Benchmark scores
Higher is better for all benchmark scores (SWE-bench, GPQA, HLE, Terminal-Bench, etc.). Green marks the model with the higher score.
LLM Comparison
DeepSeek V4 Pro 0813 vs DeepSeek V4 Flash 0731: benchmark scores, pricing & comparison.
Side-by-side DeepSeek V4 Pro 0813 vs DeepSeek V4 Flash 0731 comparison across SWE-bench, GPQA, HLE, Terminal-Bench, coding agent scores, token pricing, context window, and AskClash RWT. Green marks the winner on each benchmark.
Rank #15 vs #18AskClash overall scores 61.1 vs 54.8.
Pricing $0.43/$0.87 vs $0.14/$0.28Input and output token prices per 1M tokens when published.
Open Weight vs Open WeightDeepSeek vs DeepSeek.
DeepSeek V4 Pro 0813 vs DeepSeek V4 Flash 0731 benchmark comparison
Green cells highlight the winning model for each metric. Scores are cached from the AskClash LLM leaderboard snapshot.
| Metric | DeepSeek V4 Pro 0813 | DeepSeek V4 Flash 0731 |
|---|---|---|
| Overall Score | 61.1 | 54.8 |
| Leaderboard Rank | #15 | #18 |
| ACB | 54.7 | 48.0 |
| RWT | 7.0 | — |
| HLE | 42.7 | 37.0 |
| GPQA | 90.1 | 91.0 |
| MATH-500 | — | 57.4 |
| SWE-bench | 80.6 | 79.0 |
| SWE-Pro | 55.4 | — |
| Terminal-Bench | 87.9 | 82.7 |
| DeepSWE | 62.7 | 54.4 |
| MCP Atlas | 73.6 | 69.0 |
| Finance Agent | — | 49.5 |
| MRCR | — | 78.7 |
| Input Price (per 1M tokens) | $0.43 | $0.14 |
| Output Price (per 1M tokens) | $0.87 | $0.28 |
| Context Window | 1M | 1M |
| Benchmarks Published | 9 | 10 |
DeepSeek V4 Pro 0813 vs DeepSeek V4 Flash 0731 head-to-head charts
DeepSeek V4 Pro 0813 leads 7 and DeepSeek V4 Flash 0731 leads 1 of 8 shared benchmarks. DeepSeek V4 Flash 0731 is cheaper on a defined 1M-input / 200K-output workload. Charts show only benchmarks both models publish.
DeepSeek V4 Pro 0813DeepSeek V4 Flash 0731
Overall
ACB
HLE
GPQA
SWE-bench
Terminal-Bench
DeepSWE
MCP Atlas
DeepSeek V4 Pro 0813
Input$0.43
Output$0.87
Workload$0.61
Context1M
DeepSeek V4 Flash 0731
Input$0.14
Output$0.28
Workload$0.20
Context1M
Workload = published cost of 1M input + 200K output tokens. Open the live leaderboard for interactive compare charts.
More DeepSeek V4 Pro 0813 and DeepSeek V4 Flash 0731 comparisons
Explore how DeepSeek V4 Pro 0813 and DeepSeek V4 Flash 0731 stack up against other top-ranked LLMs.
Claude Opus 5 vs DeepSeek V4 Pro 0813Claude Opus 5 vs DeepSeek V4 Flash 0731Claude Fable 5 vs DeepSeek V4 Pro 0813Claude Fable 5 vs DeepSeek V4 Flash 0731GPT-5.6 Sol vs DeepSeek V4 Pro 0813GPT-5.6 Sol vs DeepSeek V4 Flash 0731Kimi K3 vs DeepSeek V4 Pro 0813Kimi K3 vs DeepSeek V4 Flash 0731Grok 4.6 vs DeepSeek V4 Pro 0813Grok 4.6 vs DeepSeek V4 Flash 0731
How to read this comparison
Token pricing
Lower is better for input and output prices. Green marks the cheaper model per 1M tokens.
Coverage matters
Models with fewer disclosed benchmark cells may have inflated percentile scores. Check the benchmark cell count for context.
This comparison page is generated from the AskClash LLM leaderboard cache. Open the live leaderboard for real-time scores and interactive filtering.