Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

SimpleQA leaderboard — the family board.

5 TRACKED VARIANTS · 2 FIRST-CLASS BOARDS

One family, 5 tracked prints: SimpleQA Verified is cited standalone and keeps live board of its own. Scoring configs and splits of the base board render as sections of this page, each under its own honest label.

● LIVE DATA73 MODELS ON THIS BOARDLEADER DEEPSEEK-V3.2-EXP AT 97.1

First-class boards in this familyCITED STANDALONE · EACH KEEPS ITS OWN LIVE BOARD

#BoardModels scored
02SimpleQATHIS PAGE73

The board — SimpleQATOP 73 OF 73 MEASURED · BEST SCORE PER MODEL, DEFAULT VARIANT

#ModelVendorScoreVLast seen
01DeepSeek-V3.2-ExpDeepSeek97.12026-08-23
02Grok 4 FastSpaceXAI952026-08-23
03DeepSeek-V3.1DeepSeek93.42026-08-23
04Grok 3SpaceXAI822026-07-13
05ERNIE 5.0 Thinking PreviewBaidu752026-08-23
06Gemini 3 ProGoogle72.12026-08-23
07Gemini 3 Flash PreviewGoogle68.72026-08-23
08GPT-4.5 PreviewOpenAI62.52026-08-23
09DeepSeek-V4-ProDeepSeek57.92026-08-23
10Qwen3 VL 32B ReasoningAlibaba55.42026-08-23
11Qwen3 235B A22B Instruct 2507Alibaba54.32026-08-23
12Gemini 2.5 ProGoogle542026-09-03
13Qwen3 VL 235B A22B InstructAlibaba51.92026-08-23
14Qwen3 VL Thinking (8B)Alibaba49.62026-08-23
15o3OpenAI49.42026-06-05
16Qwen3 VL 4B InstructAlibaba482026-08-23
17o1OpenAI472026-08-23
18Qwen3 VL 235B A22B ReasoningAlibaba44.42026-08-23
19Grok 3 BetaSpaceXAI43.62026-07-13
20Gemini 3.1 Flash Lite PreviewGoogle43.32026-08-23
21GPT-4oOpenAI39.42026-08-23
22Kimi K2 BaseMoonshot35.32026-08-23
23Step3.5 Flash BaseStepFun31.62026-06-05
24Kimi K2 InstructMoonshot312026-08-23
25DeepSeek-R1-ZeroDeepSeek30.32026-05-03
26DeepSeek-R1DeepSeek30.12026-06-05
27GLM-4.5-BaseZ.ai302026-06-05
28Claude 3.5 SonnetAnthropic28.42026-06-06
29DeepSeek-V3DeepSeek27.72026-08-23
30DeepSeek-V3.2-Exp-BaseDeepSeek272026-06-13
31Qwen3 VL 30B A3B InstructAlibaba272026-08-23
32Gemini 2.5 FlashGoogle26.92026-08-23
33Gemini 2.0 Flash ExpGoogle26.62026-06-06
34Hy3-preview-BaseTencent26.52026-06-05
35DeepSeek-V3.1-BaseDeepSeek26.32026-06-13
36DeepSeek-V3-BaseDeepSeek26.12026-06-05
37Qwen3 VL 30B A3B ReasoningAlibaba23.92026-08-23
38Mistral Large 3Mistral23.82026-08-23
39Mistral Large 3 675B Base 2512Mistral23.82026-08-23
40MiniMax Text 01MiniMax23.72026-06-06
41Qwen3 30B A3B 2507 ThinkingAlibaba23.62026-06-15
42Gemini 1.5 ProGoogle23.42026-06-06
43Llama 3.1 Instruct 405BMeta23.22026-06-06
44Claude Opus 4Anthropic22.82026-06-15
45Grok 3 Mini BetaSpaceXAI21.72026-07-13
46Llama 3.3 70B InstructMeta20.92026-05-30
47MiMo V2 Flash BaseXiaomi20.62026-06-13
48MiniMax M1 80KMiniMax18.52026-08-23
49MiniMax M1 40KMiniMax17.92026-08-23
50Claude Sonnet 4Anthropic15.92026-06-15
51o3-miniOpenAI152026-08-23
52Qwen3 235B A22BAlibaba13.22026-06-15
53Gemini 2.5 Flash LiteGoogle10.72026-08-23
54Granite 4.1 30B BaseIBM10.52026-06-15
55Qwen2.5 Instruct 72BAlibaba10.32026-06-06
56DeepSeek-V2.5DeepSeek10.22026-05-03
57Gemma 3 27BGoogle102026-08-23
58GPT-4o miniOpenAI9.92026-05-30
59Seed Oss 36B InstructByteDance9.72026-06-15
60Qwen3 32BAlibaba8.62026-06-15
61Granite 4.1 8B BaseIBM7.92026-06-15
62Phi 3 Medium 4K InstructMicrosoft7.62026-05-30
63o1-miniOpenAI72026-06-04
64Granite 4.1 3B BaseIBM6.82026-06-15
65Granite 4.1 30BIBM6.82026-06-15
66Gemma 3 12BGoogle6.32026-08-23
67Qwen 2.5 14BAlibaba5.42026-05-30
68Granite 4.1 8BIBM4.82026-06-15
69Gemma 3 4BGoogle42026-08-23
70Granite 4.1 3BIBM3.72026-06-15
71Phi 4Microsoft32026-08-23
72Gemma 3 1B InstructGoogle2.22026-08-23
73ERNIE 4.5Baidu1.82026-08-23
◆ IV — INDEPENDENTLY VERIFIED · ◆ AA — AGGREGATOR · ◆ VA — VENDOR · ◇ SA — SOURCE-ATTRIBUTED

Variants of this boardSCORING CONFIGS & SPLITS — NOT CITED STANDALONE, SO THEY LIVE HERE

Other tracked prints

THIN BOARDSunder 5 published models each — listed, never hidden
PrintLeaderScoreModels
Simple-QA verified (EM)DeepSeek-V4-Pro-Base55.23
SimpleQA hallucination rateo10.443
SimpleQA accuracyo30.492
THE FAMILY BOARD · EVERY PRINT LABELED · EVERY SCORE SOURCE-ATTRIBUTED ON ITS OWN LIVE BOARDAll leaderboardsThe frontier boardModels by vendor