Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d261Policy30d64, 10 pendingSources1,015
Pro Mode — raw scores, one benchmark under the lensofficial card harness
The field · 127 measured
3.333100

127 models measured, most on the official card harness. GPT-5.2 Pro tops the board at 100.

127 measured·1 new this week·Lifecycle Updated Oct 9, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 3.333–100 · ◆ solid = first-party or better · outlined = arm's-length
01GPT-5.2 ProOpenAI100$21.0/M$168.0/M$0.945
02GPT-5.2+4 altsOpenAI100$1.8/M$14.0/M$0.079
03Gemini 3 Pro+6 altsGoogle100$2.0/M$12.0/M$0.070
04Claude Opus 4.6Anthropic99.79$5.0/M$25.0/M$0.150
05Gemini 3 Flash Preview+1 altGoogle99.7$0.50/M$3.0/M$0.018
06NVIDIA Nemotron 3 Nano 30B A3BNVIDIA99.2$0.05/M$0.20/M$0.001
07Seed 2.0ByteDance98.3$0.50/M$3.0/M$0.018
08Step 3.5 Flash+3 altsStepFun97.3$0.10/M$0.30/M$0.002
09MAI-Thinking-1+1 altMicrosoft97———
10Sarvam 30BSarvam AI96.7$0.03/M$0.11/M$0.001
11Sarvam 105BSarvam AI96.7$0.04/M$0.17/M$0.001
12GLM-5Z.ai96.6673P$1.0/M$3.2/M$0.022
13Kimi K2.5+6 altsMoonshot96.1$0.45/M$2.3/M$0.014
14DeepSeek-V3.2-Speciale+1 altDeepSeek96$0.29/M$0.43/M$0.004
15GLM-4.7+5 altsZ.ai95.7$0.60/M$2.2/M$0.015
16GPT-5+7 altsOpenAI94.6$1.3/M$10.0/M$0.059
17Kimi K2 Thinking+7 altsMoonshot94.5$0.60/M$2.5/M$0.016
18Seed 1.8ByteDance94.3$0.25/M$2.0/M$0.012
19MiMo V2 Flash+4 altsXiaomi94.1$0.10/M$0.30/M$0.002
20GPT-5.1 InstantOpenAI94———
21GPT-5.1+2 altsOpenAI94$1.3/M$10.0/M$0.060
22GLM-4.6+3 altsZ.ai93.9$0.57/M$2.2/M$0.015
23GLM-4.5Z.ai93.3333P$0.60/M$2.2/M$0.015
24Grok 3+1 altSpaceXAI93.3$4.0/M$20.0/M$0.129
25DeepSeek-V3.2+11 altsDeepSeek93.1$0.28/M$0.42/M$0.004
26EXAONE 4.5 33BLG AI92.9———
27Claude Opus 4.5+1 altAnthropic92.83P$5.0/M$25.0/M$0.162
28O4 Mini+3 altsOpenAI92.7$1.1/M$4.4/M$0.030
29Grok 4 Fast+1 altSpaceXAI92$0.20/M$0.50/M$0.004
30Grok 4+1 altSpaceXAI91.7$3.0/M$15.0/M$0.098
31GLM-4.7-Flash+1 altZ.ai91.6$0.06/M$0.40/M$0.003
32GPT-5 mini+2 altsOpenAI91.1$0.25/M$2.0/M$0.012
33Mercury 2Inception91.1$0.25/M$0.75/M$0.005
34Grok 3 Mini Reasoning+1 altSpaceXAI90.8$0.30/M$0.50/M$0.004
35Nemotron 3 Super 120B A12BNVIDIA90.21$0.30/M$0.90/M$0.007
36Command A+Cohere90$0.30/M$1.5/M$0.010
37GPT Oss 120bOpenAI903P$0.15/M$0.59/M$0.004
38Qwen3 VL 235B A22B Reasoning+2 altsAlibaba89.7$0.40/M$4.0/M$0.025
