Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

Claw Eval (pass@3) leaderboard — the family board.

4 TRACKED VARIANTS · 1 FIRST-CLASS BOARD

One family, 4 tracked prints. 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 K2.6 AT 80.9

The board — Claw Eval (pass@3)TOP 21 OF 21 MEASURED · BEST SCORE PER MODEL, DEFAULT VARIANT

#ModelVendorScoreVLast seen
01Kimi K2.6Moonshot80.92026-08-23
02GLM 5V TurboZ.ai752026-08-23
03MiniMax M3MiniMax74.52026-08-23
04Hy3-previewTencent68.52026-08-23
05MiMo V2.5 Pro FP4 DFlashXiaomi67.82026-08-29
06Qwen3.7 MaxAlibaba65.22026-08-23
07MiMo V2.5 ProXiaomi642026-08-23
08MiMo V2.5Xiaomi63.22026-09-24
09LFM2.5-2.6BLiquid AI62.92026-08-23
10Qwen3.7 Plus PreviewAlibaba62.72026-08-23
11MiMo V2 ProXiaomi61.52026-08-23
12Qwen3.6 27BAlibaba60.62026-08-24
13Claude Opus 4.5Anthropic59.62026-08-24
14Qwen3.6 PlusAlibaba58.72026-08-23
15MiMo V2 OmniXiaomi54.82026-08-23
16Qwen3.5 35B A3BAlibaba512026-08-24
17Qwen3.6 35B A3BAlibaba502026-08-24
18Qwen3.5 397B A17BAlibaba48.12026-08-24
19Qwen3.5 27BAlibaba46.22026-08-24
20Gemma 4 26B A4BGoogle282026-08-24
21Gemma 4 31BGoogle252026-08-24
◆ IV — INDEPENDENTLY VERIFIED · ◆ AA — AGGREGATOR · ◆ VA — VENDOR · ◇ SA — SOURCE-ATTRIBUTED

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

Claw-Eval Avg

VARIANT13 models · best score per model
#ModelVendorScoreVLast seen
01Claude Opus 4.5Anthropic76.62026-06-15
02Qwen3.6 27BAlibaba72.42026-06-15
03Qwen3.5 397B A17BAlibaba70.72026-06-15
04Qwen3.6 35B A3BAlibaba68.72026-06-15
05Qwen3.5 9BAlibaba66.52026-08-10
06Qwen3.5 35B A3BAlibaba65.42026-05-03
07Qwen3.5 27BAlibaba64.32026-06-15
08LFM2.5-2.6BLiquid AI62.92026-08-10
09Qwen3.5 4BAlibaba62.32026-08-10
10Gemma 4 26B A4BGoogle58.82026-05-03
11Gemma 4 E4BGoogle58.02026-08-10
12Gemma 4 E2BGoogle53.12026-08-10
13Gemma 4 31BGoogle48.52026-06-15

Other tracked prints

THIN BOARDSunder 5 published models each — listed, never hidden
PrintLeaderScoreModels
Claw-Eval GeneralMiMo V2.5 Pro641
Claw-Eval Multi TurnMiMo V2.5 Pro63.21
THE FAMILY BOARD · EVERY PRINT LABELED · EVERY SCORE SOURCE-ATTRIBUTED ON ITS OWN LIVE BOARDAll leaderboardsThe frontier boardModels by vendor