Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d262Policy30d64, 11 pendingSources1,015
Pro Mode — raw scores, one benchmark under the lensAA-graded harness
The field · 182 measured
4.1987.688

182 models measured, most on the AA-graded harness. Claude Opus 5.5 tops the board at 87.688.

182 measured·9 new this week·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 4.19–87.688 · ◆ solid = first-party or better · outlined = arm's-length
01Claude Opus 5.5NEW+3 altsAnthropic87.688$4.0/M$20.0/M$0.137
02GPT-6 Astra+5 altsOpenAI86.879$10.0/M$50.0/M$0.345
03GPT-6.1 Sol+5 altsOpenAI85.954$2.0/M$10.0/M$0.070
04Claude Opus 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback)NEWAnthropic85.723$4.0/M$20.0/M$0.140
05Gemini 3.8 Flash+2 altsGoogle85.607$0.75/M$3.8/M$0.026
06Gemini 3.7 Flash+2 altsGoogle85.491$0.75/M$3.8/M$0.026
07Claude Opus 5NEW+4 altsAnthropic84.74$5.0/M$25.0/M$0.177
08Gemini 3.5 Flash+5 altsGoogle84.278$1.5/M$9.0/M$0.062
09Claude Fable 5Anthropic84.23P$10.0/M$50.0/M$0.356
10GPT-5.6 Sol+7 altsOpenAI83.41$4.0/M$20.0/M$0.144
11Gemini 3.6 FlashGoogle83.237$0.75/M$3.8/M$0.027
12GPT-6 Sol+5 altsOpenAI82.948$2.0/M$10.0/M$0.072
13Qwen3.8 Max Preview+2 altsAlibaba82.775$3.3/M$9.9/M$0.080
14Seed 2.1 Pro Preview+1 altByteDance82.7VENDOR———
15Gemini 3.1 Pro+8 altsGoogle82.428$2.0/M$12.0/M$0.085
16Muse Spark 1.3Meta82.023$1.3/M$4.3/M$0.034
17GPT-5.6 Terra+6 altsOpenAI80.694$2.0/M$12.0/M$0.087
18Kimi K3+3 altsMoonshot80.52$0.58/M$12.3/M$0.080
19Muse Spark+1 altMeta80.52———
20Qwen3.7 Plus Preview+1 altAlibaba80.462$0.40/M$1.6/M$0.012
21Grok4.5SpaceXAI80.405$2.0/M$6.0/M$0.050
22Gemini 3 Pro+3 altsGoogle80.173$2.0/M$12.0/M$0.087
23Seed2.1ByteDance80.1VENDOR———
24Gemini 3 Flash Preview+3 altsGoogle79.942$0.50/M$3.0/M$0.022
25GPT-5.5+6 altsOpenAI79.884$5.0/M$30.0/M$0.219
26Qwen3.8 Flash NextAlibaba79.769$0.15/M$0.47/M$0.004
27GPT-6 Luna+5 altsOpenAI79.653$0.10/M$0.50/M$0.004
28Kimi K2.6+3 altsMoonshot79.364$0.95/M$4.0/M$0.031
29Apodex 1.1Apodex79.191$0.30/M$3.0/M$0.021
30Gemini 3.5 Flash LiteGoogle79.017$0.30/M$2.5/M$0.018
31Ling-3.0-flash-VLInclusionAI78.96$0.02/M$0.06/M$0.001
32Claude Opus 4.7NEW+4 altsAnthropic78.844$5.0/M$25.0/M$0.190
33MiniMax M3+1 altMiniMax78.555$0.28/M$1.1/M$0.009
34GPT-5.6 Luna+6 altsOpenAI78.555$0.20/M$1.2/M$0.009
35GPT-5.3 CodexOpenAI78.497$1.8/M$14.0/M$0.100
36GPT-5.4+4 altsOpenAI78.439$2.5/M$15.0/M$0.112
37Grok 4.7NEWSpaceXAI78.15$2.0/M$6.0/M$0.051
38Grok 4.3+4 altsSpaceXAI78.093$1.3/M$2.5/M$0.024
39Qwen3.6 Plus+1 altAlibaba77.977$0.50/M$3.0/M$0.022
