Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models743Deals30d268Policy30d68, 11 pendingSources1,019
Pro Mode — raw scores, one benchmark under the lensofficial card harness
The field · 48 measured
1277.9

48 models measured, most on the official card harness. Gemini 4 Argon tops the board at 77.9.

48 measured·3 new this week·Lifecycle Updated Oct 9, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 12–77.9 · ◆ solid = first-party or better · outlined = arm's-length
01Gemini 4 ArgonNEW+2 altsGoogle77.9$2.0/M$10.0/M$0.077
02Muse Spark 1.3Meta75.4$1.3/M$4.3/M$0.036
03GPT-6.1 SolOpenAI75.22$2.0/M$10.0/M$0.080
04Ember-1NEWfireworks75.2$3.0/M$15.0/M$0.120
05Claude Opus 5.5+2 altsAnthropic74.2$4.0/M$20.0/M$0.162
06DeepSeek-V4.1-FlashDeepSeek74.2$0.20/M$0.60/M$0.005
07GPT-6 Astra+1 altOpenAI74.1$10.0/M$50.0/M$0.405
08Gemini 3.8 Flash+2 altsGoogle73.7$0.75/M$3.8/M$0.031
09GPT-5.6 Sol+5 altsOpenAI73$4.0/M$20.0/M$0.164
10MiMo V2.6 Pro+2 altsXiaomi71.9$0.43/M$0.87/M$0.009
11Sonnet 5.5+1 altAnthropic71$2.0/M$10.0/M$0.085
12Grok 4.7+1 altSpaceXAI71$2.0/M$6.0/M$0.056
13Claude Fable 5+4 altsAnthropic70$10.0/M$50.0/M$0.429
14GPT-5.6 Terra+1 altOpenAI70$2.0/M$12.0/M$0.100
15Kimi K3Moonshot69$0.50/M$12.0/M$0.091
16Claude Opus 5+4 altsAnthropic68.8$5.0/M$25.0/M$0.218
17GPT-6 SolOpenAI68.8$2.0/M$10.0/M$0.087
18MiMo V2.6 Flash RL+2 altsXiaomi67.9$0.14/M$0.28/M$0.003
19Claude Mythos 5.1Anthropic67.4$10.0/M$50.0/M$0.445
20GPT-5.6 Luna+1 altOpenAI67$0.20/M$1.2/M$0.010
21GPT-5.5OpenAI67$5.0/M$30.0/M$0.261
22GLM-5.3Z.ai66.9$1.4/M$4.4/M$0.043
23GPT-6 LunaOpenAI66.6$0.10/M$0.50/M$0.005
24Grok 4.6SpaceXAI65.9$2.0/M$6.0/M$0.061
25Gemini 3.7 Flash+2 altsGoogle65.3$0.75/M$3.8/M$0.034
26GLM 5.3 FlashZ.ai63.4$0.15/M$0.50/M$0.005
27Mistral Large 4NEW+2 altsMistral61.7$0.68/M$2.1/M$0.022
28Muse Spark 1.2+1 altMeta59.3$1.3/M$4.3/M$0.046
29Claude Opus 4.8+2 altsAnthropic59$5.0/M$25.0/M$0.254
30Qwen3.8 Flash Next+1 altAlibaba58.7$0.15/M$0.47/M$0.005
31Qwen3.8 Max Preview+1 altAlibaba56.6$3.3/M$9.9/M$0.117
32DeepSeek-V4-FlashDeepSeek54.4$0.44/M$1.3/M$0.016
33Claude Sonnet 5+1 altAnthropic54$2.0/M$10.0/M$0.111
34Grok4.5+1 altSpaceXAI54$2.0/M$6.0/M$0.074
35Muse Spark 1.1+1 altMeta53$1.3/M$4.3/M$0.052
36GPT-5.4OpenAI52$2.5/M$15.0/M$0.168
37Gemini 3.6 Flash+2 altsGoogle49$0.75/M$3.8/M$0.046
38GLM-5.2Z.ai44$1.4/M$4.4/M$0.066
39Qwen3.8 27B+2 altsAlibaba42.2$0.50/M$3.0/M$0.041
40Laguna S 2.1poolside40.4$0.09/M$0.18/M$0.003
41Gemini 3.5 Flash+1 altGoogle37$1.5/M$9.0/M$0.142
42Kimi K2.7 CodeMoonshot31$1.9/M$8.1/M$0.161
43Claude Sonnet 4.6Anthropic30$3.0/M$15.0/M$0.300
44Qwen3.7 MaxAlibaba21.63P$2.5/M$7.5/M$0.231
45MiMo V2.5 Pro+1 altXiaomi193P$0.43/M$0.87/M$0.034
46Qwen3.7 Plus Preview+1 altAlibaba16.5$0.40/M$1.6/M$0.061
47Qwen3.6 27BAlibaba13.33P$0.60/M$3.6/M$0.158
48Gemini 3.1 Pro+1 altGoogle12$2.0/M$12.0/M$0.583
◆ 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: 48 models scored · 0 independently verified · 1 vendor cross-reference · 47 vendor-reported · 0 with source disagreement. How these tiers are assigned