Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d262Policy30d64, 11 pendingSources1,015
Pro Mode — raw scores, one benchmark under the lensofficial card harness
The field · 90 measured
1.5189.9

90 models measured, most on the official card harness. Claude Opus 5.5 tops the board at 89.9.

90 measured·1 new this week·Lifecycle Updated Oct 9, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 1.51–89.9 · ◆ solid = first-party or better · outlined = arm's-length
01Claude Opus 5.5+2 altsAnthropic89.9$4.0/M$20.0/M$0.133
02Sonnet 5.5+2 altsAnthropic81.3$2.0/M$10.0/M$0.074
03Claude Mythos 5.1Anthropic81.2$10.0/M$50.0/M$0.369
04Claude Fable 5.1+1 altAnthropic81.2$10.0/M$50.0/M$0.369
05Claude Fable 5+5 altsAnthropic80$10.0/M$50.0/M$0.375
06Claude Mythos 5+1 altAnthropic80$10.0/M$50.0/M$0.375
07Claude Opus 5+2 altsAnthropic79.2$5.0/M$25.0/M$0.189
08Claude Mythos Preview+1 altAnthropic77.8———
09Claude Opus 4.8+8 altsAnthropic69.2$5.0/M$25.0/M$0.217
10Qwen3.8 Max Preview+1 altAlibaba67.7$3.3/M$9.9/M$0.098
11Hy4Tencent65.7$0.83/M$2.5/M$0.025
12Haiku 5.5NEW+1 altAnthropic64.8$0.10/M$0.50/M$0.005
13Grok4.5+1 altSpaceXAI64.7$2.0/M$6.0/M$0.062
14GPT-5.6 Sol+3 altsOpenAI64.6$4.0/M$20.0/M$0.186
15Claude Opus 4.7+5 altsAnthropic64.3$5.0/M$25.0/M$0.233
16GPT-5.6 TerraOpenAI63.4$2.0/M$12.0/M$0.110
17Claude Sonnet 5+2 altsAnthropic63.2$2.0/M$10.0/M$0.095
18GPT-5.6 Luna+1 altOpenAI62.7$0.20/M$1.2/M$0.011
19Qwen3.8 Flash Next+1 altAlibaba62.5$0.15/M$0.47/M$0.005
20GLM-5.2+3 altsZ.ai62.1$1.4/M$4.4/M$0.047
21Qwen3.8 27B+2 altsAlibaba61.7$0.50/M$3.0/M$0.028
22Muse Spark 1.1+2 altsMeta61.5$1.3/M$4.3/M$0.045
23Qwen3.7 Max+3 altsAlibaba60.6$2.5/M$7.5/M$0.083
24Atria Dawnshanghai-ai-lab59.6———
25Laguna S 2.1poolside59.4$0.09/M$0.18/M$0.002
26MiniMax M3+2 altsMiniMax59$0.28/M$1.1/M$0.012
27MiMo V2.5 Pro FP4 DFlashXiaomi58.83P———
28Gemini 3.6 Flash+2 altsGoogle58.7$0.75/M$3.8/M$0.038
29Kimi K2.6+7 altsMoonshot58.6$0.95/M$4.0/M$0.042
30GPT-5.5+7 altsOpenAI58.6$5.0/M$30.0/M$0.299
31GLM-5.1+8 altsZ.ai58.4$1.4/M$4.4/M$0.049
32Claude Sonnet 4.6+2 altsAnthropic58.1$3.0/M$15.0/M$0.155
33Hy3-previewTencent57.9$0.14/M$0.56/M$0.006
34GPT-5.4+12 altsOpenAI57.7$2.5/M$15.0/M$0.152
35Qwen3.7 Plus Preview+2 altsAlibaba57.6$0.40/M$1.6/M$0.017
36Seed 2.1 Pro PreviewByteDance57.5———
37MiMo V2.5 Pro+1 altXiaomi57.2$0.43/M$0.87/M$0.011
38GPT-5.3 Codex+1 altOpenAI56.8$1.8/M$14.0/M$0.139
39Ling-3.0-flashInclusionAI56.6$0.07/M$0.22/M$0.003
40Qwen3.6 Plus+3 altsAlibaba56.6$0.50/M$3.0/M$0.031
41GPT-5.2 Codex+2 altsOpenAI56.4$1.8/M$14.0/M$0.140
42Step 3.7 FlashStepFun56.3$0.20/M$1.1/M$0.012
43MiniMax M2.7+3 altsMiniMax56.2$0.21/M$0.84/M$0.009
