Which model leads Toolathlon Verified?

Claude Opus 5 leads the Toolathlon Verified board of 27 measured models on the Vector Wire tracker at 80.6. Every score is source-attributed with a verification tier.

Toolathlon Verified Leaderboard — Model Scores

Refresh Models —Deals —Regulatory —Sources —

Pro Mode — raw scores, one benchmark under the lensofficial card harness

The field · 27 measured

40.780.6

27 models measured, most on the official card harness. Claude Opus 5 tops the board at 80.6.

27 measured·9 new this week·Lifecycle Updated Sep 2, 2026Basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 27Bars show 40.7–80.6· ◆ solid = first-party or better · outlined = arm's-length

01Claude Opus 5+1 altAnthropic80.6$5.0/M$25.0/M$0.186

02Claude Opus 4.8+8 altsAnthropic79.9$5.0/M$25.0/M$0.188

03Claude Mythos 5+1 altAnthropic79.3———

04Fable 5+1 altAnthropic77.93P$10.0/M$50.0/M$0.385

05Claude Fable 5.1NEWAnthropic77.8$10.0/M$50.0/M$0.386

06Kimi K3+3 altsMoonshot76.53P$2.9/M$14.3/M$0.112

07DeepSeek-V4-Flash-Vision-ExpNEWDeepSeek75.9$0.44/M$1.3/M$0.012

08Muse Spark 1.1Meta75.6$1.3/M$4.3/M$0.036

09GPT-5.6 SolNEW+3 altsOpenAI74.93P$4.0/M$20.0/M$0.160

10Claude Sonnet 5+1 altAnthropic74.7$2.0/M$10.0/M$0.080

11GPT-5.5OpenAI73.53P$5.0/M$30.0/M$0.238

12Qwen3.8-Flash-NextNEWAlibaba73.5$0.15/M$0.47/M$0.004

13GLM-5.3NEW+1 altZ.ai733P$1.4/M$4.4/M$0.040

14Qwen3.8-Max+2 altsAlibaba72.53P$2.0/M$6.0/M$0.055

15DeepSeek-V4-Flash-0731NEW+8 altsDeepSeek70.3$0.44/M$1.3/M$0.013

16GPT 5.6 Luna+1 altOpenAI67.9$0.20/M$1.2/M$0.010

17Qwen3.8-27BNEWAlibaba67.1$0.50/M$3.0/M$0.026

18GLM-5.2NEW+4 altsZ.ai59.93P$1.4/M$4.4/M$0.048

19Gemini 3.5 Flash-Lite+1 altGoogle57.1$0.30/M$2.5/M$0.025

20DeepSeek-V4-Pro (Preview)+1 altDeepSeek55.9$1.3/M$4.0/M$0.047

21Inkling-Small+1 altThinking Machines54.4$0.30/M$1.2/M$0.014

22Qwen3.7-PlusNEWAlibaba50.6$0.40/M$1.6/M$0.020

23Qwen3.7-MaxAlibaba49.73P$2.5/M$7.5/M$0.101

24MiMo V2.5+1 altXiaomi49.1$0.43/M$0.87/M$0.013

25Minimax M2.7+1 altMiniMax47.5$0.25/M$1.0/M$0.013

26Inkling+1 altThinking Machines45.5$0.95/M$4.0/M$0.055

27Qwen3.5 397B-A17B+1 altAlibaba40.7$0.60/M$3.6/M$0.052

◆ 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.