DeepSeek-V4-ProvsKimi K2.6
Across 9 shared benchmarks, Kimi K2.6 leads overall: DeepSeek-V4-Pro wins 1, Kimi K2.6 wins 8, with 0 ties and an average score difference of -19.42.
DeepSeek-V4-Pro
DeepSeek-AI · 2026-04-24 · Reasoning model
Kimi K2.6
Moonshot AI · 2026-04-20 · Reasoning model
DeepSeek-V4-Pro1 win(11%)(89%)8 winsKimi K2.6
Benchmark scores
Grouped by capability, sorted by largest gap within each. 9 shared benchmarks.
Coding and Software Engineer
Kimi K2.6 4/4| Benchmark | DeepSeek-V4-Pro | Kimi K2.6 | Diff |
|---|---|---|---|
| LiveCodeBench | 56.8073 / 118Normal (No Tools) | 89.606 / 118Thinking (No Tools) | -32.80 |
| SWE-bench Multilingual | 69.8012 / 17Normal (With Tools) | 76.702 / 17Thinking (With Tools) | -6.90 |
| SWE-bench Verified | 73.6036 / 103Normal (With Tools) |
Specs
| Field | DeepSeek-V4-Pro | Kimi K2.6 |
|---|---|---|
| Publisher | DeepSeek-AI | Moonshot AI |
| Release date | 2026-04-24 | 2026-04-20 |
| Model type | Reasoning model | Reasoning model |
| Architecture | MoE | MoE |
| Parameters | 16000.0 | 10000.0 |
| Context length | 1M | 256K |
| Max output | 384000 | Not available |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | DeepSeek-V4-Pro | Kimi K2.6 |
|---|---|---|
| Text input | $1.74 / 1M tokens | $0.95 / 1M tokens |
| Text output | $3.48 / 1M tokens | $4 / 1M tokens |
| Cache read | $0.145 / 1M tokens | $0.16 / 1M tokens |
| Cache write | $1.74 / 1M tokens | $0.95 / 1M tokens |
Summary
- DeepSeek-V4-Proleads in:AI Agent - Information Search (1/1)
- Kimi K2.6leads in:Coding and Software Engineer (4/4), General Knowledge (2/2), AI Agent - Tool Usage (1/1), Math and Reasoning (1/1)
On average across the 9 shared benchmarks, Kimi K2.6 scores 19.42 higher.
Largest single-benchmark gap: IMO-AnswerBench — DeepSeek-V4-Pro 35.30 vs Kimi K2.6 86 (-50.70).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.