LLM Comparison

DeepSeek V4 Pro 0813 vs Hy4 Preview: benchmark scores, pricing & comparison.

Side-by-side DeepSeek V4 Pro 0813 vs Hy4 Preview 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.

Open live leaderboardDeepSeek V4 Pro 0813 model pageHy4 Preview model page
Rank #22 vs #29AskClash overall scores 53.1 vs 36.1.
Pricing $0.43/$0.87 vs $0.83/$2.50Input and output token prices per 1M tokens when published.
Open Weight vs Open WeightDeepSeek vs Tencent.

DeepSeek V4 Pro 0813 vs Hy4 Preview benchmark comparison

Green cells highlight the winning model for each metric. Scores are cached from the AskClash LLM leaderboard snapshot.

MetricDeepSeek V4 Pro 0813Hy4 Preview
Overall Score53.136.1
Leaderboard Rank#22#29
ACB54.8—
RWT7.08.5
HLE42.743.4
GPQA90.192.3
SWE-bench80.6—
SWE-Pro55.465.7
Terminal-Bench87.985.4
DeepSWE62.764.3
GDPval-AA1554.01678.0
MCP Atlas73.683.7
Finance Agent44.1—
Tau296.2—
Input Price (per 1M tokens)$0.43$0.83
Output Price (per 1M tokens)$0.87$2.50
Context Window1M1M
Benchmarks Published117

DeepSeek V4 Pro 0813 vs Hy4 Preview head-to-head charts

DeepSeek V4 Pro 0813 leads 2 and Hy4 Preview leads 7 of 9 shared benchmarks. DeepSeek V4 Pro 0813 is cheaper on a defined 1M-input / 200K-output workload. Charts show only benchmarks both models publish.

DeepSeek V4 Pro 0813Hy4 Preview
Overall
53.1DeepSeek V4 Pro 0813
36.1Hy4 Preview
RWT
7.0DeepSeek V4 Pro 0813
8.5Hy4 Preview
HLE
42.7DeepSeek V4 Pro 0813
43.4Hy4 Preview
GPQA
90.1DeepSeek V4 Pro 0813
92.3Hy4 Preview
SWE-Pro
55.4DeepSeek V4 Pro 0813
65.7Hy4 Preview
Terminal-Bench
87.9DeepSeek V4 Pro 0813
85.4Hy4 Preview
DeepSWE
62.7DeepSeek V4 Pro 0813
64.3Hy4 Preview
GDPval-AA
1554.0DeepSeek V4 Pro 0813
1678.0Hy4 Preview
MCP Atlas
73.6DeepSeek V4 Pro 0813
83.7Hy4 Preview
DeepSeek V4 Pro 0813
Input$0.43
Output$0.87
Workload$0.61
Context1M
Hy4 Preview
Input$0.83
Output$2.50
Workload$1.33
Context1M

Workload = published cost of 1M input + 200K output tokens. Open the live leaderboard for interactive compare charts.

More DeepSeek V4 Pro 0813 and Hy4 Preview comparisons

Explore how DeepSeek V4 Pro 0813 and Hy4 Preview stack up against other top-ranked LLMs.

Claude Fable 5.1 vs DeepSeek V4 Pro 0813Claude Fable 5.1 vs Hy4 PreviewClaude Fable 5 vs DeepSeek V4 Pro 0813Claude Fable 5 vs Hy4 PreviewGPT-5.6 Sol vs DeepSeek V4 Pro 0813GPT-5.6 Sol vs Hy4 PreviewClaude Opus 5 vs DeepSeek V4 Pro 0813Claude Opus 5 vs Hy4 PreviewGrok 4.6 vs DeepSeek V4 Pro 0813Grok 4.6 vs Hy4 Preview

How to read this comparison

Benchmark scores

Higher is better for all benchmark scores (SWE-bench, GPQA, HLE, Terminal-Bench, etc.). Green marks the model with the higher score.

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.