Data points: 120
Model compare
The readout for DeepSeek V4 Pro and Kimi K2.7 Code, before the detailed comparison sheet.
Weighted outcome: Kimi K2.7 Code. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Decision read
Kimi K2.7 Code
Kimi K2.7 Code has the higher weighted result; Model A / B score 28 to 72.
Evidence depth
120 data points
Includes 27 benchmark rows, 0 audit samples, and 8 provider examples.
Selection signal
Start with Kimi K2.7 Code
The charts below split 35 high-signal samples across speed, scores, and audit health.
Switch either side of this report to compare another model with the same LMSpeed data pipeline.
Select a different model to open a new comparison URL.
This report only uses LMSpeed data for DeepSeek V4 Pro and Kimi K2.7 Code: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Model compare | DeepSeek V4 Pro | Kimi K2.7 Code |
|---|---|---|
| Overall leader | Contender | Leading |
| Weighted overall score | 28.0 pts | 72.0 pts |
| Benchmark category leads | 1 categories | 4 categories |
| Operational advantages | Cheapest input price, Free providers, Provider coverage | Average speed, First-token latency |
| Context window | 1.0M tokens | 262.1K tokens |
| Max output | 384K tokens | 262.1K tokens |
| Modalities | Input Text Output Text | Input Text |
The overall result weights benchmark capability categories at 80% and price, API speed/latency, and availability at 20%. Recent test volume does not affect the winner, and missing benchmark categories are excluded.
| Model compare | DeepSeek V4 Pro | Kimi K2.7 Code |
|---|---|---|
| Developer | DeepSeek | MoonshotAI |
| Released | Apr 2026 | Jun 2026 |
| Parameters | No data | No data |
| Tokenizer | DeepSeek | Other |
| Knowledge cutoff | No data | No data |
| OpenRouter ID | deepseek/deepseek-v4-pro | moonshotai/kimi-k2.7-code |
| References | No data | No data |
This report only uses LMSpeed data for DeepSeek V4 Pro and Kimi K2.7 Code: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
DeepSeek V4 Pro
DeepSeek V4 Pro is stronger in benchmark categories (Instruction following) and operational dimensions (Cheapest input price, Free providers, Provider coverage).
Kimi K2.7 Code
Kimi K2.7 Code is stronger in benchmark categories (Agents, Coding, Reasoning, Knowledge) and operational dimensions (Average speed, First-token latency).
Third-party benchmark profile synced into LMSpeed; only metrics available for both models are shown.
Compare benchmark category scores on a 0-100 scale. Select a category to inspect the gap.
Avg. score
DeepSeek V4 Pro
47.9
Avg. score
Kimi K2.7 Code
54
Kimi K2.7 Code leads by 2.4
Kimi K2.7 Code leads by 9.4
Kimi K2.7 Code leads by 3.5
Kimi K2.7 Code leads by 6.1
DeepSeek V4 Pro
No data
No data
DeepSeek V4 Pro leads by 2.8
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
DeepSeek V4 Pro
winner1.04 s
Rank #31/73 · confidence 4
Kimi K2.7 Code
1.26 s
Rank #37/73 · confidence 4
DeepSeek V4 Pro
winner75.7 tok/s
Rank #44/73 · confidence 4
Kimi K2.7 Code
41.8 tok/s
Rank #68/73 · confidence 4
DeepSeek V4 Pro
winner27.36 s
Rank #50/73 · confidence 4
Kimi K2.7 Code
54.57 s
Rank #65/73 · confidence 4
DeepSeek V4 Pro
winner$0.870/M
Rank #35/169 · confidence 4
Kimi K2.7 Code
$4.00/M
Rank #96/169 · confidence 4
DeepSeek V4 Pro
winner$0.544/M
Rank #48/169 · confidence 4
Kimi K2.7 Code
$1.71/M
Rank #99/169 · confidence 4
DeepSeek V4 Pro
winner$0.435/M
Rank #68/169 · confidence 4
Kimi K2.7 Code
$0.950/M
Rank #99/169 · confidence 4
DeepSeek V4 Pro
winner12.9
Rank #20/77 · confidence 2 · eval date 2026-04-24
Kimi K2.7 Code
10.0
Rank #24/77 · confidence 1 · eval date 2026-06-12
DeepSeek V4 Pro
winner90.5%
Rank #20/194 · confidence 4
Kimi K2.7 Code
89.6%
Rank #27/194 · confidence 4
DeepSeek V4 Pro
winner33.5%
Rank #27/193 · confidence 4
Kimi K2.7 Code
32.8%
Rank #30/193 · confidence 4
DeepSeek V4 Pro
66.3
Rank #41/94 · confidence 2 · eval date 2026-04-24
Kimi K2.7 Code
66.3
Rank #41/94 · confidence 1 · eval date 2026-06-12
DeepSeek V4 Pro
50.6
Rank #41/71 · confidence 2 · eval date 2026-04-24
Kimi K2.7 Code
winner63.6
