Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models763Deals30d247Policy30d59, 11 pendingSources1,060
Pro Mode — raw scores, one benchmark under the lensofficial card harness
The field · 35 measured
25.980.6

35 models measured, most on the official card harness. Claude Opus 5 tops the board at 80.6.

35 measured·Lifecycle Updated Oct 17, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 25.9–80.6 · ◆ solid = first-party or better · outlined = arm's-length
01Claude Opus 5+4 altsAnthropic80.6$5.0/M$25.0/M$0.186
02Claude Opus 4.8+9 altsAnthropic79.9$5.0/M$25.0/M$0.188
03Claude Mythos 5+2 altsAnthropic79.3$10.0/M$50.0/M$0.378
04Claude Fable 5+3 altsAnthropic77.93P$10.0/M$50.0/M$0.385
05Claude Opus 5.5+1 altAnthropic77.8$4.0/M$20.0/M$0.154
06Claude Sonnet 5.5Anthropic77.8$2.0/M$10.0/M$0.077
07Claude Fable 5.1+1 altAnthropic77.8$10.0/M$50.0/M$0.386
08MiMo V2.6 Pro+2 altsXiaomi76.9$0.43/M$0.87/M$0.008
09Kimi K3+3 altsMoonshot76.53P$0.30/M$11.9/M$0.080
10DeepSeek-V4-Flash-Vision-ExpDeepSeek75.9$0.22/M$0.65/M$0.006
11Muse Spark 1.1Meta75.6$1.3/M$4.3/M$0.036
12GPT-5.6 Sol+5 altsOpenAI74.93P$4.0/M$20.0/M$0.160
13Claude Sonnet 5+2 altsAnthropic74.7$2.0/M$10.0/M$0.080
14DeepSeek-V4-Pro 0813+2 altsDeepSeek74.1$0.66/M$2.0/M$0.018
15MiMo V2.6 Flash RL+2 altsXiaomi73.6$0.14/M$0.28/M$0.003
16Qwen3.8 Flash NextAlibaba73.5$0.15/M$0.47/M$0.004
17GPT-5.5OpenAI73.53P$5.0/M$30.0/M$0.238
18GLM-5.3+1 altZ.ai733P$1.4/M$4.4/M$0.040
19Qwen3.8 Max Preview+2 altsAlibaba72.53P$3.3/M$9.9/M$0.091
20DeepSeek-V4-Flash+8 altsDeepSeek70.3$0.01/M$0.30/M$0.002
21GPT-5.6 Luna+1 altOpenAI67.9$0.20/M$1.2/M$0.010
22Qwen3.8 27BAlibaba67.1$0.50/M$3.0/M$0.026
23GLM-5.2+4 altsZ.ai59.93P$1.4/M$4.4/M$0.048
24Gemini 3.5 Flash Lite+1 altGoogle57.1$0.30/M$2.5/M$0.025
25DeepSeek-V4-Pro+1 altDeepSeek55.9$0.43/M$0.87/M$0.012
26Inkling-Small+1 altThinking Machines54.4$0.30/M$1.2/M$0.014
27Qwen3.7 Plus PreviewAlibaba50.6$0.40/M$1.6/M$0.020
28Qwen3.7 MaxAlibaba49.73P$2.5/M$7.5/M$0.101
29MiMo V2.5 Pro+1 altXiaomi49.13P$0.43/M$0.87/M$0.013
30MiMo V2.5+1 altXiaomi49.1$0.14/M$0.28/M$0.004
31MiniMax M2.7+1 altMiniMax47.5$0.30/M$1.2/M$0.016
32Inkling+1 altThinking Machines45.5$0.95/M$4.0/M$0.055
33Qwen3.5 397B A17B+1 altAlibaba40.7$0.60/M$3.6/M$0.052
34Nemotron 3 Ultra 550B A55B+1 altNVIDIA34.3$0.60/M$2.7/M$0.048
35Qwen3.5 9BAlibaba25.9$0.14/M$0.20/M$0.006
◆ 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: 35 models scored · 0 independently verified · 10 vendor cross-reference · 25 vendor-reported · 5 with source disagreement. How these tiers are assigned