Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models739Deals30d257Policy30d64, 14 pendingSources1,010
Pro Mode — raw scores, one benchmark under the lensofficial card harness
The field · 39 measured
40.687.6

39 models measured, most on the official card harness. Claude Opus 4.8 tops the board at 87.6.

39 measured·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 40.6–87.6 · ◆ solid = first-party or better · outlined = arm's-length
01Claude Opus 4.8Anthropic87.6$5.0/M$25.0/M$0.171
02Qwen3.7 MaxAlibaba86.2$2.5/M$7.5/M$0.058
03Qwen3.5 397B A17BAlibaba85.6$0.60/M$3.6/M$0.025
04Qwen3.6 PlusAlibaba85.1$0.50/M$3.0/M$0.021
05Qwen3.7 Plus PreviewAlibaba83$0.40/M$1.6/M$0.012
06Qwen3.5 122B A10BAlibaba82.8$0.40/M$3.2/M$0.022
07Qwen3.5 27BAlibaba81.6$0.30/M$2.4/M$0.017
08Qwen3 VL 235B A22B InstructAlibaba80$0.40/M$1.6/M$0.013
09Qwen3 VL 235B A22B ReasoningAlibaba80$0.40/M$4.0/M$0.028
10Qwen3.5 35B A3BAlibaba79.7$0.25/M$2.0/M$0.014
11Qwen3 235B A22B Instruct 2507Alibaba79.5$0.23/M$0.92/M$0.007
12Qwen3 Next 80B A3B InstructAlibaba78.9$0.15/M$1.2/M$0.009
13Qwen3 Next 80B A3BAlibaba78.9$0.15/M$1.2/M$0.009
14Hy3-preview-Base+1 altTencent78.64———
15DeepSeek-V3-Base+1 altDeepSeek77.86———
16DeepSeek-V3.1-BaseDeepSeek77.23P———
17DeepSeek-V3.2-Exp-BaseDeepSeek77.23P———
18Qwen3 VL 32B ReasoningAlibaba76.3$0.16/M$0.64/M$0.005
19GLM-4.5-Base+1 altZ.ai76.27———
20Kimi K2 Base+2 altsMoonshot75.66———
21Qwen3.5 9BAlibaba75.6$0.14/M$0.20/M$0.002
22Qwen3 VL 30B A3B ReasoningAlibaba74.5$0.20/M$2.4/M$0.017
23Qwen3 VL 32B InstructAlibaba74$0.16/M$0.64/M$0.005
24Qwen3 235B A22BAlibaba73.46$0.70/M$2.8/M$0.024
25Qwen3 VL 30B A3B InstructAlibaba71.6$0.20/M$0.80/M$0.007
26MiMo V2 Flash BaseXiaomi71.43P———
27Qwen3.5 4BAlibaba71$0.03/M$0.15/M$0.001
28Qwen3 VL Thinking (8B)Alibaba69.5$0.18/M$2.1/M$0.016
29Granite 4.1 30BIBM67.263P———
30Granite 4.1 30B Base+1 altIBM67.073P———
31Qwen3 VL 8B InstructAlibaba67$0.18/M$0.70/M$0.007
32Qwen3 VL 4B (Reasoning)Alibaba64.6———
33Qwen3 VL 4B InstructAlibaba61.4———
34Granite 4.1 8BIBM58.893P$0.05/M$0.10/M$0.001
35Granite 4.1 8B Base+1 altIBM57.63P———
36Qwen3.5 2BAlibaba55.4———
37Granite 4.1 3BIBM52.053P———
38Granite 4.1 3B BaseIBM51.773P———
39Qwen3.5 0.8BAlibaba40.6———
◆ 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: 39 models scored · 0 independently verified · 5 vendor cross-reference · 34 vendor-reported · 0 with source disagreement. How these tiers are assigned