Rank #11/71 · confidence 1 · eval date 2026-06-12
DeepSeek V4 Pro
59.4
Rank #22/64 · confidence 2 · eval date 2026-04-24
Kimi K2.7 Code
winner60.8
Rank #20/64 · confidence 1 · eval date 2026-06-12
DeepSeek V4 Pro
winner50.0
Rank #25/101 · confidence 2 · eval date 2026-04-24
Kimi K2.7 Code
47.5
Rank #32/101 · confidence 1 · eval date 2026-06-12
DeepSeek V4 Pro
46.4%
Rank #34/191 · confidence 4
Kimi K2.7 Code
winner47.5%
Rank #25/191 · confidence 4
DeepSeek V4 Pro
winner94.0
Rank #4/95 · confidence 2 · eval date 2026-04-24
Kimi K2.7 Code
80.3
Rank #37/95 · confidence 1 · eval date 2026-06-12
DeepSeek V4 Pro
winner43.3
Rank #20/95 · confidence 2 · eval date 2026-04-24
Kimi K2.7 Code
38.6
Rank #30/95 · confidence 1 · eval date 2026-06-12
DeepSeek V4 Pro
winner44.3
Rank #20/104 · confidence 2 · eval date 2026-04-24
Kimi K2.7 Code
42.0
Rank #26/104 · confidence 1 · eval date 2026-06-12
DeepSeek V4 Pro
winner35.9
Rank #22/101 · confidence 2 · eval date 2026-04-24
Kimi K2.7 Code
32.8
Rank #29/101 · confidence 1 · eval date 2026-06-12
DeepSeek V4 Pro
88.8
Rank #32/101 · confidence 2 · eval date 2026-04-24
Kimi K2.7 Code
winner89.6
Rank #28/101 · confidence 1 · eval date 2026-06-12
DeepSeek V4 Pro
1260.0
Rank #31/69 · confidence 2 · eval date 2026-04-24
Kimi K2.7 Code
winner1300.0
Rank #15/69 · confidence 1 · eval date 2026-06-12
DeepSeek V4 Pro
winner76.5
Rank #12/86 · confidence 2 · eval date 2026-04-24
Kimi K2.7 Code
63.1
Rank #50/86 · confidence 1 · eval date 2026-06-12
DeepSeek V4 Pro
73.6
Rank #13/26 · confidence 2 · eval date 2026-04-24
Kimi K2.7 Code
winner76.0
Rank #9/26 · confidence 1 · eval date 2026-06-12
DeepSeek V4 Pro
winner96.2
Rank #12/84 · confidence 2 · eval date 2026-04-24
Kimi K2.7 Code
90.1
Rank #35/84 · confidence 1 · eval date 2026-06-12
DeepSeek V4 Pro
winner36.4
Rank #17/60 · confidence 2 · eval date 2026-04-24
Kimi K2.7 Code
29.6
Rank #27/60 · confidence 1 · eval date 2026-06-12
DeepSeek V4 Pro
winner1306.0
Rank #18/60 · confidence 2 · eval date 2026-04-24
Kimi K2.7 Code
1186.0
Rank #27/60 · confidence 1 · eval date 2026-06-12
DeepSeek V4 Pro
winner40.3
Rank #18/55 · confidence 2 · eval date 2026-04-24
Kimi K2.7 Code
34.3
Rank #27/55 · confidence 1 · eval date 2026-06-12
DeepSeek V4 Pro
67.4
Rank #22/59 · confidence 2 · eval date 2026-04-24
Kimi K2.7 Code
winner68.2
Rank #21/59 · confidence 1 · eval date 2026-06-12
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | DeepSeek V4 Pro | Kimi K2.7 Code |
|---|---|---|
| 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 V4 Pro | Kimi K2.7 Code |
|---|---|---|
15 tests | DeepSeek V4 Pro speed / latency 53 tok/s / 13840ms input / output No data | Kimi K2.7 Code speed / latency 46 tok/s / 3665ms input / output No data |
10 tests | DeepSeek V4 Pro speed / latency 41 tok/s / 5113ms input / output No data | Kimi K2.7 Code speed / latency N/A / N/A input / output No data |
10 tests | DeepSeek V4 Pro speed / latency 35 tok/s / 7489ms input / output No data | Kimi K2.7 Code speed / latency N/A / N/A input / output No data |
5 tests | DeepSeek V4 Pro speed / latency 48 tok/s / 4105ms input / output No data | Kimi K2.7 Code speed / latency N/A / N/A input / output No data |
5 tests | DeepSeek V4 Pro speed / latency 46 tok/s / 3739ms input / output No data | Kimi K2.7 Code speed / latency N/A / N/A input / output No data |
DeepSeek V4 Pro deepseek-v4-pro speed / latency No data input / output $0/M/$0/M | Kimi K2.7 Code kimi-k2-7-code speed / latency No data input / output $0.049/M | |
DeepSeek V4 Pro deepseek-v4-pro speed / latency No data input / output $0/request | Kimi K2.7 Code kimi-k2.7-code speed / latency No data input / output $0.100/request | |
DeepSeek V4 Pro 次DeepSeek-V4-Pro speed / latency No data input / output $0.0068/request | Kimi K2.7 Code kimi-k2.7-code speed / latency No data input / output $0.342/M |
Weighted outcome: Kimi K2.7 Code. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Output
| Features | Text inputText outputTool callingStructured outputsJSON modeReasoning | Text inputImage inputText outputTool callingStructured outputsJSON modeReasoning |
|---|
