DeepSeek-V4.1-Flash-1017 vs Kimi K3
| Spec | DeepSeek-V4.1-Flash-1017 | Kimi K3 |
|---|---|---|
| Respan Index | 59.3 (#23) | 52.8 (#35) |
| Blended price per 1M | $0.1 | $2.52 |
| Context window | 1M | 1.0M |
| Input / output per 1M | $0.036 / $0.294 | $0.192 / $9.5 |
| Max output | - | 1.0M |
| Input | text, image | text, vision |
| Released | 2026-10-17 | 2026-07-16 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | DeepSeek-V4.1-Flash-1017 | Kimi K3 |
|---|---|---|
| Coding | 48.1 DeepSeek-V4.1-Flash-1017 | 38.8 Kimi K3 |
| Agents | 76.3 DeepSeek-V4.1-Flash-1017 | 61.8 Kimi K3 |
| Reasoning | 61.1 DeepSeek-V4.1-Flash-1017 | 54.8 Kimi K3 |
| Knowledge & language | 42.7 DeepSeek-V4.1-Flash-1017 | 52.9 Kimi K3 |
| Human preference | 57.9* DeepSeek-V4.1-Flash-1017 | 57.7 Kimi K3 |
* Estimated: no published scores in that category. How the Respan Index works
Benchmarks both report
DeepSeek-V4.1-Flash-1017 leads on 6 of the 11 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | DeepSeek-V4.1-Flash-1017 | Kimi K3 |
|---|---|---|
| APEX-Agents (Mercor) | 69.8% | 47.8% |
| Chess Puzzles (Epoch AI) | 46% | 37% |
| FrontierMath Tier 4 v2 (Epoch AI) | 46.3% | 39% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 71.2% | 72.2% |
| GPQA Diamond | 93.2% | 93.5% |
| Mystery Game Puzzles (Epoch AI) | 49% | 26% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 99.4% | 97.2% |
| SimpleQA Verified | 42.5% | 50.6% |
| Terminal-Bench 4.0 (Vals AI) | 31.8% | 17.2% |
| Humanity's Last Exam (no tools) | 42.6% | 43.5% |
| ProgramBench | 29.1% | 77.8% |
FAQ
Is DeepSeek-V4.1-Flash-1017 better than Kimi K3?
DeepSeek-V4.1-Flash-1017 scores 59.3 on the Respan Index (#23), ahead of Kimi K3 at 52.8 (#35). DeepSeek-V4.1-Flash-1017 leads on 6 of the 11 benchmarks both report.
Which is cheaper, DeepSeek-V4.1-Flash-1017 or Kimi K3?
DeepSeek-V4.1-Flash-1017 lists at $0.036 input and $0.294 output per 1M tokens; Kimi K3 at $0.192 and $9.5. DeepSeek-V4.1-Flash-1017 is 25x cheaper per token at list price.
Which has the larger context window?
DeepSeek-V4.1-Flash-1017 accepts 1M tokens and Kimi K3 1.0M tokens.