Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

HMMT25 no tools leaderboard — the family board.

3 TRACKED VARIANTS · 1 FIRST-CLASS BOARD

One family, 3 tracked prints. Scoring configs and splits of the base board render as sections of this page, each under its own honest label.

● LIVE DATA6 MODELS ON THIS BOARDLEADER GPT-5 AT 93.3

The board — HMMT25 no toolsTOP 6 OF 6 MEASURED · BEST SCORE PER MODEL, DEFAULT VARIANT

#ModelVendorScoreVLast seen
01GPT-5OpenAI93.32026-06-12
02Grok 4SpaceXAI902026-06-12
03Kimi K2 ThinkingMoonshot89.42026-06-12
04DeepSeek-V3.2DeepSeek83.62026-06-12
05Claude Sonnet 4.5Anthropic74.62026-06-12
06Kimi K2 InstructMoonshot38.82026-06-12
◆ IV — INDEPENDENTLY VERIFIED · ◆ AA — AGGREGATOR · ◆ VA — VENDOR · ◇ SA — SOURCE-ATTRIBUTED

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

HMMT25 w/ python

VARIANT6 models · best score per model
#ModelVendorScoreVLast seen
01GPT-5OpenAI96.72026-05-15
02Kimi K2 ThinkingMoonshot95.12026-05-15
03Grok 4SpaceXAI93.92026-05-15
04Claude Sonnet 4.5Anthropic88.82026-06-12
05Kimi K2 InstructMoonshot70.42026-05-15
06DeepSeek-V3.2DeepSeek49.52026-05-15

Other tracked prints

THIN BOARDSunder 5 published models each — listed, never hidden
PrintLeaderScoreModels
HMMT25 heavyGPT-51003
THE FAMILY BOARD · EVERY PRINT LABELED · EVERY SCORE SOURCE-ATTRIBUTED ON ITS OWN LIVE BOARDAll leaderboardsThe frontier boardModels by vendor