Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

CRUXEval-O (output prediction) leaderboard — the family board.

4 TRACKED VARIANTS · 2 FIRST-CLASS BOARDS

One family, 4 tracked prints: CRUXEval-I (input prediction) 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 DATA21 MODELS ON THIS BOARDLEADER KIMI K2 BASE AT 83.5

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

#BoardModels scored
01CRUXEval-O (output prediction)THIS PAGE21

The board — CRUXEval-O (output prediction)TOP 21 OF 21 MEASURED · BEST SCORE PER MODEL, DEFAULT VARIANT

#ModelVendorScoreVLast seen
01Kimi K2 BaseMoonshot83.52026-06-13
02MiMo V2 Flash BaseXiaomi79.12026-06-13
03DeepSeek-V3.1-BaseDeepSeek76.42026-06-13
04DeepSeek-V3.2-Exp-BaseDeepSeek74.92026-06-13
05DeepSeek-V3-BaseDeepSeek712026-06-05
06DeepSeek-V3DeepSeek69.82026-05-01
07Hy3-preview-BaseTencent68.42026-06-05
08GLM-4.5-BaseZ.ai67.82026-06-05
09Qwen2.5 7B BaseAlibaba63.42026-05-03
10Stable-DiffCoder-8B-BaseByteDance602026-06-05
11Qwen2.5 Instruct 72BAlibaba59.92026-05-01
12Llama 3.1 Instruct 405BMeta59.92026-05-01
13Qwen2.5 Coder Instruct 7BAlibaba562026-06-05
14Granite 4.1 30BIBM55.82026-06-15
15Qwen3 4B Base DenseAlibaba50.72026-05-03
16DeepSeek-V2DeepSeek49.82026-05-01
17Granite 4.1 8BIBM47.62026-06-15
18DeepSeek-Coder-6.7B-BaseDeepSeek412026-06-05
19Granite 4.1 3BIBM40.82026-06-15
20Qwen2.5 3B BaseAlibaba26.12026-05-03
21Gemma 3 1B Base DenseGoogle3.72026-05-03
◆ 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