Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models739Deals30d266Policy30d65, 15 pendingSources1,010
Pro Mode — raw scores, one benchmark under the lensofficial card harness
The field · 17 measured
7173,348

17 models measured, most on the official card harness. DeepSeek-V4-Pro tops the board at 3,348.

17 measured·Lifecycle Updated Oct 7, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 717–3,348 · ◆ solid = first-party or better · outlined = arm's-length
01DeepSeek-V4-Pro+5 altsDeepSeek3,348$0.43/M$0.87/M$0.000
02GPT-5.4+2 altsOpenAI3,168$2.5/M$15.0/M$0.003
03DeepSeek-V4-FlashDeepSeek3,052$0.44/M$1.3/M$0.000
04Gemini 3.1 Pro+3 altsGoogle3,052$2.0/M$12.0/M$0.002
05O1+4 altsOpenAI2,061$15.0/M$60.0/M$0.018
06DeepSeek-R1+4 altsDeepSeek2,029$2.0/M$4.0/M$0.001
07O1 Mini+4 altsOpenAI1,820———
08DeepSeek-R1-Distill-Qwen-32B+3 altsDeepSeek1,691$0.29/M$0.29/M$0.000
09DeepSeek-R1-Distill-Llama-70B+3 altsDeepSeek1,633$0.70/M$1.1/M$0.001
10DeepSeek-R1-Distill-Qwen-14B+3 altsDeepSeek1,481$0.20/M$0.20/M$0.000
11QwQ 32B Preview+3 altsAlibaba1,316$0.66/M$1.0/M$0.001
12DeepSeek-R1-Distill-Llama-8B+3 altsDeepSeek1,205$0.05/M$0.05/M$0.000
13DeepSeek-R1-Distill-Qwen-7B+3 altsDeepSeek1,189$0.15/M$0.15/M$0.000
14DeepSeek-V3+4 altsDeepSeek1,134$0.24/M$0.90/M$0.001
15DeepSeek-R1-Distill-Qwen-1.5B+3 altsDeepSeek954———
16GPT-4o+4 altsOpenAI759$5.0/M$15.0/M$0.013
17Claude 3.5 Sonnet+4 altsAnthropic717$3.0/M$15.0/M$0.013
◆ 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: 17 models scored · 0 independently verified · 7 vendor cross-reference · 10 vendor-reported · 1 with source disagreement. How these tiers are assigned