Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d271Policy30d67, 15 pendingSources1,015
Pro Mode — raw scores, one benchmark under the lensofficial card harness
The field · 56 measured
5.265

56 models measured, most on the official card harness. Claude Mythos 5.1 tops the board at 65.

56 measured·5 new this week·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 5.2–65 · ◆ solid = first-party or better · outlined = arm's-length
01Claude Mythos 5.1Anthropic65$10.0/M$50.0/M$0.462
02Claude Fable 5.1+2 altsAnthropic65$10.0/M$50.0/M$0.462
03Claude Mythos PreviewAnthropic64.7———
04GPT-5.6 Sol+3 altsOpenAI64.53P$4.0/M$20.0/M$0.186
05Sonnet 5.5Anthropic64.5$2.0/M$10.0/M$0.093
06DeepSeek-V4.1-FlashDeepSeek63.9$0.20/M$0.60/M$0.006
07Claude Mythos 5+1 altAnthropic63.8$10.0/M$50.0/M$0.470
08Claude Fable 5+5 altsAnthropic63.8$10.0/M$50.0/M$0.470
09Claude Opus 5+3 altsAnthropic63.6$5.0/M$25.0/M$0.236
10GLM-5.3+2 altsZ.ai62.53P$1.4/M$4.4/M$0.046
11DeepSeek-V4-Pro+9 altsDeepSeek60$0.43/M$0.87/M$0.011
12Kimi K3+1 altMoonshot59.83P$0.58/M$12.3/M$0.108
13GPT-5.4 Pro+1 altOpenAI58.7$30.0/M$180.0/M$1.789
14Claude Opus 4.8+9 altsAnthropic57.9$5.0/M$25.0/M$0.259
15Claude Sonnet 5Anthropic57.4$2.0/M$10.0/M$0.105
16Haiku 5.5NEWAnthropic57.4$0.10/M$0.50/M$0.005
17Qwen3.8 Max Preview+2 altsAlibaba56.23P$3.3/M$9.9/M$0.117
18Claude Opus 4.7+2 altsAnthropic54.7$5.0/M$25.0/M$0.274
19GLM-5.2+5 altsZ.ai54.7$1.4/M$4.4/M$0.053
20Kimi K2.6+5 altsMoonshot543P$0.95/M$4.0/M$0.046
21Qwen3.7 Max+2 altsAlibaba53.53P$2.5/M$7.5/M$0.093
22Claude Opus 4.6+11 altsAnthropic53.3$5.0/M$25.0/M$0.281
23GLM-5.1+6 altsZ.ai52.3$1.4/M$4.4/M$0.055
24GPT-5.5+6 altsOpenAI52.2$5.0/M$30.0/M$0.335
25GPT-5.4NEW+8 altsOpenAI52.1$2.5/M$15.0/M$0.168
26Gemini 3.1 ProNEW+16 altsGoogle51.4$2.0/M$12.0/M$0.136
27Qwen3.6 PlusNEW+2 altsAlibaba50.6$0.50/M$3.0/M$0.035
28GLM-5+2 altsZ.ai50.4$1.0/M$3.2/M$0.042
29Kimi K2.5+5 altsMoonshot50.23P$0.45/M$2.3/M$0.027
30GPT-5.6 Luna+1 altOpenAI48.9$0.20/M$1.2/M$0.014
31Qwen3.5 397B A17B+2 altsAlibaba48.3$0.60/M$3.6/M$0.043
32Inkling-Small+1 altThinking Machines47.8$0.30/M$1.2/M$0.016
33Claude Sonnet 4.6+1 altAnthropic46.8$3.0/M$15.0/M$0.192
34Inkling+2 altsThinking Machines46.6$0.95/M$4.0/M$0.054
35Gemini 3 Pro+1 altGoogle45.83P$2.0/M$12.0/M$0.153
36GPT-5.2OpenAI45.53P$1.8/M$14.0/M$0.173
37DeepSeek-V4-Flash+3 altsDeepSeek45.1$0.44/M$1.3/M$0.020
38Kimi K2 ThinkingMoonshot44.93P$0.60/M$2.5/M$0.035
39Claude Opus 4.5Anthropic43.23P$5.0/M$25.0/M$0.347
40GLM-4.7Z.ai42.83P$0.60/M$2.2/M$0.033
41GPT-5.1OpenAI42.73P$1.3/M$10.0/M$0.132
42Gemini 3.5 Flash Lite+1 altGoogle42.5$0.30/M$2.5/M$0.033
43DeepSeek-V3.2NEW+5 altsDeepSeek40.8$0.28/M$0.42/M$0.009
44MiniMax M2.7+1 altMiniMax40.3$0.21/M$0.84/M$0.013
45MiMo V2.5+1 altXiaomi40$0.14/M$0.28/M$0.005
46Nemotron 3 Ultra 550B A55B+3 altsNVIDIA37.43P$0.60/M$2.5/M$0.041
47GPT-5+1 altOpenAI35.23P$1.3/M$10.0/M$0.160
48Claude Sonnet 4.5+1 altAnthropic323P$3.0/M$15.0/M$0.281
49MiniMax M2MiniMax31.83P$0.30/M$1.2/M$0.024
50GLM-4.6+1 altZ.ai30.43P$0.57/M$2.2/M$0.046
51Gemini 2.5 ProGoogle28.43P$1.3/M$10.0/M$0.198
52Kimi K2 InstructMoonshot26.93P$0.57/M$2.3/M$0.053
53Gemma 4 31B+23 altsGoogle26.5$0.17/M$0.40/M$0.011
54Claude Sonnet 4Anthropic20.33P$3.0/M$15.0/M$0.443
55Gemma 4 26B A4B+23 altsGoogle17.2$0.07/M$0.34/M$0.012
56Gemma 4 12BGoogle5.2$0.10/M$0.30/M$0.038
◆ 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: 56 models scored · 0 independently verified · 23 vendor cross-reference · 33 vendor-reported · 2 with source disagreement. How these tiers are assigned