Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d268Policy30d67, 15 pendingSources1,014
Pro Mode — raw scores, one benchmark under the lensAA-graded harness
The field · 45 measured
1.84460

45 models measured, most on the AA-graded harness. GPT-6.1 Sol tops the board at 60.

45 measured·3 new this week·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 1.844–60 · ◆ solid = first-party or better · outlined = arm's-length
01GPT-6.1 SolNEWOpenAI60VENDOR$2.0/M$10.0/M$0.100
02Grok 4.6SpaceXAI57.5VENDOR$2.0/M$6.0/M$0.070
03Gemini 3.5 FlashGoogle47.05$1.5/M$9.0/M$0.112
04Claude Fable 5Anthropic43.33P$10.0/M$50.0/M$0.693
05Qwen3.8 Max PreviewAlibaba42.404$3.3/M$9.9/M$0.156
06Kimi K3+3 altsMoonshot41.298$0.58/M$12.3/M$0.156
07GPT-5.6 SolOpenAI39.93P$4.0/M$20.0/M$0.301
08Claude Opus 4.8Anthropic39.43P$5.0/M$25.0/M$0.381
09GPT-5.6 TerraOpenAI38.938$2.0/M$12.0/M$0.180
10Step 5 PreviewStepFun37.979$1.0/M$2.7/M$0.049
11GPT-5.5+2 altsOpenAI37.684$5.0/M$30.0/M$0.464
12Hy4Tencent37.1VENDOR$0.83/M$2.5/M$0.045
13GPT-5.6 LunaOpenAI35.841$0.20/M$1.2/M$0.020
14Claude Opus 4.7Anthropic33.9VENDOR$5.0/M$25.0/M$0.442
15Seed 2.1 Pro Preview+1 altByteDance33.8VENDOR———
16GLM-5.2+1 altZ.ai33.702$1.4/M$4.4/M$0.086
17GPT-5.4+1 altOpenAI33.26$2.5/M$15.0/M$0.263
18Claude Opus 4.6NEW+2 altsAnthropic33.038$5.0/M$25.0/M$0.454
19Gemini 3.1 Pro+6 altsGoogle32.006$2.0/M$12.0/M$0.219
20Apodex 1.1Apodex31.195$0.30/M$3.0/M$0.053
21Seed2.1ByteDance29.2VENDOR———
22Kimi K2.6+2 altsMoonshot28.466$0.95/M$4.0/M$0.087
23GPT-5.4 miniOpenAI28.171$0.75/M$4.5/M$0.093
24Claude Sonnet 4.6NEWAnthropic28.024$3.0/M$15.0/M$0.321
25Gemini 3 Flash PreviewGoogle27.729$0.50/M$3.0/M$0.063
26MiniMax M3MiniMax27.7VENDOR$0.28/M$1.1/M$0.025
27Ling-3.0-flash-Fin+1 altInclusionAI27.434$0.04/M$0.12/M$0.003
28Hy3-previewTencent25.6VENDOR$0.14/M$0.56/M$0.013
29GPT-5.4 nanoOpenAI24.926$0.20/M$1.3/M$0.029
30DeepSeek-V4-Pro+1 altDeepSeek24.263$0.43/M$0.87/M$0.027
31GPT-5.2OpenAI23VENDOR$1.8/M$14.0/M$0.342
32Qwen3.7 Plus PreviewAlibaba22.419$0.40/M$1.6/M$0.045
33Gemini 3 ProGoogle18.4VENDOR$2.0/M$12.0/M$0.380
34Grok 4.3SpaceXAI17.035$1.3/M$2.5/M$0.110
35Qwen3.5 397B A17BAlibaba15.339$0.60/M$3.6/M$0.137
36Step 3.7 FlashStepFun14.823$0.20/M$1.1/M$0.046
37DeepSeek-V3.2DeepSeek14.528$0.28/M$0.42/M$0.024
38GLM-5Z.ai14.454$1.0/M$3.2/M$0.145
39Grok 4.20SpaceXAI14.233$1.3/M$2.5/M$0.132
40Gemini 3.1 Flash Lite PreviewGoogle12.168$0.25/M$1.5/M$0.072
41Kimi K2.5+1 altMoonshot11.504$0.45/M$2.3/M$0.117
42MiniMax M2.7MiniMax10.62$0.21/M$0.84/M$0.049
43GPT Oss 120bOpenAI3.097$0.15/M$0.59/M$0.120
44MiMo V2.5 ProXiaomi2.434$0.43/M$0.87/M$0.268
45Nemotron 3 Super 120B A12BNVIDIA1.844$0.30/M$0.90/M$0.325
◆ 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: 45 models scored · 0 independently verified · 32 aggregator-attributed · 5 vendor cross-reference · 8 vendor-reported · 0 with source disagreement. How these tiers are assigned