Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d269Policy30d65, 14 pendingSources1,014
Pro Mode — raw scores, one benchmark under the lensthird-party eval harness
The field · 91 measured
675.6

91 models measured, most on the third-party eval harness. GPT-6 Astra tops the board at 75.6.

91 measured·2 new this week·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 6–75.6 · ◆ solid = first-party or better · outlined = arm's-length
01GPT-6 AstraOpenAI75.6$10.0/M$50.0/M$0.397
02GPT-6.1 SolNEW+1 altOpenAI73.9VENDOR$2.0/M$10.0/M$0.081
03Gemini 3.1 Pro+5 altsGoogle73.5$2.0/M$12.0/M$0.095
04Gemini 3 ProGoogle72.9$2.0/M$12.0/M$0.096
05Claude Opus 5.5Anthropic72.2$4.0/M$20.0/M$0.166
06Claude Fable 5.1Anthropic70.8$10.0/M$50.0/M$0.424
07Claude Fable 5+1 altAnthropic70.7$10.0/M$50.0/M$0.424
08Gemini 3.8 FlashGoogle69.7$0.75/M$3.8/M$0.032
09GPT-5.6 Sol+1 altOpenAI69.7$4.0/M$20.0/M$0.172
10Gemini 3.7 FlashGoogle69.2$0.75/M$3.8/M$0.033
11Gemini 3 Flash PreviewGoogle66.8$0.50/M$3.0/M$0.026
12Muse SparkMeta66.3———
13Gemini 3.6 FlashGoogle66.2$0.75/M$3.8/M$0.034
14Gemini 3.5 FlashGoogle66.2$1.5/M$9.0/M$0.079
15GPT-5.5 ProOpenAI64.5$30.0/M$180.0/M$1.628
16GPT-5.5OpenAI63$5.0/M$30.0/M$0.278
17GPT-6 SolOpenAI60.7$2.0/M$10.0/M$0.099
18Muse Spark 1.2Meta60.3$1.3/M$4.3/M$0.046
19Claude Opus 5+1 altAnthropic59.9$5.0/M$25.0/M$0.250
20Muse Spark 1.1Meta57.79$1.3/M$4.3/M$0.048
21Grok 4.7NEWSpaceXAI56$2.0/M$6.0/M$0.071
22Gemini 2.5 ProGoogle56$1.3/M$10.0/M$0.100
23Qwen3.7 MaxAlibaba55.77$2.5/M$7.5/M$0.090
24Claude Opus 4.8Anthropic53$5.0/M$25.0/M$0.283
25Qwen3.6 Max PreviewAlibaba52$1.3/M$7.8/M$0.087
26Claude Opus 4.7Anthropic51.7$5.0/M$25.0/M$0.290
27Kimi K3Moonshot50.6$0.58/M$12.3/M$0.127
28GPT-5OpenAI50.1$1.3/M$10.0/M$0.112
29O3OpenAI49.4$2.0/M$8.0/M$0.101
30Grok 4.6+1 altSpaceXAI48.9$2.0/M$6.0/M$0.082
31Qwen3 Max InstructAlibaba48.75———
32Grok4.5SpaceXAI48.3$2.0/M$6.0/M$0.083
33GPT-5.1OpenAI48$1.3/M$10.0/M$0.117
34Grok 4SpaceXAI47.9$3.0/M$15.0/M$0.188
35Qwen3.8 Max Preview+1 altAlibaba47.3$3.3/M$9.9/M$0.140
36Claude Opus 4.6+4 altsAnthropic47$5.0/M$25.0/M$0.319
37Sonnet 5.5Anthropic46.5$2.0/M$10.0/M$0.129
38GPT-5.4 ProOpenAI46.3$30.0/M$180.0/M$2.268
39DeepSeek-V4-Pro+10 altsDeepSeek46.2VENDOR$0.43/M$0.87/M$0.014
40Claude Opus 4.5Anthropic45.7$5.0/M$25.0/M$0.328
41GPT-5.4+4 altsOpenAI45.1$2.5/M$15.0/M$0.194
42Qwen3.6 PlusAlibaba44.14$0.50/M$3.0/M$0.040
43Inkling+3 altsThinking Machines43.9VENDOR$0.95/M$4.0/M$0.057
