Skip to content
VECTOR WIREAI INTELLIGENCE
UTC
Pro Mode — raw scores, one benchmark under the lensthird-party eval harness
The field · 7 measured
37.151.7

7 models measured, most on the third-party eval harness. Qwen3 8B tops the board at 51.7.

7 measured·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 37.1–51.7 · ◆ solid = first-party or better · outlined = arm's-length
01Qwen3 8BAlibaba51.7$0.18/M$0.70/M$0.009
02Qwen 2.5 Coder 32B InstructAlibaba49.6VENDOR$0.06/M$0.20/M$0.003
03Yi Coder 9B Chat01.AI49———
04Qwen2.5 Coder Instruct 7BAlibaba48.8$0.01/M$0.03/M$0.000
05DeepSeek-Coder-6.7B-InstructDeepSeek43.8———
06Llama 3.1 8B InstructMeta40.5$0.02/M$0.04/M$0.001
07Seed Coder 8B InstructByteDance37.1———
◆ 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: 7 models scored · 0 independently verified · 5 vendor cross-reference · 2 vendor-reported · 0 with source disagreement. How these tiers are assigned