Data points: 95
Model compare
The readout for DeepSeek R1 and DeepSeek V3, before the detailed comparison sheet.
Weighted outcome: DeepSeek R1. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Decision read
DeepSeek R1
DeepSeek R1 has the higher weighted result; Model A / B score 90 to 10.
Evidence depth
95 data points
Includes 19 benchmark rows, 0 audit samples, and 6 provider examples.
Selection signal
Start with DeepSeek R1
The charts below split 25 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 R1 and DeepSeek V3: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Model compare | DeepSeek R1 | DeepSeek V3 |
|---|---|---|
| Overall leader | Leading | Contender |
| Weighted overall score | 90.0 pts | 10.0 pts |
| Benchmark category leads | 6 categories | 0 categories |
| Operational advantages | Cheapest input price, Average speed | First-token latency, Provider coverage |
| Context window | 163.8K tokens | No data |
| Max output | 16K tokens | No data |
| Modalities | Input Text Output Text | No data |
| 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 R1 | DeepSeek V3 |
|---|---|---|
| Developer | DeepSeek | No data |
| Released | May 2025 | No data |
| Parameters | No data | No data |
| Tokenizer | DeepSeek | No data |
| Knowledge cutoff | 2024-07-31 | No data |
| OpenRouter ID | deepseek/deepseek-r1 | No data |
| References | No data | No data |
This report only uses LMSpeed data for DeepSeek R1 and DeepSeek V3: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
DeepSeek R1
DeepSeek R1 is stronger in benchmark categories (Agents, Coding, Reasoning, Knowledge, Math) and operational dimensions (Cheapest input price, Average speed).
DeepSeek V3
DeepSeek V3 has these operational advantages: First-token latency, 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 R1
48.1
Avg. score
DeepSeek V3
41.5
DeepSeek R1 leads by 6.2
DeepSeek R1 leads by 12.4
DeepSeek R1 leads by 6.2
DeepSeek R1 leads by 3.6
DeepSeek R1 leads by 7.7
No data
No data
DeepSeek R1 leads by 3.6
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
DeepSeek R1
$4.20/M
Rank #95/162 · confidence 4
DeepSeek V3
winner$0.890/M
Rank #37/162 · confidence 4
DeepSeek R1
$2.06/M
Rank #102/162 · confidence 4
DeepSeek V3
winner$0.493/M
Rank #39/162 · confidence 4
DeepSeek R1
$1.35/M
Rank #115/162 · confidence 4
DeepSeek V3
winner$0.360/M
Rank #59/162 · confidence 4
DeepSeek R1
winner84.9%
Rank #27/125 · confidence 4
DeepSeek V3
75.2%
Rank #85/125 · confidence 4
DeepSeek R1
winner54.7
Rank #64/89 · confidence 1 · eval date 2025-01-20
DeepSeek V3
29.0
Rank #81/89 · confidence 1 · eval date 2024-12-26
DeepSeek R1
winner81.3%
Rank #70/188 · confidence 4
DeepSeek V3
55.7%
Rank #155/188 · confidence 4
DeepSeek R1
winner14.9%
Rank #73/187 · confidence 4
DeepSeek V3
3.6%
Rank #173/187 · confidence 4
DeepSeek R1
winner77.0%
Rank #22/115 · confidence 4
DeepSeek V3
35.9%
Rank #78/115 · confidence 4
DeepSeek R1
winner40.3
Rank #55/96 · confidence 1 · eval date 2025-01-20
DeepSeek V3
35.4
Rank #77/96 · confidence 1 · eval date 2024-12-26
DeepSeek R1
winner40.3%
Rank #66/185 · confidence 4
DeepSeek V3
35.4%
Rank #110/185 · confidence 4
DeepSeek R1
winner89.3%
Rank #4/68 · confidence 4
DeepSeek V3
25.3%
Rank #44/68 · confidence 4
DeepSeek R1
winner98.3%
Rank #6/74 · confidence 4
DeepSeek V3
88.7%
Rank #37/74 · confidence 4
DeepSeek R1
84.0
Rank #28/90 · confidence 1 · eval date 2025-01-20
DeepSeek V3
winner89.4
Rank #14/90 · confidence 1 · eval date 2024-12-26
DeepSeek R1
winner31.0
Rank #42/90 · confidence 1 · eval date 2025-01-20
DeepSeek V3
25.4
Rank #54/90 · confidence 1 · eval date 2024-12-26
DeepSeek R1
winner81.3
Rank #58/96 · confidence 1 · eval date 2025-01-20
DeepSeek V3
55.7
Rank #90/96 · confidence 1 · eval date 2024-12-26
DeepSeek R1
winner14.9
Rank #60/96 · confidence 1 · eval date 2025-01-20
DeepSeek V3
3.6
Rank #93/96 · confidence 1 · eval date 2024-12-26
DeepSeek R1
winner20.1
Rank #73/99 · confidence 1 · eval date 2025-01-20
DeepSeek V3
14.2
Rank #85/99 · confidence 1 · eval date 2024-12-26
DeepSeek R1
winner39.6
Rank #71/86 · confidence 1 · eval date 2025-01-20
DeepSeek V3
34.8
Rank #81/86 · confidence 1 · eval date 2024-12-26
DeepSeek R1
winner36.5
Rank #72/84 · confidence 1 · eval date 2025-01-20
DeepSeek V3
22.8
Rank #78/84 · confidence 1 · eval date 2024-12-26
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | DeepSeek R1 | DeepSeek V3 |
|---|---|---|
| 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 | DeepSeek V3 |
|---|---|---|
381 tests | DeepSeek R1 speed / latency 45 tok/s / 1011ms input / output No data | DeepSeek V3 speed / latency 17 tok/s / 1076ms input / output No data |
124 tests | DeepSeek R1 speed / latency 56 tok/s / 9259ms input / output No data | DeepSeek V3 speed / latency N/A / N/A input / output No data |
110 tests | DeepSeek R1 speed / latency 13 tok/s / 54820ms input / output No data | DeepSeek V3 speed / latency 36 tok/s / 2831ms input / output No data |
104 tests | DeepSeek R1 speed / latency 46 tok/s / 11949ms input / output No data | DeepSeek V3 speed / latency N/A / N/A input / output No data |
50 tests | DeepSeek R1 speed / latency 32 tok/s / 21696ms input / output No data | DeepSeek V3 speed / latency N/A / N/A input / output No data |
DeepSeek R1 deepseek-r1 speed / latency No data input / output $0/request | DeepSeek V3 deepseek-v3-0324 speed / latency No data input / output $0/request |
Weighted outcome: DeepSeek R1. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Text inputText outputTool callingStructured outputsJSON modeReasoning |
| None listed |
