Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models739Deals30d257Policy30d64, 14 pendingSources1,010
Pro Mode — raw scores, one benchmark under the lensofficial card harness
The field · 61 measured
1581.95

61 models measured, most on the official card harness. GPT-6.1 Sol tops the board at 81.95.

61 measured·2 new this week·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 15–81.95 · ◆ solid = first-party or better · outlined = arm's-length
01GPT-6.1 SolNEWOpenAI81.953P$2.0/M$10.0/M$0.073
02Muse SparkMeta75.523P———
03Muse Spark 1.1Meta75.33P$1.3/M$4.3/M$0.037
04Gemini 3.1 ProGoogle71.373P$2.0/M$12.0/M$0.098
05Ling-3.1-flashNEWInclusionAI69.78$0.30/M$0.90/M$0.009
06GPT-5+3 altsOpenAI69.6$1.3/M$10.0/M$0.081
07GPT-5.4 ProOpenAI69.233P$30.0/M$180.0/M$1.517
08Qwen3.5 397B A17BAlibaba67.6$0.60/M$3.6/M$0.031
09Seed 1.8ByteDance66.7$0.25/M$2.0/M$0.017
10Gemini 3 ProGoogle65.673P$2.0/M$12.0/M$0.107
11Nemotron 3 Ultra 550B A55BNVIDIA63.8$0.60/M$2.5/M$0.024
12GPT-5.1OpenAI63.413P$1.3/M$10.0/M$0.089
13Qwen3 Max (Reasoning)Alibaba63.3$1.2/M$6.0/M$0.057
14Step3 VL 10BStepFun62.6———
15O3 ProOpenAI62.43P$20.0/M$80.0/M$0.801
16Qwen3.5 122B A10BAlibaba61.5$0.40/M$3.2/M$0.029
17Kimi K2.5Moonshot61.393P$0.45/M$2.3/M$0.022
18Qwen3.5 27BAlibaba60.8$0.30/M$2.4/M$0.022
19Gemini 3.1 Flash Lite PreviewGoogle60.613P$0.25/M$1.5/M$0.014
20O3+3 altsOpenAI60.4$2.0/M$8.0/M$0.083
21Qwen3 235B Thinking+1 altAlibaba60.3———
22Qwen3.5 35B A3BAlibaba60$0.25/M$2.0/M$0.019
23GPT-5 miniOpenAI58.993P$0.25/M$2.0/M$0.019
24Claude Opus 4.5Anthropic58.973P$5.0/M$25.0/M$0.254
25Claude Opus 4+4 altsAnthropic58.623P$15.0/M$75.0/M$0.768
26Claude Opus 4.1Anthropic57.23P$15.0/M$75.0/M$0.787
27Claude Sonnet 4+2 altsAnthropic57.113P$3.0/M$15.0/M$0.158
28Kimi K2 Thinking+2 altsMoonshot55.423P$0.60/M$2.5/M$0.028
29Claude Sonnet 4.5Anthropic55.323P$3.0/M$15.0/M$0.163
30Nemotron 3 Super 120B A12BNVIDIA55.23$0.30/M$0.90/M$0.011
31GLM-4.6+1 altZ.ai54.9$0.57/M$2.2/M$0.025
32Qwen3.5 9BAlibaba54.5$0.14/M$0.20/M$0.003
33DeepSeek-V3.1-Terminus+1 altDeepSeek54.4$0.27/M$1.0/M$0.012
34Kimi K2 Instruct+3 altsMoonshot54.1$0.57/M$2.3/M$0.027
35Gemini 2.5 Pro+2 altsGoogle53.623P$1.3/M$10.0/M$0.105
36MAI-Thinking-1Microsoft53———
37Claude 3.7 SonnetAnthropic51.583P$3.0/M$15.0/M$0.174
38GPT-5.1 InstantOpenAI51.233P———
39Claude Haiku 4.5Anthropic50.493P$1.0/M$5.0/M$0.059
40Qwen3.5 4BAlibaba49$0.03/M$0.15/M$0.002
41PaCoRe-8BStepFun47———
42DeepSeek-V3.1DeepSeek46.13P$0.56/M$1.7/M$0.024
43GPT Oss 120bOpenAI45.343P$0.15/M$0.59/M$0.008
44MiniMax M1 80K+2 altsMiniMax44.7$0.55/M$2.2/M$0.031
45MiniMax M1 40K+2 altsMiniMax44.7———
46GPT-4.5 PreviewOpenAI43.8———
47O4 Mini+1 altOpenAI43$1.1/M$4.4/M$0.064
48Qwen3 235B A22B+4 altsAlibaba41.223P$0.70/M$2.8/M$0.042
49DeepSeek-R1+1 altDeepSeek40.73P$2.0/M$4.0/M$0.074
50GPT-4oOpenAI40.3$5.0/M$15.0/M$0.248
51O3 MiniOpenAI39.9$1.1/M$4.4/M$0.069
52NVIDIA Nemotron 3 Nano 30B A3BNVIDIA38.5$0.05/M$0.20/M$0.003
53GPT-4.1+1 altOpenAI38.3$2.0/M$8.0/M$0.131
54Claude Opus 4.6+2 altsAnthropic37.153P$5.0/M$25.0/M$0.404
55Gemini 2.0 Flash (Non-Reasoning)Google36.353P———
56GPT-4.1 miniOpenAI35.8$0.40/M$1.6/M$0.028
57Qwen3.5 2BAlibaba33.7———
58RLVR-8B+1 altStepFun33.3———
59DeepSeek-V3+1 altDeepSeek31.43P$0.24/M$0.90/M$0.018
60Qwen3.5 0.8BAlibaba18.9———
61GPT-4.1 nanoOpenAI15$0.10/M$0.40/M$0.017
◆ 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: 61 models scored · 26 independently verified · 5 vendor cross-reference · 30 vendor-reported · 0 with source disagreement. How these tiers are assigned