Which model leads LiveCodeBench (v5)?

Q: Which model leads LiveCodeBench (v5)?

Gemini 2.5 Pro tops the board at 75.6

LiveCodeBench (v5) Leaderboard — Model Scores

Pro Mode — raw scores, one benchmark under the lensthird-party eval harness

The field · 9 measured

9.675.6

9 models measured, most on the third-party eval harness. Gemini 2.5 Pro tops the board at 75.6.

9 measured·Lifecycle Updated Oct 8, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 9Bars show 9.6–75.6 · ◆ solid = first-party or better · outlined = arm's-length

01Gemini 2.5 ProGoogle75.6VENDOR$1.3/M$10.0/M$0.074

02Gemini 2.5 FlashGoogle63.9VENDOR$0.30/M$2.5/M$0.022

03Qwen3 VL 235B A22B InstructAlibaba61.4VENDOR$0.40/M$1.6/M$0.016

04Seed Coder 8B InstructByteDance24.7———

05Qwen3 8BAlibaba23.5$0.18/M$0.70/M$0.019

06Yi Coder 9B Chat01.AI17.5———

07Qwen2.5 Coder Instruct 7BAlibaba17.3$0.01/M$0.03/M$0.001

08Llama 3.1 8B InstructMeta11.5$0.02/M$0.04/M$0.003

09DeepSeek-Coder-6.7B-InstructDeepSeek9.6———

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