DeepSeek Chat (V3) — Benchmark Results
DeepSeek Overall Score: 62/100
Performance Scores
Overall
62
Rank #26 of 45 — Top 42%
SWE-bench
56
Rank #26 of 45 — Top 42%
LiveCodeBench
64
Rank #26 of 45 — Top 42%
HumanEval
84
Rank #24 of 45 — Top 47%
BigCodeBench
46
Rank #26 of 45 — Top 42%
Strengths & Weaknesses
Strengths
- Excellent value
- Strong coding focus
Weaknesses
- Less general-purpose
Compare with Similar-Priced Models
| Model | Overall Score | Input $/M |
|---|---|---|
| DeepSeek Chat (V3) | 62 | $0.270 |
| Claude 3.5 Haiku | 52 | $0.800 |
| Claude 3 Haiku | 45 | $0.250 |
| GPT-4o mini | 58 | $0.150 |
| GPT-3.5 Turbo | 40 | $0.500 |
| OpenAI o1-mini | 70 | $1.10 |