39DeepSeek-V3.2-Exp+1 altDeepSeek89.3$0.28/M$0.42/M$0.004
40Granite 4.2 30BIBM89.17$0.16/M$0.65/M$0.005
41GPT Oss 20b+1 altOpenAI89.1673P$0.07/M$0.18/M$0.001
42Qwen3 Next 80B A3BAlibaba87.8$0.15/M$1.2/M$0.008
43Step3 VL 10B+2 altsStepFun87.7———
44ERNIE 5.0 Thinking PreviewBaidu87$0.89/M$3.6/M$0.026
45Claude Sonnet 4.5+6 altsAnthropic87$3.0/M$15.0/M$0.103
46Granite 4.2 8BIBM86.67$0.06/M$0.25/M$0.002
47O3+3 altsOpenAI86.4$2.0/M$8.0/M$0.058
48Mistral Medium 3.5 128BMistral86.3$1.5/M$7.5/M$0.052
49GPT-5 nano+2 altsOpenAI85.2$0.05/M$0.40/M$0.003
50Qwen3 30B A3B 2507 ThinkingAlibaba853P$0.20/M$2.4/M$0.015
51Ministral 3 14BNEW+3 altsMistral85$0.20/M$0.20/M$0.002
52Seed Oss 36B InstructByteDance84.73P$0.21/M$0.57/M$0.005
53Mistral Small 4Mistral83.8$0.15/M$0.60/M$0.004
54Qwen3 VL 32B ReasoningAlibaba83.7$0.16/M$0.64/M$0.005
55GLM-4.5-AirZ.ai83.3333P$0.17/M$0.98/M$0.007
56K2-ThinkMBZUAI83.3333P———
57Qwen3 VL 30B A3B ReasoningAlibaba83.1$0.20/M$2.4/M$0.016
58Gemini 2.5 Pro+9 altsGoogle83$1.3/M$10.0/M$0.068
59O1OpenAI81.6673P$15.0/M$60.0/M$0.459
60Qwen3 Max (Reasoning)Alibaba81.6$1.2/M$6.0/M$0.044
61Qwen3 235B A22B+6 altsAlibaba81.5$0.70/M$2.8/M$0.021
62GPT-5.5 InstantOpenAI81.2$5.0/M$30.0/M$0.216
63MiniMax M2.1+4 altsMiniMax81$0.30/M$1.2/M$0.009
64Claude Haiku 4.5Anthropic80.7$1.0/M$5.0/M$0.037
65Qwen3 VL Thinking (8B)+4 altsAlibaba80.3$0.18/M$2.1/M$0.014
66Ministral 3 8B+3 altsMistral78.7$0.15/M$0.15/M$0.002
67Granite 4.2 3BIBM78.33$0.03/M$0.12/M$0.001
68Claude Opus 4.1Anthropic78$15.0/M$75.0/M$0.577
69Phi 4 Reasoning Plus+2 altsMicrosoft78———
70MiniMax M2+2 altsMiniMax78$0.30/M$1.2/M$0.010
71QED-NanoLM-Provers77.53P———
72MiniMax M1 80K+2 altsMiniMax76.9$0.55/M$2.2/M$0.018
73DeepSeek-R1 0528-Qwen3-8BDeepSeek76.3———
74Claude Opus 4+5 altsAnthropic75.5$15.0/M$75.0/M$0.596
75Qwen3 VL 235B A22B InstructAlibaba74.7$0.40/M$1.6/M$0.013
76MiniMax M1 40K+2 altsMiniMax74.6———
77Qwen3 VL 4B (Reasoning)+4 altsAlibaba74.5———
78Qwen3 32B+1 altAlibaba72.9$0.16/M$0.64/M$0.005
79Llama 3.1 Nemotron Ultra 253B V1NVIDIA72.5———
80NVIDIA Nemotron Nano 9B V2NVIDIA72.1$0.04/M$0.16/M$0.001
81Ministral 3 3B+3 altsMistral72.1$0.10/M$0.10/M$0.001
82Gemini 2.5 Flash+4 altsGoogle72$0.30/M$2.5/M$0.019
83GLM-4.6V (106B-A12B)+1 altZ.ai71.88———
84Qwen3 30B A3B+1 altAlibaba70.9$0.20/M$0.80/M$0.007