40Claude Sonnet 5NEW+1 altAnthropic77.283$2.0/M$10.0/M$0.078
41Qwen3.5 397B A17B+2 altsAlibaba77.283$0.60/M$3.6/M$0.027
42DeepSeek-V4.1-Flash+1 altDeepSeek76.994$0.20/M$0.60/M$0.005
43Mistral Large 4NEWMistral76.416$0.68/M$2.1/M$0.018
44Step 5 PreviewStepFun76.358$1.0/M$2.7/M$0.024
45GPT-5.2 CodexOpenAI76.301$1.8/M$14.0/M$0.103
46Qwen3.8 27B+3 altsAlibaba76.301$0.50/M$3.0/M$0.023
47GPT-5.5 InstantOpenAI76VENDOR$5.0/M$30.0/M$0.230
48Gemini 3.1 Flash Lite Preview+1 altGoogle75.549$0.25/M$1.5/M$0.012
49GPT-5.1+1 altOpenAI75.491$1.3/M$10.0/M$0.075
50Claude Opus 4.6NEW+5 altsAnthropic75.434$5.0/M$25.0/M$0.199
51Agnes 2.5 Pro BetaSapiens AI75.434———
52MiMo V2.5+1 altXiaomi75.434$0.14/M$0.28/M$0.003
53Kimi K2.5+5 altsMoonshot75.376$0.45/M$2.3/M$0.018
54Step 3.7 FlashStepFun75.318$0.20/M$1.1/M$0.009
55Qwen3.6 35B A3B+4 altsAlibaba75.029$0.38/M$2.3/M$0.017
56Qwen3.5 27B+3 altsAlibaba75.029$0.30/M$2.4/M$0.018
57Qwen3.5 122B A10B+2 altsAlibaba74.971$0.40/M$3.2/M$0.024
58Gemini 2.5 ProGoogle74.913$1.3/M$10.0/M$0.075
59Qwen3.6 27B+2 altsAlibaba74.624$0.60/M$3.6/M$0.028
60GPT-5.2+4 altsOpenAI74.567$1.8/M$14.0/M$0.106
61Muse Glimmer+1 altMeta74.335$0.33/M$1.4/M$0.011
62GPT-5+4 altsOpenAI74.22$1.3/M$10.0/M$0.076
63Inkling-Small+1 altThinking Machines74.046$0.30/M$1.2/M$0.010
64Claude Opus 4.5+3 altsAnthropic74.046$5.0/M$25.0/M$0.203
65GPT-5 CodexOpenAI73.815$1.3/M$10.0/M$0.076
66Inkling+2 altsThinking Machines73.468$0.95/M$4.0/M$0.034
67Gemma 4 31B+31 altsGoogle73.41$0.17/M$0.40/M$0.004
68GPT-5.4 mini+3 altsOpenAI73.295$0.75/M$4.5/M$0.036
69Claude Sonnet 4.6NEW+5 altsAnthropic73.295$3.0/M$15.0/M$0.123
70Seed 1.8ByteDance73.2VENDOR$0.25/M$2.0/M$0.015
71Grok 4.20SpaceXAI73.179$1.3/M$2.5/M$0.026
72Gemini 2.5 Flash (Sep) (Non-Reasoning)+1 altGoogle73.121———
73MiMo V2.6 Flash RLXiaomi73.064$0.14/M$0.28/M$0.003
74GLM 5V TurboZ.ai72.775$1.2/M$4.0/M$0.036
75Qwen3.5 35B A3B+3 altsAlibaba72.659$0.25/M$2.0/M$0.015
76GPT-5.1 CodexOpenAI72.486$1.3/M$10.0/M$0.078
77Qwen3.5 Omni PlusAlibaba70.52$0.40/M$4.8/M$0.037
78GPT-5 mini+2 altsOpenAI70.058$0.25/M$2.0/M$0.016
79O3+1 altOpenAI70.058$2.0/M$8.0/M$0.071
80MiMo V2 Omni+1 altXiaomi69.884$0.40/M$2.0/M$0.017
81Gemma 4 12B+25 altsGoogle69.653$0.10/M$0.30/M$0.003
82Gemma 4 26B A4B+34 altsGoogle69.249$0.07/M$0.34/M$0.003
83O4 MiniOpenAI69.249$1.1/M$4.4/M$0.040
84Qwen3.5 9B+1 altAlibaba69.249$0.14/M$0.20/M$0.002
85Gemini 2.5 Flash+1 altGoogle69.075$0.30/M$2.5/M$0.020
86GPT-5.1 Codex miniOpenAI69.017$0.25/M$2.0/M$0.016
87Grok 4SpaceXAI68.844$3.0/M$15.0/M$0.131
