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
73.7497.08

60 models measured, most on the third-party eval harness. Claude Opus 5.5 tops the board at 97.08.

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 73.74–97.08 · ◆ solid = first-party or better · outlined = arm's-length
01Claude Opus 5.5+1 altAnthropic97.08$4.0/M$20.0/M$0.124
02Claude Fable 5.1Anthropic97.01$10.0/M$50.0/M$0.309
03GPT-6.1 Sol+1 altOpenAI96.83$2.0/M$10.0/M$0.062
04GPT-6 AstraOpenAI96.81$10.0/M$50.0/M$0.310
05GPT-6 SolOpenAI96.36$2.0/M$10.0/M$0.062
06GPT-5.6 SolOpenAI96.2$4.0/M$20.0/M$0.125
07Sonnet 5.5+1 altAnthropic96.13$2.0/M$10.0/M$0.062
08Claude Fable 5Anthropic95.99$10.0/M$50.0/M$0.313
09Muse Spark 1.3Meta95.95$1.3/M$4.3/M$0.029
10GPT-5.5OpenAI95.86$5.0/M$30.0/M$0.183
11Claude Opus 5Anthropic95.73$5.0/M$25.0/M$0.157
12Grok 4.7SpaceXAI95.68$2.0/M$6.0/M$0.042
13Union AlphaStealth95.29———
14GPT-5.6 TerraOpenAI94.91$2.0/M$12.0/M$0.074
15Claude Opus 4.8Anthropic94.32$5.0/M$25.0/M$0.159
16GPT-5.4OpenAI94.15$2.5/M$15.0/M$0.093
17Mistral Large 4NEWMistral93.58$0.68/M$2.1/M$0.015
18Gemini 3.7 FlashGoogle93.47$0.75/M$3.8/M$0.024
19DeepSeek-V4.1-FlashDeepSeek93.29$0.20/M$0.60/M$0.004
20GPT-5.2OpenAI93.17$1.8/M$14.0/M$0.085
21Claude Sonnet 5Anthropic92.94$2.0/M$10.0/M$0.065
22Claude Opus 4.7Anthropic92.85$5.0/M$25.0/M$0.162
23Grok 4.6SpaceXAI92.57$2.0/M$6.0/M$0.043
24Gemini 3.8 FlashGoogle91.56$0.75/M$3.8/M$0.025
25Qwen3.8 Max PreviewAlibaba91.31$3.3/M$9.9/M$0.072
26Muse Spark 1.2Meta91.2$1.3/M$4.3/M$0.030
27Gemini 3.1 ProGoogle91.04$2.0/M$12.0/M$0.077
28GPT-5.4 nanoOpenAI90.98$0.20/M$1.3/M$0.008
29Grok4.5SpaceXAI90.82$2.0/M$6.0/M$0.044
30DeepSeek-V4-ProDeepSeek90.68$0.43/M$0.87/M$0.007
31Claude Opus 4.5Anthropic90.39$5.0/M$25.0/M$0.166
32GLM-5.2Z.ai89.78$1.4/M$4.4/M$0.032
33Claude Opus 4.6Anthropic89.32$5.0/M$25.0/M$0.168
34GPT-6 LunaOpenAI89.12$0.10/M$0.50/M$0.003
35GPT-5.2 CodexOpenAI88.77$1.8/M$14.0/M$0.089
36Nemotron 3 Ultra 550B A55BNVIDIA88.66$0.60/M$2.5/M$0.017
37InklingThinking Machines88.36$0.95/M$4.0/M$0.028
38Gemini 3.5 FlashGoogle88.24$1.5/M$9.0/M$0.059
39GLM-5.3Z.ai87.9$1.4/M$4.4/M$0.033
40DeepSeek-V4-Flash-Vision-ExpDeepSeek87.81$0.22/M$0.65/M$0.005
41GPT-5.6 LunaOpenAI87.2$0.20/M$1.2/M$0.008
42Muse Spark 1.1Meta87.14$1.3/M$4.3/M$0.032
43Claude Sonnet 4.6Anthropic86.99$3.0/M$15.0/M$0.103
44DeepSeek-V4-Flash+1 altDeepSeek86.79$0.44/M$1.3/M$0.010
45Haiku 5.5NEW+1 altAnthropic86.44$0.10/M$0.50/M$0.003
46Gemini 3.6 FlashGoogle86.4$0.75/M$3.8/M$0.026
47Qwen3.8 27BAlibaba86.21$0.50/M$3.0/M$0.020
48Qwen3.8 Flash NextAlibaba85.82$0.15/M$0.47/M$0.004
49Qwen3.7 MaxAlibaba85.25$2.5/M$7.5/M$0.059
50Kimi K3Moonshot84.44$0.58/M$12.3/M$0.076
51Grok 4.3SpaceXAI84.34$1.3/M$2.5/M$0.022
52Kimi K2.6Moonshot84.28$0.95/M$4.0/M$0.029
53Qwen3.6 PlusAlibaba83.72$0.50/M$3.0/M$0.021
54GLM 5.3 FlashZ.ai81.24$0.15/M$0.50/M$0.004
55Qwen3.6 27BAlibaba79.87$0.60/M$3.6/M$0.026
56Kimi K2.7 CodeMoonshot79.6$1.9/M$8.1/M$0.063
57GPT-5.4 miniOpenAI78.46$0.75/M$4.5/M$0.033
58Ox Alpha MaxStealth77.53———
59MiniMax M3MiniMax76.95$0.28/M$1.1/M$0.009
60Gemini 3.5 Flash LiteGoogle73.74$0.30/M$2.5/M$0.019
◆ 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