85Claude Sonnet 4+3 altsAnthropic70.5$3.0/M$15.0/M$0.128
86Qwen3 14B+4 altsAlibaba70.4$0.35/M$1.4/M$0.012
87Qwen3 235B A22B Instruct 2507Alibaba70.3$0.23/M$0.92/M$0.008
88DeepSeek-R1+3 altsDeepSeek70$2.0/M$4.0/M$0.043
89Qwen3 Next 80B A3B InstructAlibaba69.5$0.15/M$1.2/M$0.010
90Qwen3 VL 30B A3B InstructAlibaba69.3$0.20/M$0.80/M$0.007
91Qwen3 8BAlibaba67.3$0.18/M$0.70/M$0.007
92Qwen3 VL 32B InstructAlibaba66.2$0.16/M$0.64/M$0.006
93Magistral Medium 1Mistral64.9———
94Seed 1.5 VL+1 altByteDance64.06———
95LongCat Flash LiteMeituan63.23———
96DeepSeek-R1-Distill-Qwen-32BDeepSeek603P$0.29/M$0.29/M$0.005
97MiMo 7B RL+8 altsXiaomi55.4———
98DeepSeek-R1-Distill-Llama-70BDeepSeek553P$0.70/M$1.1/M$0.016
99Claude 3.7 Sonnet+1 altAnthropic54.8$3.0/M$15.0/M$0.164
100Gemini 2.0 Flash (Non-Reasoning)Google53.3333P———
101LFM2.5-2.6BLiquid AI51.87———
102DeepSeek-V3+5 altsDeepSeek51.3$0.24/M$0.90/M$0.011
103O1 Mini+4 altsOpenAI50.7———
104Gemini 2.5 Flash LiteGoogle49.8$0.10/M$0.40/M$0.005
105DeepSeek-V3.1+3 altsDeepSeek49.8$0.56/M$1.7/M$0.022
106Kimi K2 Instruct+5 altsMoonshot49.5$0.57/M$2.3/M$0.029
107DeepSeek-R1-Distill-Qwen-14B+5 altsDeepSeek49.1673P$0.20/M$0.20/M$0.004
108O3 Mini+2 altsOpenAI48.3333P$1.1/M$4.4/M$0.057
109Llama 3.1 Nemotron Nano 8B V1NVIDIA47.1———
110Qwen3 VL 4B InstructAlibaba46.6———
111GPT-4.1OpenAI46.4$2.0/M$8.0/M$0.108
112MiMo 7B RL Zero+4 altsXiaomi46.3———
113Qwen3 VL 8B InstructAlibaba45.9$0.18/M$0.70/M$0.010
114MiMo 7B SFT+4 altsXiaomi44.3———
115GPT-5.1 Codex miniOpenAI42.1$0.25/M$2.0/M$0.027
116GPT-4.1 miniOpenAI40.2$0.40/M$1.6/M$0.025
117DeepSeek-R1-Distill-Qwen-7B+4 altsDeepSeek38.8$0.15/M$0.15/M$0.004
118QwQ 32B Preview+5 altsAlibaba33.3333P$0.66/M$1.0/M$0.025
119Gemini 2.0 Pro Exp 02.05Google27.53P———
120Gemini 2.0 Flash (Reasoning)+1 altGoogle27.53P———
121MiMo 7B Base+4 altsXiaomi24.3———
122Llama 4 Maverick+1 altMeta22.53P$0.25/M$0.87/M$0.025
123DeepSeek-R1-Distill-Qwen-1.5BDeepSeek203P———
124Qwen3.5 2BAlibaba19———
125GPT-4o+5 altsOpenAI11.6673P$5.0/M$15.0/M$0.857
126Qwen3.5 0.8BAlibaba8.67———
127Claude 3.5 Sonnet+5 altsAnthropic3.3333P$3.0/M$15.0/M$2.700
◆ 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: 127 models scored · 20 independently verified · 7 vendor cross-reference · 100 vendor-reported · 4 with source disagreement. How these tiers are assigned