44MiMo V2.5Xiaomi56.1$0.14/M$0.28/M$0.004
45Inkling-SmallThinking Machines55.9$0.30/M$1.2/M$0.013
46MiniMax M2.5MiniMax55.4$0.27/M$1.1/M$0.012
47DeepSeek-V4-Pro+9 altsDeepSeek55.4$0.43/M$0.87/M$0.012
48Gemini 3.5 Flash+5 altsGoogle55.1$1.5/M$9.0/M$0.095
49GLM-5+2 altsZ.ai55.1$1.0/M$3.2/M$0.038
50GPT-5.4 miniOpenAI54.4$0.75/M$4.5/M$0.048
51Gemini 3.1 Pro+19 altsGoogle54.2$2.0/M$12.0/M$0.129
52Gemini 3.5 Flash Lite+4 altsGoogle54.2$0.30/M$2.5/M$0.026
53Qwen3.6 27B+2 altsAlibaba53.5$0.60/M$3.6/M$0.039
54Claude Opus 4.6+12 altsAnthropic53.4$5.0/M$25.0/M$0.281
55MAI-Thinking-1Microsoft52.8———
56DeepSeek-V4-Flash+1 altDeepSeek52.6$0.44/M$1.3/M$0.017
57Muse Spark+2 altsMeta52.4———
58GPT-5.4 nanoOpenAI52.4$0.20/M$1.3/M$0.014
59Claude Opus 4.5+4 altsAnthropic52$5.0/M$25.0/M$0.288
60Muse Glimmer+1 altMeta51.2$0.33/M$1.4/M$0.016
61MAI-Code-1-FlashMicrosoft51.2———
62Qwen3.5 27B+1 altAlibaba51.2$0.30/M$2.4/M$0.026
63Qwen3.5 397B A17BAlibaba50.93P$0.60/M$3.6/M$0.041
64Kimi K2.5+5 altsMoonshot50.7$0.45/M$2.3/M$0.027
65Gemini 3 Flash Preview+5 altsGoogle49.6$0.50/M$3.0/M$0.035
66Qwen3.6 35B A3B+2 altsAlibaba49.5$0.38/M$2.3/M$0.027
67Laguna-XS-2.1poolside47.6$0.06/M$0.12/M$0.002
68Qwen3.5 35B A3BAlibaba44.6$0.25/M$2.0/M$0.025
69Claude Sonnet 4.5+1 altAnthropic43.63P$3.0/M$15.0/M$0.206
70Gemini 3 Pro+2 altsGoogle43.3$2.0/M$12.0/M$0.162
71Claude Sonnet 4+1 altAnthropic42.73P$3.0/M$15.0/M$0.211
72GPT-5OpenAI41.783P$1.3/M$10.0/M$0.135
73North-Mini-Code-1.0Cohere40.2———
74Claude Haiku 4.5+1 altAnthropic39.453P$1.0/M$5.0/M$0.076
75Qwen3 Coder 480B A35B Instruct+1 altAlibaba38.73P$1.5/M$7.5/M$0.116
76MiniMax M2.1+1 altMiniMax36.813P$0.30/M$1.2/M$0.020
77Gemma 4 31B+1 altGoogle35.7$0.17/M$0.40/M$0.008
78Granite 4.2 30B+1 altIBM33.29$0.16/M$0.65/M$0.012
79GPT-5.2+2 altsOpenAI29.943P$1.8/M$14.0/M$0.263
80Kimi K2 Instruct+1 altMoonshot27.673P$0.57/M$2.3/M$0.052
81Qwen3 235B A22B+1 altAlibaba21.413P$0.70/M$2.8/M$0.082
82Granite 4.2 8B+2 altsIBM19.11$0.06/M$0.25/M$0.008
83GPT Oss 120b+1 altOpenAI16.23P$0.15/M$0.59/M$0.023
84DeepSeek-V3.2+1 altDeepSeek15.563P$0.28/M$0.42/M$0.022
85Gemma 4 26B A4BGoogle13.8$0.07/M$0.34/M$0.015
86Gemma 3 27B+1 altGoogle11.383P$0.08/M$0.16/M$0.011
87Llama 3.1 Instruct 405B+1 altMeta11.183P———
88GLM-4.6+1 altZ.ai9.673P$0.57/M$2.2/M$0.143
89Llama 4 Maverick+1 altMeta5.243P$0.25/M$0.87/M$0.107
90Codestral 2405+1 altMistral1.513P$0.30/M$0.90/M$0.397
◆ 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: 90 models scored · 16 independently verified · 2 vendor cross-reference · 72 vendor-reported · 0 with source disagreement. How these tiers are assigned