Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

BabyVision 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 DATA20 MODELS ON THIS BOARDLEADER DEEPSEEK-V4.1-FLASH AT 89.6

The board — BabyVisionTOP 20 OF 20 MEASURED · BEST SCORE PER MODEL, DEFAULT VARIANT

#ModelVendorScoreVLast seen
01DeepSeek-V4.1-FlashDeepSeek89.62026-09-11
02Kimi K3Moonshot85.72026-08-23
03Qwen3.8 27BAlibaba85.62026-08-24
04Muse Spark 1.1Meta76.32026-08-23
05Seed 2.1 Pro PreviewByteDance73.72026-09-28
06Muse GlimmerMeta70.42026-08-24
07Qwen3.7 Plus PreviewAlibaba70.42026-08-24
08Kimi K2.6Moonshot68.52026-08-23
09Seed2.1ByteDance62.92026-09-28
10GPT-5.5OpenAI55.92026-09-28
11Gemini 3.1 ProGoogle54.42026-09-28
12GLM 5.3 FlashZ.ai53.42026-08-27
13GPT-5.4OpenAI49.72026-05-03
14Qwen3.5 27BAlibaba44.62026-08-23
15Qwen3.5 122B A10BAlibaba40.22026-08-23
16Qwen3.5 35B A3BAlibaba38.42026-08-23
17Kimi K2.5Moonshot36.52026-05-03
18Qwen3.6 27BAlibaba28.92026-08-24
19Claude Opus 4.7Anthropic22.22026-09-28
20Claude Opus 4.6Anthropic14.82026-08-24
◆ IV — INDEPENDENTLY VERIFIED · ◆ AA — AGGREGATOR · ◆ VA — VENDOR · ◇ SA — SOURCE-ATTRIBUTED

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

baby_vision_with_python

VARIANT9 models · best score per model
#ModelVendorScoreVLast seen
01Claude Fable 5Anthropic90.52026-08-24
02GPT-5.6 SolOpenAI88.92026-08-24
03Kimi K3Moonshot85.72026-08-24
04Claude Opus 4.8Anthropic81.22026-08-24
05GPT-5.4OpenAI80.22026-05-03
06Kimi K2.6Moonshot68.52026-05-03
07Gemini 3.1 ProGoogle68.32026-05-03
08Kimi K2.5Moonshot40.52026-05-03
09Claude Opus 4.6Anthropic38.42026-05-03
THE FAMILY BOARD · EVERY PRINT LABELED · EVERY SCORE SOURCE-ATTRIBUTED ON ITS OWN LIVE BOARDAll leaderboardsThe frontier boardModels by vendor