Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d261Policy30d64, 10 pendingSources1,015
Pro Mode — raw scores, one benchmark under the lensofficial card harness
The field · 34 measured
3.3541.2

34 models measured, most on the official card harness. Atria Dawn tops the board at 41.2.

34 measured·Lifecycle Updated Oct 9, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 3.35–41.2 · ◆ solid = first-party or better · outlined = arm's-length
01Atria Dawnshanghai-ai-lab41.2———
02Ling-3.0-flash-FinInclusionAI41$0.04/M$0.12/M$0.002
03Grok4.5SpaceXAI33$2.0/M$6.0/M$0.121
04GPT-5.6 SolOpenAI333P$4.0/M$20.0/M$0.364
05Ling-3.0-flashInclusionAI28$0.07/M$0.22/M$0.005
06Claude Fable 5Anthropic26.83P$10.0/M$50.0/M$1.119
07GLM-5.2+1 altZ.ai26.8$1.4/M$4.4/M$0.108
08DeepSeek-V4-Pro+1 altDeepSeek26$0.43/M$0.87/M$0.025
09GPT-5.6 LunaOpenAI24.33P$0.20/M$1.2/M$0.029
10Inkling+3 altsThinking Machines23.7$0.95/M$4.0/M$0.105
11Muse GlimmerMeta23.5$0.33/M$1.4/M$0.036
12Solar Pro4Upstage23$0.30/M$1.2/M$0.033
13DeepSeek-V4-Flash+1 altDeepSeek22.9$0.44/M$1.3/M$0.038
14Kimi K2.6+1 altMoonshot20.6$0.95/M$4.0/M$0.120
15Gemini 3.1 ProGoogle16.53P$2.0/M$12.0/M$0.424
16Gemini 3.5 Flash LiteGoogle16.53P$0.30/M$2.5/M$0.085
17Inkling-Small+2 altsThinking Machines15.5$0.30/M$1.2/M$0.048
18Kimi K2.5+1 altMoonshot14.2$0.45/M$2.3/M$0.095
19Gemma 4 26B A4BGoogle14.023P$0.07/M$0.34/M$0.015
20Nemotron 3 Ultra 550B A55B+2 altsNVIDIA13.8$0.60/M$2.5/M$0.112
21Qwen3.5 397B A17B+1 altAlibaba13.4$0.60/M$3.6/M$0.157
22Mistral Medium 3.5 128BMistral13.4$1.5/M$7.5/M$0.336
23MiniMax M3MiniMax13$0.28/M$1.1/M$0.053
24Nemotron 3 SuperNVIDIA12.373P———
25Qwen3.6 35B A3BAlibaba10.523P$0.38/M$2.3/M$0.125
26Nemotron 3.5 Lightning+1 altNVIDIA9.28$0.06/M$0.20/M$0.014
27MiMo V2.5+1 altXiaomi9$0.14/M$0.28/M$0.023
28MiniMax M2.7+1 altMiniMax8.9$0.21/M$0.84/M$0.059
29Nemotron 3 NanoNVIDIA7.013P———
30LFM2.5-2.6B+2 altsLiquid AI5.67———
31Qwen3.5 4B+1 altAlibaba5.45$0.03/M$0.15/M$0.017
32Qwen3.5 9B+1 altAlibaba5.15$0.14/M$0.20/M$0.033
33Gemma 4 E4B+1 altGoogle4.12$0.02/M$0.10/M$0.015
34Gemma 4 E2B+1 altGoogle3.35———
◆ 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: 34 models scored · 0 independently verified · 17 vendor cross-reference · 17 vendor-reported · 2 with source disagreement. How these tiers are assigned