88Qwen3 VL 235B A22B Reasoning+2 altsAlibaba68.728$0.40/M$4.0/M$0.032
89Claude Sonnet 4.5+2 altsAnthropic68.728$3.0/M$15.0/M$0.131
90Doubao Seed CodeByteDance68.093———
91Claude Opus 4.1Anthropic67.919$15.0/M$75.0/M$0.663
92Qwen3 VL 235B A22B Instruct+1 altAlibaba67.572$0.40/M$1.6/M$0.015
93EXAONE 4.5 33B+1 altLG AI67.341———
94GPT-5.4 nano+3 altsOpenAI65.376$0.20/M$1.3/M$0.011
95Qwen3.5 4B+2 altsAlibaba65.376$0.03/M$0.15/M$0.001
96Gemini 2.5 Flash Lite Preview 09-2025+1 altGoogle64.971$0.10/M$0.40/M$0.004
97Mistral Medium 3.5 128BMistral64.856$1.5/M$7.5/M$0.069
98Qwen3.5 Omni FlashAlibaba64.74$0.10/M$0.80/M$0.007
99ERNIE 5.0 Thinking PreviewBaidu64.567$0.89/M$3.6/M$0.035
100Nova 2.0 Pro Preview+1 altAmazon64.509$1.3/M$10.0/M$0.087
101Qwen3 VL 32B Instruct+1 altAlibaba64.278$0.16/M$0.64/M$0.006
102JT-4.1 Flash 236B A21BChina Mobile64.104———
103Step3 VL 10BStepFun63.988———
104Nova 2.0 Lite+3 altsAmazon63.757$0.30/M$2.5/M$0.022
105Qwen3 VL 32B Reasoning+1 altAlibaba63.41$0.16/M$0.64/M$0.006
106Grok 4.1 Fast+1 altSpaceXAI63.295$0.20/M$0.50/M$0.006
107Command A++1 altCohere63.237$0.30/M$1.5/M$0.014
108Qwen3 VL 30B A3B Instruct+1 altAlibaba62.139$0.20/M$0.80/M$0.008
109Llama 4 Maverick+3 altsMeta62.139$0.25/M$0.87/M$0.009
110Nova 2.0 Omni Reasoning Medium+2 altsAmazon61.908$0.30/M$2.5/M$0.023
111Qwen3 VL 30B A3B Reasoning+1 altAlibaba61.85$0.20/M$2.4/M$0.021
112Grok 4 Fast+1 altSpaceXAI61.792$0.20/M$0.50/M$0.006
113Claude Sonnet 4+1 altAnthropic61.792$3.0/M$15.0/M$0.146
114GPT-4.1OpenAI61.214$2.0/M$8.0/M$0.082
115GPT-5 nano+2 altsOpenAI60.983$0.05/M$0.40/M$0.004
116Qwen3 Omni 30B A3BAlibaba60.231$0.25/M$0.97/M$0.010
117Claude 3.7 SonnetAnthropic60.058$3.0/M$15.0/M$0.150
118Magistral Medium 1.2Mistral59.653———
119GPT-4.1 miniOpenAI58.728$0.40/M$1.6/M$0.017
120Claude Haiku 4.5+1 altAnthropic58.555$1.0/M$5.0/M$0.051
121Gemini 2.5 Flash Lite+1 altGoogle58.208$0.10/M$0.40/M$0.004
122Apriel-v1.5-15B-ThinkerServiceNow57.052———
123Gemini 2.0 Flash ExpGoogle573P———
124Mistral Small 4+2 altsMistral56.821$0.15/M$0.60/M$0.007
125Qwen3 VL Thinking (8B)+1 altAlibaba56.647$0.18/M$2.1/M$0.020
126GPT-4o+4 altsOpenAI56.301$5.0/M$15.0/M$0.178
127Mistral Large 3Mistral55.665$0.50/M$1.5/M$0.018
128Qwen3 Omni 30B A3B InstructAlibaba55.491$0.25/M$0.97/M$0.011
129Magistral Small 1.2Mistral55.491$0.50/M$1.5/M$0.018
130Gemini 1.5 Pro+2 altsGoogle55.029———
131Claude 3.5 Sonnet+1 altAnthropic54.7VENDOR$3.0/M$15.0/M$0.165
132Mistral Medium 3.1 (Non-Reasoning)Mistral54.162$0.40/M$2.0/M$0.022
