Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d271Policy30d66, 14 pendingSources1,015
Pro Mode — raw scores, one benchmark under the lensthird-party eval harness
The field · 60 measured
49.6490.68

60 models measured, most on the third-party eval harness. Claude Fable 5 tops the board at 90.68.

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 49.64–90.68 · ◆ solid = first-party or better · outlined = arm's-length
01Claude Fable 5Anthropic90.68$10.0/M$50.0/M$0.331
02GPT-6.1 Sol+1 altOpenAI90.13$2.0/M$10.0/M$0.067
03Claude Fable 5.1Anthropic89.5$10.0/M$50.0/M$0.335
04GPT-6 AstraOpenAI89.43$10.0/M$50.0/M$0.335
05Claude Opus 5Anthropic88.69$5.0/M$25.0/M$0.169
06Gemini 3.8 FlashGoogle87.79$0.75/M$3.8/M$0.026
07GPT-5.6 SolOpenAI87.68$4.0/M$20.0/M$0.137
08GPT-5.5OpenAI87.36$5.0/M$30.0/M$0.200
09Claude Opus 5.5+1 altAnthropic86.27$4.0/M$20.0/M$0.139
10Union AlphaStealth85.89———
11Kimi K3Moonshot85.53$0.58/M$12.3/M$0.075
12Gemini 3.7 FlashGoogle85.46$0.75/M$3.8/M$0.026
13Gemini 3.1 ProGoogle85.38$2.0/M$12.0/M$0.082
14GPT-6 SolOpenAI85.3$2.0/M$10.0/M$0.070
15Gemini 3.5 FlashGoogle84.58$1.5/M$9.0/M$0.062
16Gemini 3.6 FlashGoogle83.9$0.75/M$3.8/M$0.027
17Grok 4.6SpaceXAI83.7$2.0/M$6.0/M$0.048
18Claude Opus 4.6Anthropic83.27$5.0/M$25.0/M$0.180
19GPT-5.6 TerraOpenAI82.89$2.0/M$12.0/M$0.084
20Grok4.5SpaceXAI82.8$2.0/M$6.0/M$0.048
21Muse Spark 1.3Meta82.79$1.3/M$4.3/M$0.033
22GPT-5.4OpenAI82.63$2.5/M$15.0/M$0.106
23Claude Opus 4.5Anthropic81.26$5.0/M$25.0/M$0.185
24DeepSeek-V4.1-FlashDeepSeek81.19$0.20/M$0.60/M$0.005
25DeepSeek-V4-Flash-Vision-ExpDeepSeek80.36$0.22/M$0.65/M$0.005
26Grok 4.7SpaceXAI80.14$2.0/M$6.0/M$0.050
27GLM-5.3Z.ai79.86$1.4/M$4.4/M$0.036
28GPT-5.2OpenAI79.81$1.8/M$14.0/M$0.099
29Qwen3.7 MaxAlibaba79.74$2.5/M$7.5/M$0.063
30Qwen3.8 Max PreviewAlibaba79.69$3.3/M$9.9/M$0.083
31Claude Opus 4.8Anthropic79.66$5.0/M$25.0/M$0.188
32DeepSeek-V4-Flash+1 altDeepSeek79.18$0.44/M$1.3/M$0.011
33Muse Spark 1.2Meta78.57$1.3/M$4.3/M$0.035
34DeepSeek-V4-ProDeepSeek78.13$0.43/M$0.87/M$0.008
35Sonnet 5.5+1 altAnthropic77.98$2.0/M$10.0/M$0.077
36Claude Opus 4.7Anthropic77.91$5.0/M$25.0/M$0.193
37Kimi K2.7 CodeMoonshot77.91$1.9/M$8.1/M$0.064
38GLM 5.3 FlashZ.ai77.31$0.15/M$0.50/M$0.004
39MiniMax M3MiniMax76.84$0.28/M$1.1/M$0.009
40GLM-5.2Z.ai76.24$1.4/M$4.4/M$0.038
41Claude Sonnet 4.6Anthropic76.1$3.0/M$15.0/M$0.118
42Kimi K2.6Moonshot75.14$0.95/M$4.0/M$0.033
43Qwen3.6 PlusAlibaba74.99$0.50/M$3.0/M$0.023
44Claude Sonnet 5Anthropic74.97$2.0/M$10.0/M$0.080
45Qwen3.8 Flash NextAlibaba74.64$0.15/M$0.47/M$0.004
46Qwen3.8 27BAlibaba74.35$0.50/M$3.0/M$0.024
47Muse Spark 1.1Meta74.34$1.3/M$4.3/M$0.037
48GPT-6 LunaOpenAI73.83$0.10/M$0.50/M$0.004
49GPT-5.2 CodexOpenAI73.68$1.8/M$14.0/M$0.107
50Grok 4.3SpaceXAI73.58$1.3/M$2.5/M$0.025
51InklingThinking Machines73.46$0.95/M$4.0/M$0.034
52GPT-5.6 LunaOpenAI72.57$0.20/M$1.2/M$0.010
53Gemini 3.5 Flash LiteGoogle71.82$0.30/M$2.5/M$0.019
54GPT-5.4 miniOpenAI70.95$0.75/M$4.5/M$0.037
55Nemotron 3 Ultra 550B A55BNVIDIA70.81$0.60/M$2.5/M$0.022
56Ox Alpha MaxStealth66.14———
57Qwen3.6 27BAlibaba63.3$0.60/M$3.6/M$0.033
58Haiku 5.5NEW+1 altAnthropic62.63$0.10/M$0.50/M$0.005
59GPT-5.4 nanoOpenAI62.51$0.20/M$1.3/M$0.012
60Mistral Large 4NEWMistral49.64$0.68/M$2.1/M$0.028
◆ 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