Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d267Policy30d65, 14 pendingSources1,013
Pro Mode — raw scores, one benchmark under the lensofficial card harness
The field · 60 measured
5.0386.1

60 models measured, most on the official card harness. Qwen3.8 Max Preview tops the board at 86.1.

60 measured·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 5.03–86.1 · ◆ solid = first-party or better · outlined = arm's-length
01Qwen3.8 Max PreviewAlibaba86.1$3.3/M$9.9/M$0.077
02Claude Mythos 5Anthropic85$10.0/M$50.0/M$0.353
03Claude Fable 5+5 altsAnthropic85$10.0/M$50.0/M$0.353
04Kimi K3Moonshot84.83P$0.58/M$12.3/M$0.076
05Qwen3.8 27BAlibaba84.3$0.50/M$3.0/M$0.021
06Claude Opus 5+1 altAnthropic83.43P$5.0/M$25.0/M$0.180
07Claude Opus 4.8+3 altsAnthropic83.4$5.0/M$25.0/M$0.180
08Gemini 3.6 Flash+5 altsGoogle83$0.75/M$3.8/M$0.027
09GPT-5.6 Sol+1 altOpenAI833P$4.0/M$20.0/M$0.145
10MiMo V2.6 Pro+2 altsXiaomi82$0.43/M$0.87/M$0.008
11Claude Sonnet 5+2 altsAnthropic81.2$2.0/M$10.0/M$0.074
12Muse Spark 1.1+1 altMeta80.8$1.3/M$4.3/M$0.034
13MiMo V2.6 Flash RL+2 altsXiaomi80.8$0.14/M$0.28/M$0.003
14Claude Mythos Preview+1 altAnthropic79.6———
15Seed 2.1 Pro PreviewByteDance78.8———
16GPT-5.5+4 altsOpenAI78.7$5.0/M$30.0/M$0.222
17Gemini 3.5 Flash+9 altsGoogle78.4$1.5/M$9.0/M$0.067
18Claude Opus 4.7+6 altsAnthropic78$5.0/M$25.0/M$0.192
19Gemini 3.1 Pro+3 altsGoogle76.2$2.0/M$12.0/M$0.092
20GPT-5.4+3 altsOpenAI75$2.5/M$15.0/M$0.117
21Gemini 3.5 Flash Lite+4 altsGoogle74$0.30/M$2.5/M$0.019
22Qwen3.7 Plus PreviewAlibaba73.3$0.40/M$1.6/M$0.014
23Kimi K2.6+1 altMoonshot73.1$0.95/M$4.0/M$0.034
24Claude Opus 4.6+3 altsAnthropic72.7$5.0/M$25.0/M$0.206
25GPT-5.6 LunaOpenAI72.6$0.20/M$1.2/M$0.010
26Claude Sonnet 4.6+3 altsAnthropic72.5$3.0/M$15.0/M$0.124
27GPT-5.4 miniOpenAI72.1$0.75/M$4.5/M$0.036
28MiniMax M3MiniMax70.06$0.28/M$1.1/M$0.010
29Qwen3 VL 235B A22B InstructAlibaba66.7$0.40/M$1.6/M$0.015
30Claude Opus 4.5+2 altsAnthropic66.3$5.0/M$25.0/M$0.226
31Muse GlimmerMeta65.9$0.33/M$1.4/M$0.013
32Gemini 3 Flash Preview+3 altsGoogle65.1$0.50/M$3.0/M$0.027
33GPT-5.3 CodexOpenAI64.7$1.8/M$14.0/M$0.122
34Kimi K2.5Moonshot63.33P$0.45/M$2.3/M$0.021
35Qwen3.6 PlusAlibaba62.5$0.50/M$3.0/M$0.028
36GLM 5V TurboZ.ai62.3$1.2/M$4.0/M$0.042
37Seed 1.8ByteDance61.9$0.25/M$2.0/M$0.018
38Claude Sonnet 4.5+2 altsAnthropic61.4$3.0/M$15.0/M$0.147
39Qwen3.5 122B A10BAlibaba58$0.40/M$3.2/M$0.031
40Qwen3.5 27BAlibaba56.2$0.30/M$2.4/M$0.024
41Qwen3.5 35B A3BAlibaba54.5$0.25/M$2.0/M$0.021
42Claude Haiku 4.5Anthropic50.7$1.0/M$5.0/M$0.059
43Nemotron 3 Nano OmniNVIDIA47.43P$0.30/M$0.90/M$0.013
44Claude Opus 4.1Anthropic44.4$15.0/M$75.0/M$1.014
45Claude Sonnet 4Anthropic42.2$3.0/M$15.0/M$0.213
46Qwen3 VL 32B ReasoningAlibaba41$0.16/M$0.64/M$0.010
47GPT-5.4 nanoOpenAI39$0.20/M$1.3/M$0.019
48Qwen3 VL 235B A22B ReasoningAlibaba38.1$0.40/M$4.0/M$0.058
49Qwen3 VL 8B InstructAlibaba33.9$0.18/M$0.70/M$0.013
50Qwen3 VL Thinking (8B)Alibaba33.9$0.18/M$2.1/M$0.034
51Qwen3 VL 32B InstructAlibaba32.6$0.16/M$0.64/M$0.012
52Qwen3 VL 4B (Reasoning)Alibaba31.4———
53Qwen3 VL 30B A3B ReasoningAlibaba30.6$0.20/M$2.4/M$0.042
54Qwen3 VL 30B A3B InstructAlibaba30.3$0.20/M$0.80/M$0.017
55Qwen3 VL 4B InstructAlibaba26.2———
56NVIDIA Nemotron Nano 12B v2 VLNVIDIA11.13P$0.20/M$0.60/M$0.036
57Qwen2.5 VL 72BAlibaba8.83———
58Kimi VL A3B InstructMoonshot8.22———
59Qwen2.5 VL 32B Instruct+1 altAlibaba5.92———
60GPT-4oOpenAI5.033P$5.0/M$15.0/M$1.988
◆ 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: 60 models scored · 0 independently verified · 4 vendor cross-reference · 56 vendor-reported · 2 with source disagreement. How these tiers are assigned