Skip to content
VECTOR WIREAI INTELLIGENCE
UTC
Pro Mode — raw scores, one benchmark under the lensofficial card harness
The field · 22 measured
2.665.7

22 models measured, most on the official card harness. Claude Opus 5 tops the board at 65.7.

22 measured·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 2.6–65.7 · ◆ solid = first-party or better · outlined = arm's-length
01Claude Opus 5+1 altAnthropic65.73P$5.0/M$25.0/M$0.228
02Muse Spark 1.3Meta64.9$1.3/M$4.3/M$0.042
03MiMo V2.6 Pro+2 altsXiaomi62$0.43/M$0.87/M$0.010
04Hy4Tencent61.7$0.83/M$2.5/M$0.027
05MiMo V2.6 Flash RL+2 altsXiaomi61.2$0.14/M$0.28/M$0.003
06Claude Fable 5+3 altsAnthropic57.43P$10.0/M$50.0/M$0.523
07Qwen3.8 Flash Next+1 altAlibaba55.7$0.15/M$0.47/M$0.006
08Muse Spark 1.1+1 altMeta54.7$1.3/M$4.3/M$0.050
09Qwen3.8 Max Preview+1 altAlibaba53.4$3.3/M$9.9/M$0.124
10Kimi K3+1 altMoonshot52.9$0.58/M$12.3/M$0.122
11Claude Opus 4.8+1 altAnthropic48.43P$5.0/M$25.0/M$0.310
12GPT-5.6 Sol+3 altsOpenAI45.43P$4.0/M$20.0/M$0.264
13GLM-5.2Z.ai43.43P$1.4/M$4.4/M$0.067
14DeepSeek-V4-FlashDeepSeek41.3$0.44/M$1.3/M$0.021
15GPT-5.5OpenAI38.33P$5.0/M$30.0/M$0.457
16Claude Opus 4.6Anthropic36.6$5.0/M$25.0/M$0.410
17Qwen3.8 27B+2 altsAlibaba33.4$0.50/M$3.0/M$0.052
18Qwen3.7 MaxAlibaba31.33P$2.5/M$7.5/M$0.160
19Qwen3.7 Plus Preview+1 altAlibaba27.6$0.40/M$1.6/M$0.036
20MiMo V2.5 Pro+1 altXiaomi253P$0.43/M$0.87/M$0.026
21Qwen3.6 27BAlibaba21.83P$0.60/M$3.6/M$0.096
22Qwen3.5 9BAlibaba2.6$0.14/M$0.20/M$0.064
◆ 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: 22 models scored · 0 independently verified · 9 vendor cross-reference · 13 vendor-reported · 0 with source disagreement. How these tiers are assigned