Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

Legal Agent Benchmark leaderboard — the family board.

5 TRACKED VARIANTS · 1 FIRST-CLASS BOARD

One family, 5 tracked prints. Scoring configs and splits of the base board render as sections of this page, each under its own honest label.

● LIVE DATA16 MODELS ON THIS BOARDLEADER CLAUDE FABLE 5 AT 13.3

The board — Legal Agent BenchmarkTOP 16 OF 16 MEASURED · BEST SCORE PER MODEL, DEFAULT VARIANT

#ModelVendorScoreVLast seen
01Claude Fable 5Anthropic13.32026-08-23
02Sonnet 5.5Anthropic11.72026-09-29
03Claude Opus 5Anthropic11.72026-08-23
04Claude Opus 4.8Anthropic102026-06-18
05Claude Opus 5.5Anthropic8.32026-09-23
06Claude Opus 4.7Anthropic7.12026-08-23
07Claude Sonnet 5Anthropic5.82026-08-23
08Claude Sonnet 4.6Anthropic5.42026-08-23
09Claude Opus 4.6Anthropic4.22026-08-23
10GPT-5.5OpenAI2.12026-08-23
11Gemini 3.5 FlashGoogle0.802026-08-23
12GPT-5.4OpenAI0.402026-08-23
13Gemini 3.1 ProGoogle0.002026-08-23
14Gemini 3 Flash PreviewGoogle0.002026-08-23
15GPT-5.4 miniOpenAI0.002026-08-23
16Gemini 3.1 Flash Lite PreviewGoogle0.002026-08-23
◆ 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
THE FAMILY BOARD · EVERY PRINT LABELED · EVERY SCORE SOURCE-ATTRIBUTED ON ITS OWN LIVE BOARDAll leaderboardsThe frontier boardModels by vendor