Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d263Policy30d65, 14 pendingSources1,013
Pro Mode — raw scores, one benchmark under the lensofficial card harness
The field · 38 measured
4731,853

38 models measured, most on the official card harness. Claude Fable 5.1 tops the board at 1,853.

38 measured·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 473–1,853 · ◆ solid = first-party or better · outlined = arm's-length
01Claude Fable 5.1+2 altsAnthropic1,853$10.0/M$50.0/M$0.016
02Claude Mythos 5.1Anthropic1,853$10.0/M$50.0/M$0.016
03Claude Opus 5+3 altsAnthropic1,824$5.0/M$25.0/M$0.008
04GLM-5.3+1 altZ.ai1,7693P$1.4/M$4.4/M$0.002
05Qwen3.8 Max Preview+1 altAlibaba1,7393P$3.3/M$9.9/M$0.004
06Claude Fable 5+4 altsAnthropic1,723$10.0/M$50.0/M$0.017
07Claude Mythos 5Anthropic1,723$10.0/M$50.0/M$0.017
08GPT-5.6 Sol+6 altsOpenAI1,711$4.0/M$20.0/M$0.007
09Kimi K3+1 altMoonshot1,6823P$0.58/M$12.3/M$0.004
10Claude Sonnet 5Anthropic1,618$2.0/M$10.0/M$0.004
11Claude Opus 4.8+2 altsAnthropic1,593$5.0/M$25.0/M$0.009
12Gemini 3.8 FlashGoogle1,545$0.75/M$3.8/M$0.001
13GPT-5.6 LunaOpenAI1,5303P$0.20/M$1.2/M$0.000
14Gemini 3.7 FlashGoogle1,525$0.75/M$3.8/M$0.001
15GPT-5.5+1 altOpenAI1,509$5.0/M$30.0/M$0.012
16GLM-5.2+3 altsZ.ai1,5083P$1.4/M$4.4/M$0.002
17Gemini 3.6 Flash+3 altsGoogle1,421$0.75/M$3.8/M$0.002
18Claude Sonnet 4.6+1 altAnthropic1,395$3.0/M$15.0/M$0.006
19MiniMax M3MiniMax1,390.8$0.28/M$1.1/M$0.000
20Gemini 3.5 Flash+4 altsGoogle1,349$1.5/M$9.0/M$0.004
21DeepSeek-V4-Pro+1 altDeepSeek1,306$0.43/M$0.87/M$0.000
22MiMo V2.5+1 altXiaomi1,265.1$0.14/M$0.28/M$0.000
23Inkling-Small+1 altThinking Machines1,238$0.30/M$1.2/M$0.001
24Inkling+2 altsThinking Machines1,238$0.95/M$4.0/M$0.002
25Kimi K2.6+1 altMoonshot1,190$0.95/M$4.0/M$0.002
26DeepSeek-V4-Flash+1 altDeepSeek1,189$0.44/M$1.3/M$0.001
27Nemotron 3 Ultra 550B A55B+2 altsNVIDIA1,164$0.60/M$2.5/M$0.001
28MiniMax M2.7+1 altMiniMax1,159$0.21/M$0.84/M$0.000
29Gemini 3.5 Flash Lite+4 altsGoogle1,140$0.30/M$2.5/M$0.001
30Qwen3.6 35B A3BAlibaba1,0153P$0.38/M$2.3/M$0.001
31Kimi K2.5+1 altMoonshot1,009$0.45/M$2.3/M$0.001
32Gemini 3.1 ProGoogle9623P$2.0/M$12.0/M$0.007
33Qwen3.5 397B A17B+1 altAlibaba962$0.60/M$3.6/M$0.002
34Nemotron 3.5 LightningNVIDIA8323P$0.06/M$0.20/M$0.000
35Gemma 4 26B A4BGoogle8073P$0.07/M$0.34/M$0.000
36Nemotron 3 SuperNVIDIA7463P———
37Gemini 3.1 Flash Lite Preview+2 altsGoogle642$0.25/M$1.5/M$0.001
38Nemotron 3 NanoNVIDIA4733P———
◆ 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: 38 models scored · 0 independently verified · 17 vendor cross-reference · 21 vendor-reported · 4 with source disagreement. How these tiers are assigned