Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

NaturalQuestions leaderboard — the family board.

3 TRACKED VARIANTS · 2 FIRST-CLASS BOARDS

One family, 3 tracked prints: naturalquestions_closedbook 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 DATA8 MODELS ON THIS BOARDLEADER HUNYUAN LARGE AT 52.8

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

#BoardModels scored
02NaturalQuestionsTHIS PAGE8

The board — NaturalQuestionsTOP 8 OF 8 MEASURED · BEST SCORE PER MODEL, DEFAULT VARIANT

#ModelVendorScoreVLast seen
01Hunyuan LargeTencent52.82026-05-31
02Llama 3.1 Instruct 405BMeta41.52026-05-01
03DeepSeek-V3DeepSeek402026-05-01
04DeepSeek-V2DeepSeek38.72026-05-31
05Gemma 2 27B ITGoogle34.52026-08-23
06Qwen2.5 Instruct 72BAlibaba33.22026-05-01
07Gemma 2 Instruct (9B)Google29.22026-08-23
08Gemma 3n E2B InstructGoogle15.52026-09-10
◆ 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
NaturalQuestions (EM)Llama 3.1 Instruct 405B41.54
THE FAMILY BOARD · EVERY PRINT LABELED · EVERY SCORE SOURCE-ATTRIBUTED ON ITS OWN LIVE BOARDAll leaderboardsThe frontier boardModels by vendor