DeepSeek V4 Pro vs Kimi K3 benchmark

Interactive Comparison Diagram

Recommended Workload Routing

Frequently Asked Questions

Which is better overall, DeepSeek V4 Pro or Kimi K3?

DeepSeek V4 Pro has the higher preference Elo in our latest snapshot (1,536). “Better” still depends on coding, price, and latency — see the table.

Which is better at coding, DeepSeek V4 Pro or Kimi K3?

Kimi K3 leads SWE-bench at 73.8% vs 71.6%. SWE-bench is one harness, not your repo.

Which is cheaper to run in production?

DeepSeek V4 Pro output tokens are $0.87/1M versus $15/1M. Input prices and retry rates still move the real bill.

Which is faster, DeepSeek V4 Pro or Kimi K3?

Kimi K3 has the lower time-to-first-token (290 ms vs 410 ms). Tokens/sec is a separate column if you care about long completions.

Which has the larger context window?

DeepSeek V4 Pro accepts 1M tokens versus 1M.

Can I self-host either model?

DeepSeek V4 Pro is marked open-weights in our catalog. The other side is a closed API. Check the provider license before you ship weights.

Are these scores from CompareLLM’s own evals?

No. V1 aggregates public leaderboards (and optional first-party latency pings). Each cell names its source and date. Read /methodology.

What does preference Elo mean on this page?

Preference Elo is a crowd vote from LMArena / Arena. People see two hidden answers and pick the one they like more. The model that wins more often gets a higher Elo. That means people preferred it — not that it passed a school test. It is not SWE-bench, not accuracy, and not a number we invent. DeepSeek V4 Pro and Kimi K3 Elo cells are dated snapshots from the named source — we do not compute Arena ourselves.