Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

Agents' Last Exam leaderboard — the family board.

3 TRACKED VARIANTS · 2 FIRST-CLASS BOARDS

One family, 3 tracked prints: Agents' Last Exam (ALE-CLI) 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 DATA30 MODELS ON THIS BOARDLEADER GPT-6 ASTRA AT 59.3

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

#BoardModels scored
01Agents' Last ExamTHIS PAGE30

The board — Agents' Last ExamTOP 30 OF 30 MEASURED · BEST SCORE PER MODEL, DEFAULT VARIANT

#ModelVendorScoreVLast seen
01GPT-6 AstraOpenAI59.32026-09-23
02GPT-6 SolOpenAI56.42026-09-23
03GPT-5.6 SolOpenAI52.72026-09-22
04Qwen3.8 Max PreviewAlibaba52.42026-08-23
05Qwen3.8 Flash NextAlibaba51.22026-09-23
06GPT-6 LunaOpenAI50.92026-09-23
07GPT-5.6 TerraOpenAI50.42026-08-23
08GPT-5.6 LunaOpenAI50.32026-08-23
09Qwen3.8 27BAlibaba42.92026-08-26
10Seed 2.1 Pro PreviewByteDance41.42026-09-26
11Gemini 4 ArgonGoogle39.52026-10-08
12Qwen3.7 Plus PreviewAlibaba33.62026-08-26
13DeepSeek-V4.1-FlashDeepSeek31.82026-09-23
14MiMo V2.6 ProXiaomi31.62026-09-23
15Claude Opus 5Anthropic31.62026-09-22
16GLM-5.3Z.ai28.52026-09-10
17Kimi K3Moonshot28.32026-08-13
18MiMo V2.6 Flash RLXiaomi27.62026-09-23
19DeepSeek-V4-Flash-Vision-ExpDeepSeek27.32026-08-31
20Qwen3.6 27BAlibaba27.32026-08-24
21Claude Opus 4.8Anthropic272026-08-31
22GPT-5.5OpenAI26.62026-07-27
23Gemini 3.7 FlashGoogle26.32026-08-24
24GLM 5.3 FlashZ.ai26.32026-09-23
25DeepSeek-V4-ProDeepSeek25.72026-09-10
26Claude Fable 5Anthropic25.72026-09-22
27DeepSeek-V4-FlashDeepSeek25.22026-08-31
28GLM-5.2Z.ai23.82026-08-13
29Hy4Tencent22.82026-09-23
30MiMo V2.5 ProXiaomi13.22026-09-22
◆ 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
Agents' Last Exam (Pass / Score)GPT-5.6 Sol53.64
THE FAMILY BOARD · EVERY PRINT LABELED · EVERY SCORE SOURCE-ATTRIBUTED ON ITS OWN LIVE BOARDAll leaderboardsThe frontier boardModels by vendor