Which model leads HumanEval-V?

Q: Which model leads HumanEval-V?

Step3 VL 10B tops the board at 66.05

HumanEval-V Leaderboard — 5 Models Ranked

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

The field · 5 measured

24.3166.05

5 models measured, most on the official card harness. Step3 VL 10B tops the board at 66.05.

5 measured·Lifecycle Updated Oct 8, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 5Bars show 24.31–66.05 · ◆ solid = first-party or better · outlined = arm's-length

01Step3 VL 10B+1 altStepFun66.05———

02MiMo VL RL 2508 (7B)+1 altXiaomi31.96———

03GLM-4.6V-Flash (9B)+1 altZ.ai29.26$0.30/M$0.90/M$0.021

04Qwen3 VL Thinking (8B)+1 altAlibaba26.94$0.18/M$2.1/M$0.042

05InternVL-3.5 (8B)+1 altOpenGVLab24.31———

◆ 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: 5 models scored · 0 independently verified · 4 vendor cross-reference · 1 vendor-reported · 0 with source disagreement. How these tiers are assigned