Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models739Deals30d254Policy30d64, 14 pendingSources1,010
Pro Mode — raw scores, one benchmark under the lensthird-party eval harness
The field · 50 measured
53.0398.5

50 models measured, most on the third-party eval harness. GPT-5.6 Luna tops the board at 98.5.

50 measured·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 53.03–98.5 · ◆ solid = first-party or better · outlined = arm's-length
01GPT-5.6 Luna+1 altOpenAI98.5VENDOR$0.20/M$1.2/M$0.007
02GPT-5.5+3 altsOpenAI98.48$5.0/M$30.0/M$0.178
03GPT-5.4+8 altsOpenAI97.73$2.5/M$15.0/M$0.090
04Qwen3.7 Max+2 altsAlibaba97.1VENDOR$2.5/M$7.5/M$0.051
05GPT-5.2+1 altOpenAI96.97$1.8/M$14.0/M$0.081
06Kimi K3Moonshot96.97$0.62/M$15.0/M$0.081
07Claude Opus 4.6+8 altsAnthropic96.21$5.0/M$25.0/M$0.156
08Claude Opus 4.8+2 altsAnthropic95.45$5.0/M$25.0/M$0.157
09Gemini 3.5 Flash+1 altGoogle95.45$1.5/M$9.0/M$0.055
10DeepSeek-V4-Pro+11 altsDeepSeek95.2VENDOR$0.43/M$0.87/M$0.007
11DeepSeek-V4-Flash+4 altsDeepSeek94.8VENDOR$0.44/M$1.3/M$0.009
12Gemini 3.1 Pro+11 altsGoogle94.7$2.0/M$12.0/M$0.074
13Claude Opus 4.7+1 altAnthropic93.94$5.0/M$25.0/M$0.160
14Qwen3.7 Plus PreviewAlibaba92.9VENDOR$0.40/M$1.6/M$0.011
15Kimi K2.6+7 altsMoonshot92.7VENDOR$0.95/M$4.0/M$0.027
16GLM-5.2+4 altsZ.ai92.5VENDOR$1.4/M$4.4/M$0.031
17Inkling-Small+1 altThinking Machines90.2VENDOR$0.30/M$1.2/M$0.008
18Gemini 3.6 FlashGoogle89.39$0.75/M$3.8/M$0.025
19Gemini 3 Flash Preview+1 altGoogle89.39$0.50/M$3.0/M$0.020
20Step 3.7 FlashStepFun87.88$0.20/M$1.1/M$0.008
21Qwen3.5 397B A17B+4 altsAlibaba87.88$0.60/M$3.6/M$0.024
22Qwen3.6 Plus+2 altsAlibaba87.8VENDOR$0.50/M$3.0/M$0.020
23Kimi K2.5+4 altsMoonshot87.12$0.45/M$2.3/M$0.015
24Ling-3.0-flashInclusionAI87VENDOR$0.07/M$0.22/M$0.002
25Step 3.5 Flash+2 altsStepFun86.36VENDOR$0.10/M$0.30/M$0.002
26Grok 4.1 Fast+1 altSpaceXAI86.36$0.20/M$0.50/M$0.004
27Gemini 3 Pro+2 altsGoogle86.36$2.0/M$12.0/M$0.081
28InklingThinking Machines86.3$0.95/M$4.0/M$0.029
29Claude Opus 4.5Anthropic85.3$5.0/M$25.0/M$0.176
30MAI-Thinking-1+1 altMicrosoft84.9VENDOR———
31Nemotron 3 Super 120B A12B+1 altNVIDIA84.85$0.30/M$0.90/M$0.007
32MiniMax M3+1 altMiniMax84.4VENDOR$0.28/M$1.1/M$0.008
33Qwen3.6 27B+1 altAlibaba84.3VENDOR$0.60/M$3.6/M$0.025
34DeepSeek-V3.2+3 altsDeepSeek84.09$0.26/M$0.38/M$0.004
35Qwen3.6 35B A3B+2 altsAlibaba83.6VENDOR$0.38/M$2.3/M$0.016
36GLM-5+3 altsZ.ai82.8VENDOR$1.0/M$3.2/M$0.025
37MiMo V2.5+1 altXiaomi82.6VENDOR$0.14/M$0.28/M$0.003
38GLM-5.1+8 altsZ.ai82.6VENDOR$1.4/M$4.4/M$0.035
39Qwen3.5 35B A3B+3 altsAlibaba81.82$0.25/M$2.0/M$0.014
40Qwen3.5 27B+3 altsAlibaba81.06$0.30/M$2.4/M$0.017
41Gemma 4 26B A4BGoogle79$0.07/M$0.34/M$0.003
42Nemotron 3 Ultra 550B A55B+1 altNVIDIA78.8VENDOR$0.60/M$2.5/M$0.020
43Qwen3 30B A3B 2507 Thinking+1 altAlibaba78.79$0.20/M$2.4/M$0.016
44Gemma 4 31B+1 altGoogle77.2$0.17/M$0.40/M$0.004
45Qwen3.5 4B+1 altAlibaba72.87$0.03/M$0.15/M$0.001
46Qwen3.5 9B+1 altAlibaba71.21$0.14/M$0.20/M$0.002
47MiniMax M2.7+3 altsMiniMax71.2VENDOR$0.21/M$0.84/M$0.007
48QED-Nano+1 altLM-Provers64.39———
49Gemini 3.5 Flash Lite+1 altGoogle63.6VENDOR$0.30/M$2.5/M$0.022
50Qwen3 4B 2507 Thinking+1 altAlibaba53.03$0.01/M$0.03/M$0.000
◆ 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: 50 models scored · 25 independently verified · 9 vendor cross-reference · 16 vendor-reported · 2 with source disagreement. How these tiers are assigned