133Nemotron 3 Nano OmniNVIDIA53.179$0.30/M$0.90/M$0.011
134Llama 4 Scout+1 altMeta52.948$0.19/M$0.68/M$0.008
135NVIDIA Nemotron Nano 12B v2 VL+1 altNVIDIA52.89$0.20/M$0.60/M$0.008
136MiniMax VL 01MiniMax52.73P———
137Qwen3 VL 4B (Reasoning)+1 altAlibaba52.023———
138Gemma 4 E4B+34 altsGoogle51.387$0.02/M$0.10/M$0.001
139Qwen2.5 VL 72B+1 altAlibaba51.1VENDOR———
140Pixtral LargeMistral50.578———
141GLM-4.5V+1 altZ.ai50.462$0.60/M$1.8/M$0.024
142Ministral 3 14BMistral49.827$0.20/M$0.20/M$0.004
143Qwen2.5 VL 32B Instruct+2 altsAlibaba49.5VENDOR———
144GLM-4.6V+1 altZ.ai48.555$0.30/M$0.90/M$0.012
145Gemini 1.5 Flash (001)Google48.382———
146Gemma 3 27B+28 altsGoogle48.035$0.08/M$0.16/M$0.002
147Mistral Small 3.2Mistral47.977$0.07/M$0.20/M$0.003
148Qwen3 VL 8B Instruct+1 altAlibaba47.341$0.18/M$0.70/M$0.009
149InternVL2.5-78BOpenGVLab47.33P———
150Qwen2 VL 72B Instruct+1 altAlibaba46.2VENDOR———
151Ministral 3 8BMistral45.954$0.15/M$0.15/M$0.003
152Claude 3.5 HaikuAnthropic45.607———
153Devstral Small 2Mistral44.624———
154Gemma 4 E2B+41 altsGoogle44.567———
155Nova ProAmazon44.335$0.80/M$3.2/M$0.045
156Qwen3 VL 4B Instruct+1 altAlibaba43.873———
157Kimi VL A3B Thinking+1 altMoonshot43.23P———
158Qwen3.5 2B+2 altsAlibaba43.006———
159GPT-4o miniOpenAI41.503$0.15/M$0.60/M$0.009
160GPT-4.1 nanoOpenAI40.116$0.10/M$0.40/M$0.006
161Llama 3.2 Instruct 90B (Vision)+1 altMeta39.48———
162Ministral 3 3BMistral38.093$0.10/M$0.10/M$0.003
163MiniCPM-V 4.6 1.3BOpenBMB37.919———
164Nova LiteAmazon37.804$0.06/M$0.24/M$0.004
165Gemma 3 12B+1 altGoogle37.515$0.05/M$0.15/M$0.003
166Molmo2-8BAllenAI37.457———
167Qwen2.5 Omni 7BAlibaba36.6VENDOR$0.10/M$6.8/M$0.094
168Gemini 1.5 Flash 8BGoogle36.532———
169Kimi VL A3B InstructMoonshot363P———
170Claude 3 HaikuAnthropic30.809$0.25/M$1.3/M$0.024
171LFM2.5-VL-3B+2 altsLiquid AI30.5VENDOR———
172Gemma 3 4BGoogle29.942$0.05/M$0.10/M$0.003
173Llama 3.2 Instruct 11B (Vision)Meta29.306$0.34/M$0.34/M$0.012
174LFM2-VL-3B+1 altLiquid AI28.7VENDOR———
175LFM2.5-VL-1.6BLiquid AI26.532———
176Gemma 3n E4B InstructGoogle26.243———
177Qwen3.5 0.8B+1 altAlibaba25.838———
178Molmo 7B-DAllenAI24.509———
179InternVL3_5-4BOpenGVLab22.7VENDOR———
180InternVL3_5-2BOpenGVLab21.3VENDOR———
181Phi 4 Multimodal Instruct+1 altMicrosoft14.509———
182LFM2.5-VL-3B-DSparkLiquid AI4.193P———
◆ 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: 182 models scored · 0 independently verified · 162 aggregator-attributed · 4 vendor cross-reference · 16 vendor-reported · 3 with source disagreement. How these tiers are assigned