Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

Chinese SimpleQA (C-SimpleQA) leaderboard — the family board.

2 TRACKED VARIANTS · 1 FIRST-CLASS BOARD

One family, 2 tracked prints. Scoring configs and splits of the base board render as sections of this page, each under its own honest label.

● LIVE DATA27 MODELS ON THIS BOARDLEADER GEMINI 3.1 PRO AT 85.9

The board — Chinese SimpleQA (C-SimpleQA)TOP 27 OF 27 MEASURED · BEST SCORE PER MODEL, DEFAULT VARIANT

#ModelVendorScoreVLast seen
01Gemini 3.1 ProGoogle85.92026-07-04
02DeepSeek-V4-FlashDeepSeek78.92026-07-04
03DeepSeek-V4-ProDeepSeek77.72026-07-04
04Kimi K2 BaseMoonshot77.62026-06-13
05GPT-5.4OpenAI76.82026-07-04
06Claude Opus 4.6Anthropic76.42026-07-04
07Kimi K2.6Moonshot75.92026-07-04
08DeepSeek-V3.1-BaseDeepSeek70.92026-06-13
09GLM-4.5-BaseZ.ai70.12026-06-12
10Hy3-preview-BaseTencent69.72026-06-05
11DeepSeek-V3-BaseDeepSeek68.72026-06-05
12DeepSeek-V3.2-Exp-BaseDeepSeek682026-06-13
13DeepSeek-V3DeepSeek682026-09-11
14MiniMax Text 01MiniMax67.42026-06-06
15DeepSeek-R1-ZeroDeepSeek66.42026-05-03
16GPT-4oOpenAI64.62026-09-11
17DeepSeek-R1DeepSeek63.72026-09-11
18Gemini 2.0 Flash ExpGoogle63.32026-06-06
19Step3.5 Flash BaseStepFun63.22026-06-12
20MiMo V2 Flash BaseXiaomi61.52026-06-13
21Gemini 1.5 ProGoogle59.42026-06-06
22Claude 3.5 SonnetAnthropic56.82026-09-11
23Llama 3.1 Instruct 405BMeta54.72026-06-06
24DeepSeek-V2.5DeepSeek54.12026-05-03
25Qwen2.5 Instruct 72BAlibaba52.22026-06-06
26DeepSeek-V2DeepSeek48.52026-05-03
27o1-miniOpenAI40.32026-09-11
◆ IV — INDEPENDENTLY VERIFIED · ◆ AA — AGGREGATOR · ◆ VA — VENDOR · ◇ SA — SOURCE-ATTRIBUTED
THE FAMILY BOARD · EVERY PRINT LABELED · EVERY SCORE SOURCE-ATTRIBUTED ON ITS OWN LIVE BOARDAll leaderboardsThe frontier boardModels by vendor