Data points: 79
The readout for DeepSeek R1 and Kimi K2.5, before the detailed comparison sheet.
Decision read
Kimi K2.5
Kimi K2.5 currently has the stronger profile, with verified wins split 2 to 4.
Evidence depth
79 data points
Includes 6 benchmark rows, 0 audit samples, and 8 provider examples.
Selection signal
Start with Kimi K2.5
The charts below split 14 high-signal samples across speed, scores, and audit health.
Model compare DeepSeek R1 vs Kimi K2.5deepseek-r1-vs-kimi-k2-5 | Model A DeepSeek R1 | Model B Kimi K2.5 |
|---|---|---|
| Overall leader | Contender | Leading |
| Verified metric wins | 2 wins | 4 wins |
| Where it leads | First-token latency, Recent tests | Cheapest input price, Average speed, Free providers, Provider coverage |
| Model metadata | DeepSeek R1 exposes 163.8K tokens; notable signals: Text input, Text output, Tool calling, Structured outputs. | Kimi K2.5 exposes 262.1K tokens; notable signals: Text input, Image input, Text output, Tool calling. |
| Developer | DeepSeek | Moonshot AI |
| Context window | 163.8K tokens | 262.1K tokens |
| Max output | 32.8K tokens | 262.1K tokens |
| Released | May 2025 | Jan 2026 |
| Modalities | Input Text Output Text | Input TextImage Output Text |
| Features | Text inputText outputTool callingStructured outputsJSON modeReasoning | Text inputImage inputText outputTool callingStructured outputsJSON modeReasoning |
| Parameters | No data | No data |
| Tokenizer | DeepSeek | Other |
| Knowledge cutoff | 2025-03-31 | No data |
| OpenRouter ID | deepseek/deepseek-r1-0528 | moonshotai/kimi-k2.5 |
| References | No data | No data |
Third-party benchmark profile synced into LMSpeed; only metrics available for both models are shown.
| Metric | DeepSeek R1 | Kimi K2.5 |
|---|---|---|
| HLE | 14.9%#52 | 29.4%#14 |
| SciCode | 40.3%#45 | 49.0%#14 |
| GPQA | 81.3%#51 | 87.9%#16 |
| Input price | $1.35/M#31 | $0.580/M#21 |
| Output price | $4.20/M#32 | $3.00/M#28 |
| Blended price | $2.06/M#52 | $1.19/M#43 |
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | DeepSeek R1 | Kimi K2.5 |
|---|---|---|
| No completed audits are available from shared providers yet. | ||
Speed aggregates and input/output pricing share each provider row for real API selection and migration cost checks.
| Provider | DeepSeek R1 | Kimi K2.5 |
|---|---|---|
阿里云百炼 DashScope150 tests | DeepSeek R1 speed / latency 25 tok/s / 38312ms input / output No data | Kimi K2.5 speed / latency 45 tok/s / 2058ms input / output No data |
Tencent60 tests | DeepSeek R1 speed / latency 13 tok/s / 54820ms input / output No data | Kimi K2.5 speed / latency 41 tok/s / 14388ms input / output No data |
Gitee AI50 tests | DeepSeek R1 speed / latency 32 tok/s / 21696ms input / output No data | Kimi K2.5 speed / latency N/A / N/A input / output No data |
火山引擎 Ark50 tests | DeepSeek R1 speed / latency 29 tok/s / 27766ms input / output No data | Kimi K2.5 speed / latency 18 tok/s / 25450ms input / output No data |
NVIDIA NIM35 tests | DeepSeek R1 speed / latency 88 tok/s / 8956ms input / output No data | Kimi K2.5 speed / latency 48 tok/s / 18528ms input / output No data |
DeepSeek R1 deepseek-ai/deepseek-r1-0528 speed / latency No data input / output $0/M / $0/M | Kimi K2.5 moonshotai/kimi-k2.5 speed / latency No data input / output $0.300/M / $1.90/M | |
DeepSeek R1 deepseek-r1-0528 speed / latency No data input / output $0.010/M / $0.010/M | Kimi K2.5 moonshotai/kimi-k2.5 speed / latency No data input / output $0.010/M / $0.010/M | |
DeepSeek R1 deepseek-r1 speed / latency No data input / output $0.010/M / $0.010/M | Kimi K2.5 kimi-k2.5 speed / latency No data input / output $0.010/M / $0.010/M |
This report only uses LMSpeed data for DeepSeek R1 and Kimi K2.5: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Guidance | DeepSeek R1 | Kimi K2.5 |
|---|---|---|
| When to choose each model | DeepSeek R1 DeepSeek R1 is stronger when you prioritize First-token latency, Recent tests. | Kimi K2.5 Kimi K2.5 is stronger when you prioritize Cheapest input price, Average speed, Free providers, Provider coverage. |
TL;DR: Kimi K2.5 leads across 79 verifiable data points, including pricing, speed, latency, benchmarks, and provider examples.
Continue from DeepSeek R1 vs Kimi K2.5 into nearby model comparisons with enough verified LMSpeed data.
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
