Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models762Deals30d247Policy30d59, 11 pendingSources1,061
Pro Mode — raw scores, one benchmark under the lensofficial card harness
The field · 21 measured
68.183.4

21 models measured, most on the official card harness. Qwen3.6 Plus tops the board at 83.4.

21 measured·Lifecycle Updated Oct 17, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 68.1–83.4 · ◆ solid = first-party or better · outlined = arm's-length
01Qwen3.6 PlusAlibaba83.4$0.50/M$3.0/M$0.021
02Qwen3 VL 235B A22B InstructAlibaba82.2$0.21/M$1.4/M$0.010
03Qwen3.6 35B A3B+1 altAlibaba81.9$0.38/M$2.3/M$0.016
04Qwen3.5 122B A10BAlibaba81.8$0.40/M$3.2/M$0.022
05Qwen3 VL 235B A22B ReasoningAlibaba81.5$0.40/M$4.0/M$0.027
06Qwen3.6 27BAlibaba81.2$0.60/M$3.6/M$0.026
07Qwen3.5 27B+1 altAlibaba81$0.30/M$2.4/M$0.017
08Qwen3.5 35B A3B+1 altAlibaba80.7$0.25/M$2.0/M$0.014
09Qwen3 VL 30B A3B InstructAlibaba80.7$0.20/M$0.80/M$0.006
10Qwen3 VL 32B InstructAlibaba80.3$0.16/M$0.64/M$0.005
11Qwen3 VL 8B InstructAlibaba79.9$0.18/M$0.70/M$0.006
12Qwen2.5 VL 72BAlibaba79.8———
13Qwen3 VL 30B A3B ReasoningAlibaba77.8$0.20/M$2.4/M$0.017
14Qwen2.5 VL 32B Instruct+1 altAlibaba77.1———
15Qwen3 VL Thinking (8B)Alibaba76.3$0.18/M$2.1/M$0.015
16Qwen3 VL 4B InstructAlibaba76.2———
17Gemma 4 31BGoogle75.7$0.17/M$0.40/M$0.004
18Gemma 4 26B A4BGoogle74.5$0.07/M$0.23/M$0.002
19Qwen3 VL 4B (Reasoning)Alibaba73.8———
20Qwen2 VL 72B InstructAlibaba68.7———
21Claude Sonnet 4.5Anthropic68.1$3.0/M$15.0/M$0.132
◆ solid = independently verified · aggregator attested · vendor attributed — outlined = cross-reference · source-attributed. Dimmed ◆ = confidence inferred. “+N alts” = alternate disclosures in the drawer with why-demoted. Prices per million tokens; $/point = input price ÷ score. Every row opens its model dossier.

Verification: 21 models scored · 0 independently verified · 3 vendor cross-reference · 18 vendor-reported · 0 with source disagreement. How these tiers are assigned