44GPT-5.6 TerraOpenAI43.2$2.0/M$12.0/M$0.162
45GPT-6 LunaOpenAI41.4$0.10/M$0.50/M$0.007
46O1+1 altOpenAI41.1$15.0/M$60.0/M$0.912
47GPT-5.6 LunaOpenAI41$0.20/M$1.2/M$0.017
48GLM-5.3Z.ai41$1.4/M$4.4/M$0.071
49Qwen3 235B A22BAlibaba40.44$0.70/M$2.8/M$0.043
50GPT-5.5 InstantOpenAI38$5.0/M$30.0/M$0.461
51GPT-5.2+3 altsOpenAI37.1$1.8/M$14.0/M$0.212
52Kimi K2.7 CodeMoonshot36.5$1.9/M$8.1/M$0.137
53Kimi K2.6+5 altsMoonshot34.9$0.95/M$4.0/M$0.071
54Claude Opus 4.1Anthropic34.8$15.0/M$75.0/M$1.293
55Kimi K2.5+1 altMoonshot34.3$0.45/M$2.3/M$0.039
56GLM-5.2+1 altZ.ai34.2$1.4/M$4.4/M$0.085
57DeepSeek-V4-Flash+6 altsDeepSeek34.1VENDOR$0.44/M$1.3/M$0.026
58GLM-5.1+3 altsZ.ai34$1.4/M$4.4/M$0.085
59Claude Sonnet 5+1 altAnthropic33.7$2.0/M$10.0/M$0.178
60Grok 4.3 BetaSpaceXAI33.2———
61Claude Sonnet 4.6+2 altsAnthropic32.8$3.0/M$15.0/M$0.274
62Nemotron 3 Ultra 550B A55BNVIDIA32.4$0.60/M$2.5/M$0.048
63GLM-4.7Z.ai32.2$0.60/M$2.2/M$0.043
64GLM 5.3 FlashZ.ai32$0.15/M$0.50/M$0.010
65GPT-4.1OpenAI31.1$2.0/M$8.0/M$0.161
66MAI-Thinking-1Microsoft31VENDOR———
67Claude Sonnet 4.5+1 altAnthropic30.7$3.0/M$15.0/M$0.293
68Grok 4.20SpaceXAI30.2$1.3/M$2.5/M$0.062
69GPT-5.4 miniOpenAI29.4$0.75/M$4.5/M$0.089
70DeepSeek-V3.2DeepSeek27.5$0.28/M$0.42/M$0.013
71GPT-4o+1 altOpenAI26$5.0/M$15.0/M$0.385
72Qwen3.5 397B A17BAlibaba26VENDOR$0.60/M$3.6/M$0.081
73Qwen3.5 PlusAlibaba25.35$0.40/M$2.4/M$0.055
74GPT-5 miniOpenAI21.6$0.25/M$2.0/M$0.052
75Grok 3 Mini ReasoningSpaceXAI21.1$0.30/M$0.50/M$0.019
76Inkling-Small+2 altsThinking Machines20.6VENDOR$0.30/M$1.2/M$0.036
77Qwen3.5 FlashAlibaba20.32$0.10/M$0.40/M$0.012
78O4 Mini+1 altOpenAI18.8$1.1/M$4.4/M$0.146
79MiMo V2.5Xiaomi16.1VENDOR$0.14/M$0.28/M$0.013
80Qwen 3.6 FlashAlibaba15.92$0.25/M$1.5/M$0.055
81O3 MiniOpenAI15.3$1.1/M$4.4/M$0.180
82GPT Oss 120bOpenAI13.9$0.15/M$0.59/M$0.027
83Claude Haiku 4.5Anthropic13.2$1.0/M$5.0/M$0.227
84GPT-4.1 miniOpenAI12.7$0.40/M$1.6/M$0.079
85Claude 3 OpusAnthropic12.6$15.0/M$75.0/M$3.571
86GPT-5 nanoOpenAI11.7$0.05/M$0.40/M$0.019
87GPT-5.4 nanoOpenAI11.7$0.20/M$1.3/M$0.062
88Gemma 4 31BGoogle10.4$0.17/M$0.40/M$0.027
89GPT-4o miniOpenAI8.3$0.15/M$0.60/M$0.045
90Claude 3.5 Haiku+1 altAnthropic6.7———
91GPT-4.1 nanoOpenAI6$0.10/M$0.40/M$0.042
◆ 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: 91 models scored · 82 independently verified · 3 vendor cross-reference · 6 vendor-reported · 3 with source disagreement. How these tiers are assigned