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
60.1992.65

60 models measured, most on the third-party eval harness. GPT-6 Astra tops the board at 92.65.

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 60.19–92.65 · ◆ solid = first-party or better · outlined = arm's-length
01GPT-6 AstraOpenAI92.65$10.0/M$50.0/M$0.324
02GPT-6.1 Sol+1 altOpenAI92.63$2.0/M$10.0/M$0.065
03Claude Opus 5.5+1 altAnthropic92.15$4.0/M$20.0/M$0.130
04Claude Fable 5.1Anthropic91.69$10.0/M$50.0/M$0.327
05GPT-5.6 SolOpenAI91.65$4.0/M$20.0/M$0.131
06Sonnet 5.5+1 altAnthropic91.63$2.0/M$10.0/M$0.065
07Claude Opus 5Anthropic91.21$5.0/M$25.0/M$0.164
08Kimi K3Moonshot90.67$0.58/M$12.3/M$0.071
09GPT-5.6 TerraOpenAI90.63$2.0/M$12.0/M$0.077
10Grok 4.6SpaceXAI90.51$2.0/M$6.0/M$0.044
11Muse Spark 1.2Meta90$1.3/M$4.3/M$0.031
12GPT-5.5OpenAI89.65$5.0/M$30.0/M$0.195
13Muse Spark 1.3Meta89.65$1.3/M$4.3/M$0.031
14Claude Fable 5Anthropic89.65$10.0/M$50.0/M$0.335
15Gemini 3.8 FlashGoogle89.29$0.75/M$3.8/M$0.025
16Claude Opus 4.8Anthropic89.19$5.0/M$25.0/M$0.168
17Claude Sonnet 5Anthropic88.69$2.0/M$10.0/M$0.068
18Claude Opus 4.6Anthropic88.67$5.0/M$25.0/M$0.169
19GPT-6 SolOpenAI88.65$2.0/M$10.0/M$0.068
20Qwen3.8 Max PreviewAlibaba88.21$3.3/M$9.9/M$0.075
21GPT-5.4OpenAI88.12$2.5/M$15.0/M$0.099
22Gemini 3.7 FlashGoogle87.8$0.75/M$3.8/M$0.026
23Muse Spark 1.1Meta87.73$1.3/M$4.3/M$0.031
24Qwen3.8 Flash NextAlibaba87.38$0.15/M$0.47/M$0.004
25Claude Opus 4.7Anthropic87.19$5.0/M$25.0/M$0.172
26Grok4.5SpaceXAI87.17$2.0/M$6.0/M$0.046
27DeepSeek-V4.1-FlashDeepSeek86.69$0.20/M$0.60/M$0.005
28DeepSeek-V4-Flash+1 altDeepSeek86.63$0.44/M$1.3/M$0.010
29GLM-5.3Z.ai85.8$1.4/M$4.4/M$0.034
30GPT-5.6 LunaOpenAI85.64$0.20/M$1.2/M$0.008
31DeepSeek-V4-Flash-Vision-ExpDeepSeek85.4$0.22/M$0.65/M$0.005
32Gemini 3.6 FlashGoogle85.15$0.75/M$3.8/M$0.026
33Claude Sonnet 4.6Anthropic84.77$3.0/M$15.0/M$0.106
34Haiku 5.5NEW+1 altAnthropic84.63$0.10/M$0.50/M$0.004
35Gemini 3.1 ProGoogle84$2.0/M$12.0/M$0.083
36Mistral Large 4NEWMistral83.94$0.68/M$2.1/M$0.016
37Qwen3.7 MaxAlibaba83.34$2.5/M$7.5/M$0.060
38GPT-5.2OpenAI83.21$1.8/M$14.0/M$0.095
39Kimi K2.7 CodeMoonshot82.81$1.9/M$8.1/M$0.060
40DeepSeek-V4-ProDeepSeek82.69$0.43/M$0.87/M$0.008
41Grok 4.7SpaceXAI82.65$2.0/M$6.0/M$0.048
42Gemini 3.5 FlashGoogle82$1.5/M$9.0/M$0.064
43GPT-6 LunaOpenAI81.77$0.10/M$0.50/M$0.004
44GPT-5.4 nanoOpenAI81.1$0.20/M$1.3/M$0.009
45Union AlphaStealth80.75———
46Claude Opus 4.5Anthropic80.09$5.0/M$25.0/M$0.187
47Qwen3.8 27BAlibaba80.03$0.50/M$3.0/M$0.022
48Kimi K2.6Moonshot79.38$0.95/M$4.0/M$0.031
49GLM-5.2Z.ai78.63$1.4/M$4.4/M$0.037
50InklingThinking Machines78.35$0.95/M$4.0/M$0.032
51GPT-5.2 CodexOpenAI77.71$1.8/M$14.0/M$0.101
52GLM 5.3 FlashZ.ai77.64$0.15/M$0.50/M$0.004
53Ox Alpha MaxStealth76.59———
54Qwen3.6 PlusAlibaba75.83$0.50/M$3.0/M$0.023
55Nemotron 3 Ultra 550B A55BNVIDIA74.7$0.60/M$2.5/M$0.021
56MiniMax M3MiniMax74.48$0.28/M$1.1/M$0.009
57GPT-5.4 miniOpenAI71.32$0.75/M$4.5/M$0.037
58Grok 4.3SpaceXAI70.82$1.3/M$2.5/M$0.026
59Qwen3.6 27BAlibaba70.28$0.60/M$3.6/M$0.030
60Gemini 3.5 Flash LiteGoogle60.19$0.30/M$2.5/M$0.023
◆ 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