Data points: 95
Model compare
The readout for DeepSeek V3.1 and DeepSeek V3.2, before the detailed comparison sheet.
Weighted outcome: DeepSeek V3.1. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Decision read
DeepSeek V3.1
DeepSeek V3.1 has the higher weighted result; Model A / B score 61.3 to 38.7.
Evidence depth
95 data points
Includes 19 benchmark rows, 0 audit samples, and 8 provider examples.
Selection signal
Start with DeepSeek V3.1
The charts below split 27 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 V3.1 and DeepSeek V3.2: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Model compare | DeepSeek V3.1 | DeepSeek V3.2 |
|---|---|---|
| Overall leader | Leading | Contender |
| Weighted overall score | 61.3 pts | 38.7 pts |
| Benchmark category leads | 4 categories | 2 categories |
| Operational advantages | Average speed, First-token latency | Cheapest input price, Free providers, Provider coverage |
| Context window | No data | 163.8K tokens |
| Max output | No data | 65.5K tokens |
| Modalities | No data | Input Text Output Text |
| Features |
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 V3.1 | DeepSeek V3.2 |
|---|---|---|
| Developer | DeepSeek | DeepSeek |
| Released | No data | Dec 2025 |
| Parameters | No data | No data |
| Tokenizer | No data | DeepSeek |
| Knowledge cutoff | No data | No data |
| OpenRouter ID | No data | deepseek/deepseek-v3.2 |
| References | No data | No data |
This report only uses LMSpeed data for DeepSeek V3.1 and DeepSeek V3.2: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
DeepSeek V3.1
DeepSeek V3.1 is stronger in benchmark categories (Agents, Coding, Knowledge, Math) and operational dimensions (Average speed, First-token latency).
DeepSeek V3.2
DeepSeek V3.2 is stronger in benchmark categories (Reasoning, Instruction following) and operational dimensions (Cheapest input price, Free providers, Provider coverage).
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 V3.1
47.3
Avg. score
DeepSeek V3.2
46.4
DeepSeek V3.1 leads by 1.6
DeepSeek V3.1 leads by 3.0
DeepSeek V3.2 leads by 1.4
DeepSeek V3.1 leads by 1.5
DeepSeek V3.1 leads by 4.0
No data
No data
DeepSeek V3.2 leads by 3.5
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
DeepSeek V3.1
$1.68/M
Rank #59/163 · confidence 4
DeepSeek V3.2
winner$0.420/M
Rank #18/163 · confidence 4
DeepSeek V3.1
$0.840/M
Rank #67/163 · confidence 4
DeepSeek V3.2
winner$0.315/M
Rank #27/163 · confidence 4
DeepSeek V3.1
$0.560/M
Rank #79/163 · confidence 4
DeepSeek V3.2
winner$0.280/M
Rank #44/163 · confidence 4
DeepSeek V3.1
83.3%
Rank #39/125 · confidence 4
DeepSeek V3.2
winner86.2%
Rank #15/125 · confidence 4
DeepSeek V3.1
winner2.0
Rank #46/73 · confidence 1 · eval date 2025-08-21
DeepSeek V3.2
0.9
Rank #60/73 · confidence 1 · eval date 2025-12-01
DeepSeek V3.1
6.3%
Rank #121/186 · confidence 4
DeepSeek V3.2
winner22.2%
Rank #49/186 · confidence 4
DeepSeek V3.1
73.5%
Rank #105/187 · confidence 4
DeepSeek V3.2
winner84.0%
Rank #52/187 · confidence 4
DeepSeek V3.1
winner53.3
Rank #65/89 · confidence 1 · eval date 2025-08-21
DeepSeek V3.2
39.0
Rank #76/89 · confidence 1 · eval date 2025-12-01
