Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d263Policy30d65, 14 pendingSources1,013
Pro Mode — raw scores, one benchmark under the lensthird-party eval harness
The field · 60 measured
52.8281.41

60 models measured, most on the third-party eval harness. Gemini 3.8 Flash tops the board at 81.41.

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 52.82–81.41 · ◆ solid = first-party or better · outlined = arm's-length
01Gemini 3.8 FlashGoogle81.41$0.75/M$3.8/M$0.028
02Gemini 3.7 FlashGoogle79.93$0.75/M$3.8/M$0.028
03Gemini 3.1 ProGoogle79.1$2.0/M$12.0/M$0.088
04Muse Spark 1.3Meta78$1.3/M$4.3/M$0.035
05Qwen3.8 Flash NextAlibaba77.11$0.15/M$0.47/M$0.004
06Claude Fable 5Anthropic75.77$10.0/M$50.0/M$0.396
07Gemini 3.5 FlashGoogle75.6$1.5/M$9.0/M$0.069
08GPT-6 AstraOpenAI75.58$10.0/M$50.0/M$0.397
09Gemini 3.6 FlashGoogle75.37$0.75/M$3.8/M$0.030
10Grok 4.7SpaceXAI75.28$2.0/M$6.0/M$0.053
11Muse Spark 1.2Meta74.33$1.3/M$4.3/M$0.037
12GPT-6.1 Sol+1 altOpenAI74.15$2.0/M$10.0/M$0.081
13Qwen3.8 Max PreviewAlibaba74.08$3.3/M$9.9/M$0.089
14Qwen3.7 MaxAlibaba74.04$2.5/M$7.5/M$0.068
15Nemotron 3 Ultra 550B A55BNVIDIA73.45$0.60/M$2.5/M$0.021
16Claude Fable 5.1Anthropic72.99$10.0/M$50.0/M$0.411
17Qwen3.8 27BAlibaba72.66$0.50/M$3.0/M$0.024
18Claude Opus 4.8Anthropic72.03$5.0/M$25.0/M$0.208
19Grok 4.6SpaceXAI71.87$2.0/M$6.0/M$0.056
20GPT-5.6 SolOpenAI71.85$4.0/M$20.0/M$0.167
21Grok4.5SpaceXAI71.53$2.0/M$6.0/M$0.056
22Kimi K3Moonshot71.36$0.58/M$12.3/M$0.090
23DeepSeek-V4-Flash-Vision-ExpDeepSeek70.96$0.22/M$0.65/M$0.006
24GPT-5.5OpenAI70.73$5.0/M$30.0/M$0.247
25GPT-5.4OpenAI70.22$2.5/M$15.0/M$0.125
26InklingThinking Machines70.1$0.95/M$4.0/M$0.036
27DeepSeek-V4.1-FlashDeepSeek70.03$0.20/M$0.60/M$0.006
28Muse Spark 1.1Meta69.64$1.3/M$4.3/M$0.039
29GLM-5.3Z.ai69.3$1.4/M$4.4/M$0.042
30GPT-6 SolOpenAI68.57$2.0/M$10.0/M$0.088
31Gemini 3.5 Flash LiteGoogle67.24$0.30/M$2.5/M$0.021
32GPT-5.4 nanoOpenAI67.2$0.20/M$1.3/M$0.011
33Claude Opus 4.7Anthropic66.74$5.0/M$25.0/M$0.225
34GPT-5.2 CodexOpenAI66.45$1.8/M$14.0/M$0.119
35Claude Opus 5.5+1 altAnthropic65.74$4.0/M$20.0/M$0.183
36DeepSeek-V4-Flash+1 altDeepSeek65.52$0.44/M$1.3/M$0.013
37Mistral Large 4NEWMistral64.82$0.68/M$2.1/M$0.021
38GPT-5.6 TerraOpenAI64.62$2.0/M$12.0/M$0.108
39Kimi K2.6Moonshot64.36$0.95/M$4.0/M$0.038
40Claude Sonnet 5Anthropic63.86$2.0/M$10.0/M$0.094
41Claude Opus 5Anthropic63.77$5.0/M$25.0/M$0.235
42Claude Opus 4.6Anthropic63.31$5.0/M$25.0/M$0.237
43Claude Sonnet 4.6Anthropic63.22$3.0/M$15.0/M$0.142
44Grok 4.3SpaceXAI62.75$1.3/M$2.5/M$0.030
45Claude Opus 4.5Anthropic62.55$5.0/M$25.0/M$0.240
46DeepSeek-V4-ProDeepSeek62.35$0.43/M$0.87/M$0.010
47GLM-5.2Z.ai62.29$1.4/M$4.4/M$0.047
48GPT-5.2OpenAI61.77$1.8/M$14.0/M$0.127
49Ox Alpha MaxStealth60.25———
50GPT-5.6 LunaOpenAI60.12$0.20/M$1.2/M$0.012
51GPT-5.4 miniOpenAI59.8$0.75/M$4.5/M$0.044
52Union AlphaStealth59.53———
53Qwen3.6 PlusAlibaba58.34$0.50/M$3.0/M$0.030
54MiniMax M3MiniMax57.51$0.28/M$1.1/M$0.012
55Sonnet 5.5+1 altAnthropic56.79$2.0/M$10.0/M$0.106
56Kimi K2.7 CodeMoonshot56.29$1.9/M$8.1/M$0.089
57GPT-6 LunaOpenAI55.93$0.10/M$0.50/M$0.005
58Haiku 5.5NEW+1 altAnthropic54.66$0.10/M$0.50/M$0.005
59Qwen3.6 27BAlibaba53.23$0.60/M$3.6/M$0.039
60GLM 5.3 FlashZ.ai52.82$0.15/M$0.50/M$0.006
◆ 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