Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d271Policy30d67, 15 pendingSources1,014
Pro Mode — raw scores, one benchmark under the lensthird-party eval harness
The field · 60 measured
68.291.37

60 models measured, most on the third-party eval harness. Sonnet 5.5 tops the board at 91.37.

60 measured·2 new this week·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 68.2–91.37 · ◆ solid = first-party or better · outlined = arm's-length
01Sonnet 5.5+1 altAnthropic91.37$2.0/M$10.0/M$0.066
02Claude Opus 5.5+1 altAnthropic89.25$4.0/M$20.0/M$0.134
03Claude Fable 5.1Anthropic86.38$10.0/M$50.0/M$0.347
04Claude Fable 5Anthropic85.99$10.0/M$50.0/M$0.349
05GPT-5.6 SolOpenAI83.94$4.0/M$20.0/M$0.143
06GPT-5.2 CodexOpenAI83.62$1.8/M$14.0/M$0.094
07GPT-5.6 LunaOpenAI82.92$0.20/M$1.2/M$0.008
08GPT-5.5OpenAI82.15$5.0/M$30.0/M$0.213
09Union AlphaStealth82.15———
10Claude Opus 4.7Anthropic82.09$5.0/M$25.0/M$0.183
11Claude Opus 4.8Anthropic81.83$5.0/M$25.0/M$0.183
12GPT-6 SolOpenAI81.77$2.0/M$10.0/M$0.073
13Claude Opus 5Anthropic81.45$5.0/M$25.0/M$0.184
14Kimi K3Moonshot81.45$0.58/M$12.3/M$0.079
15Muse Spark 1.3Meta81.06$1.3/M$4.3/M$0.034
16Claude Sonnet 5Anthropic80.68$2.0/M$10.0/M$0.074
17GPT-6 AstraOpenAI80.36$10.0/M$50.0/M$0.373
18GPT-6.1 Sol+1 altOpenAI80.36$2.0/M$10.0/M$0.075
19DeepSeek-V4.1-FlashDeepSeek80.04$0.20/M$0.60/M$0.005
20GLM-5.2Z.ai79.65$1.4/M$4.4/M$0.036
21Claude Opus 4.5Anthropic79.65$5.0/M$25.0/M$0.188
22Claude Sonnet 4.6Anthropic79.27$3.0/M$15.0/M$0.114
23GLM 5.3 FlashZ.ai78.95$0.15/M$0.50/M$0.004
24GPT-6 LunaOpenAI78.95$0.10/M$0.50/M$0.004
25GLM-5.3Z.ai78.95$1.4/M$4.4/M$0.037
26Gemini 3.7 FlashGoogle78.89$0.75/M$3.8/M$0.029
27Kimi K2.6Moonshot78.57$0.95/M$4.0/M$0.032
28GPT-5.6 TerraOpenAI78.25$2.0/M$12.0/M$0.089
29Claude Opus 4.6Anthropic78.18$5.0/M$25.0/M$0.192
30Gemini 3.5 FlashGoogle78.18$1.5/M$9.0/M$0.067
31Qwen3.6 PlusAlibaba78.18$0.50/M$3.0/M$0.022
32Gemini 3.6 FlashGoogle77.86$0.75/M$3.8/M$0.029
33Haiku 5.5NEW+1 altAnthropic77.86$0.10/M$0.50/M$0.004
34GPT-5.4OpenAI77.54$2.5/M$15.0/M$0.113
35Muse Spark 1.2Meta77.54$1.3/M$4.3/M$0.035
36Mistral Large 4NEWMistral77.16$0.68/M$2.1/M$0.018
37Muse Spark 1.1Meta77.16$1.3/M$4.3/M$0.036
38Grok 4.7SpaceXAI77.16$2.0/M$6.0/M$0.052
39Grok 4.6SpaceXAI76.78$2.0/M$6.0/M$0.052
40Gemini 3.1 ProGoogle76.45$2.0/M$12.0/M$0.092
41GPT-5.2OpenAI76.07$1.8/M$14.0/M$0.104
42Gemini 3.5 Flash LiteGoogle76.07$0.30/M$2.5/M$0.018
43Ox Alpha MaxStealth75.75———
44Qwen3.8 27BAlibaba75.69$0.50/M$3.0/M$0.023
45DeepSeek-V4-Flash+1 altDeepSeek74.98$0.44/M$1.3/M$0.012
46Qwen3.7 MaxAlibaba74.22$2.5/M$7.5/M$0.067
47Kimi K2.7 CodeMoonshot73.96$1.9/M$8.1/M$0.068
48Qwen3.8 Max PreviewAlibaba72.87$3.3/M$9.9/M$0.091
49Qwen3.8 Flash NextAlibaba72.55$0.15/M$0.47/M$0.004
50Gemini 3.8 FlashGoogle72.49$0.75/M$3.8/M$0.031
51Qwen3.6 27BAlibaba71.79$0.60/M$3.6/M$0.029
52GPT-5.4 miniOpenAI71.62$0.75/M$4.5/M$0.037
53InklingThinking Machines71.02$0.95/M$4.0/M$0.035
54GPT-5.4 nanoOpenAI70.84$0.20/M$1.3/M$0.010
55Nemotron 3 Ultra 550B A55BNVIDIA70.7$0.60/M$2.5/M$0.022
56DeepSeek-V4-ProDeepSeek69.99$0.43/M$0.87/M$0.009
57Grok 4.3SpaceXAI69.93$1.3/M$2.5/M$0.027
58Grok4.5SpaceXAI68.59$2.0/M$6.0/M$0.058
59DeepSeek-V4-Flash-Vision-ExpDeepSeek68.2$0.22/M$0.65/M$0.006
60MiniMax M3MiniMax68.2$0.28/M$1.1/M$0.010
◆ 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: 60 models scored · 60 independently verified · 0 with source disagreement. How these tiers are assigned