ixio
← Leaderboard
model profile
Excellentopen

DeepSeek-V4-Pro

DeepSeek·deepseek-v4-pro
Rank · overall#56
Score66.4

Benchmark scores

6 benchmarks
SWE-bench Verified96.4%
% Resolved · 2026-08-13
Chatbot Arena (Coding)1550Coding Elo
WebDev Arena1446WebDev Elo · ± 7
FrontierMath (Tier 4)2.4%
Accuracy · ± 2.4
SkillsBench50.1Score
MathArena Apex28.1%
Accuracy

Across harnesses

0 agents

This model appears only in model-level benchmarks — no harness ran it directly.

Scraped and aggregated from public leaderboards · 2026-08-16