DeepSeek V3.1
57.7%
Rank #46/115 · confidence 4
DeepSeek V3.2
winner86.2%
Rank #5/115 · confidence 4
DeepSeek V3.1
winner39.1
Rank #63/96 · confidence 1 · eval date 2025-08-21
DeepSeek V3.2
38.7
Rank #65/96 · confidence 1 · eval date 2025-12-01
DeepSeek V3.1
36.7%
Rank #97/184 · confidence 4
DeepSeek V3.2
winner38.9%
Rank #81/184 · confidence 4
DeepSeek V3.1
80.3
Rank #38/90 · confidence 1 · eval date 2025-08-21
DeepSeek V3.2
winner93.5
Rank #5/90 · confidence 1 · eval date 2025-12-01
DeepSeek V3.1
winner28.8
Rank #47/90 · confidence 1 · eval date 2025-08-21
DeepSeek V3.2
24.2
Rank #62/90 · confidence 1 · eval date 2025-12-01
DeepSeek V3.1
winner13.0
Rank #64/96 · confidence 1 · eval date 2025-08-21
DeepSeek V3.2
10.5
Rank #69/96 · confidence 1 · eval date 2025-12-01
DeepSeek V3.1
winner77.9
Rank #65/96 · confidence 1 · eval date 2025-08-21
DeepSeek V3.2
75.1
Rank #70/96 · confidence 1 · eval date 2025-12-01
DeepSeek V3.1
20.7
Rank #73/99 · confidence 1 · eval date 2025-08-21
DeepSeek V3.2
winner24.7
Rank #67/99 · confidence 1 · eval date 2025-12-01
DeepSeek V3.1
1155.0
Rank #50/65 · confidence 1 · eval date 2025-08-21
DeepSeek V3.2
winner1206.0
Rank #42/65 · confidence 1 · eval date 2025-12-01
DeepSeek V3.1
41.5
Rank #67/86 · confidence 1 · eval date 2025-08-21
DeepSeek V3.2
winner49.0
Rank #58/86 · confidence 1 · eval date 2025-12-01
DeepSeek V3.1
37.4
Rank #71/84 · confidence 1 · eval date 2025-08-21
DeepSeek V3.2
winner78.9
Rank #56/84 · confidence 1 · eval date 2025-12-01
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | DeepSeek V3.1 | DeepSeek V3.2 |
|---|---|---|
| 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 V3.1 | DeepSeek V3.2 |
|---|---|---|
126 tests | DeepSeek V3.1 speed / latency N/A / N/A input / output No data | DeepSeek V3.2 speed / latency 26 tok/s / 11125ms input / output No data |
80 tests | DeepSeek V3.1 speed / latency 265 tok/s / 951ms input / output No data | DeepSeek V3.2 speed / latency 235 tok/s / 1787ms input / output No data |
55 tests | DeepSeek V3.1 speed / latency N/A / N/A input / output No data | DeepSeek V3.2 speed / latency 27 tok/s / 1295ms input / output No data |
40 tests | DeepSeek V3.1 speed / latency 41 tok/s / 2356ms input / output No data | DeepSeek V3.2 speed / latency 18 tok/s / 4488ms input / output No data |
40 tests | DeepSeek V3.1 speed / latency N/A / N/A input / output No data | DeepSeek V3.2 speed / latency 29 tok/s / 1828ms input / output No data |
DeepSeek V3.1 deepseek-v3.1 speed / latency No data input / output $0/M/$0/M | DeepSeek V3.2 deepseek-v3.2 speed / latency No data input / output $0.018/M | |
DeepSeek V3.1 deepseek-v3.1 speed / latency No data input / output $0/request | DeepSeek V3.2 deepseek-v3.2-exp speed / latency No data input / output $0/request | |
DeepSeek V3.1 deepseek-ai/deepseek-v3.1 speed / latency No data input / output $0.010/request | DeepSeek V3.2 deepseek-v3.2 speed / latency No data input / output $0.010/request |
Weighted outcome: DeepSeek V3.1. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
| None listed |
Text inputText outputTool callingStructured outputsJSON modeReasoning |
