.8Anthropic53.522026-07-27
21Kimi K2.6Moonshot53.552026-08-23
22GPT-5.3 CodexOpenAI53.212026-05-02
23Gemini 3.5 FlashGoogle53.142026-07-07
24Qwen3.8 Max PreviewAlibaba52.912026-08-06
25Gemini 3.6 FlashGoogle52.712026-07-22
26GPT-5.6 LunaOpenAI52.582026-07-30
27GPT-5.2OpenAI52.172026-08-24
28Claude Opus 4.6Anthropic5252026-08-24
29Qwen3.8 2.4T A95BAlibaba51.612026-08-14
30Muse SparkMeta51.522026-07-07
31Qwen3.7 Plus PreviewAlibaba51.332026-08-23
32Gemini 3 Flash PreviewGoogle50.622026-05-02
33GLM-5.2 Full Open SourceZ.ai50.532026-07-27
34GPT-5.5 InstantOpenAI50.342026-07-07
35Grok Build 0.1SpaceXAI50.222026-07-07
36DeepSeek-V4-ProDeepSeek5032026-06-29
37Claude Opus 4.5Anthropic5052026-08-24
38DeepSeek-V4-FlashDeepSeek49.972026-08-01
39GPT-5.4 miniOpenAI49.932026-06-01
40Kimi K2.5Moonshot4952026-08-23
41Inkling-SmallThinking Machines48.742026-08-23
42Hy3-previewTencent47.622026-05-02
43Kimi K2.7 CodeMoonshot47.522026-07-07
44Grok 4.3SpaceXAI47.352026-05-23
45MiniMax M2.7MiniMax4742026-07-30
46Claude Sonnet 4.6Anthropic4742026-05-02
47GPT-5.4 nanoOpenAI46.932026-06-01
48Qwen3.6 Max PreviewAlibaba46.912026-05-02
49o4-miniOpenAI46.512026-05-02
50GLM-5Z.ai46.222026-05-02
51InklingThinking Machines46.122026-07-30
52Grok 4SpaceXAI45.722026-07-07
53Grok 4.20 0309 V2SpaceXAI45.632026-06-18
54Solar Open2 250BUpstage45.612026-08-13
55MiniMax M3MiniMax45.422026-07-07
56GLM-4.7Z.ai45.122026-06-01
57Claude Sonnet 4.5Anthropic4572026-08-24
58Kimi K2 (Reasoning)Moonshot44.852026-07-07
59Grok 4.20SpaceXAI44.712026-05-02
60Qwen3.8 27BAlibaba44.742026-08-22
61MiniMax M2.5MiniMax44.432026-08-24
62Motif-3-BetaMotif Technologies44.312026-07-21
63Grok 4.1 FastSpaceXAI44.222026-06-23
64Grok 4 FastSpaceXAI44.222026-05-02
65DeepSeek-V3.2-SpecialeDeepSeek4422026-07-07
66GLM-5.1Z.ai43.822026-05-02
67GLM-5-TurboZ.ai43.622026-07-07
68Solar Pro4Upstage43.612026-08-13
69Muse GlimmerMeta43.612026-08-11
70muse-glimmer-30bMeta43.612026-08-23
71GLM 5V TurboZ.ai43.512026-06-01
72Gemma 4 31BGoogle43.422026-06-01
73Claude Haiku 4.5Anthropic43.322026-06-01
74GPT-5.1OpenAI43.322026-06-20
75MiMo V2.5 ProXiaomi43.152026-07-30
76Gemini 2.5 ProGoogle4372026-07-07
77GPT-5OpenAI4382026-07-07
78Nova 2.0 Pro PreviewAmazon42.732026-05-02
79GPT-5.1 Codex miniOpenAI42.612026-05-02
80MiMo V2 ProXiaomi42.522026-07-07
81Qwen3 235B A22BAlibaba42.432026-06-18
82Agnes 2.5 Pro AlphaSapiens AI42.212026-07-25
83Nemotron 3 Super 120B A12BNVIDIA4222026-08-23
84Qwen3.5 122B A10BAlibaba4222026-05-02
85Qwen3.5 397B A17BAlibaba4242026-07-30
86Gemini 3.1 Flash Lite PreviewGoogle41.922026-07-07
87Nex-N2-ProNex AGI41.822026-07-07
88GLM-4.5Z.ai41.722026-08-23
89Ling-3.0-flashInclusionAI41.112026-08-06
90MiniMax M2.1MiniMax4152026-08-24
91GPT-5 miniOpenAI4152026-07-07
92o3OpenAI4122026-07-07
93K-EXAONE 2.0 0803LG AI4112026-08-13
94Gemini 3.5 Flash LiteGoogle40.932026-07-30
95Claude Opus 4.1Anthropic40.912026-06-01
96GPT-5 CodexOpenAI40.912026-05-02
97Claude 4 OpusAnthropic40.922026-06-01
98Qwen3.6 PlusAlibaba40.722026-07-07
99Doubao Seed CodeByteDance40.722026-07-07
100Grok 3 Mini ReasoningSpaceXAI40.612026-06-01

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