How do DeepSeek V4 Pro (Max) and DeepSeek V4 Pro compare on coding benchmarks?

The comparison table shows SWE-bench, SWE-Pro, SWE-Atlas, Terminal-Bench, DeepSWE, and coding agent index scores for both DeepSeek V4 Pro (Max) and DeepSeek V4 Pro when publicly disclosed.

LLM Comparison

DeepSeek V4 Pro (Max) vs DeepSeek V4 Pro: benchmark scores, pricing & comparison.

Q: Which is better: DeepSeek V4 Pro (Max) or DeepSeek V4 Pro?

AskClash compares DeepSeek V4 Pro (Max) and DeepSeek V4 Pro side by side across SWE-bench, GPQA, HLE, Terminal-Bench, coding agent scores, token pricing, and context window so you can see which model wins on each benchmark.

Side-by-side DeepSeek V4 Pro (Max) vs DeepSeek V4 Pro 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 leaderboard DeepSeek V4 Pro (Max) model page DeepSeek V4 Pro model page

Rank #27 vs #50AskClash overall scores 48.7 vs 20.5.

Pricing $0.43/$0.87 vs $1.74/$3.48Input and output token prices per 1M tokens when published.

Open Weight vs Open WeightDeepSeek vs DeepSeek.

DeepSeek V4 Pro (Max) vs DeepSeek V4 Pro benchmark comparison

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

Metric	DeepSeek V4 Pro (Max)	DeepSeek V4 Pro
Overall Score	48.7	20.5
Leaderboard Rank	#27	#50
RWT	7.0	7.0
HLE	37.7	7.7
GPQA	90.1	72.9
MATH-500	64.5	64.5
SWE-bench	80.6	73.6
SWE-Pro	55.4	52.1
Terminal-Bench	67.9	59.1
MCP Atlas	73.6	69.4
Finance Agent	—	44.1
Tau2	96.2	—
MRCR	83.5	44.7
Input Price (per 1M tokens)	$0.43	$1.74
Output Price (per 1M tokens)	$0.87	$3.48
Context Window	1M	1M
Benchmarks Published	9	8

DeepSeek V4 Pro (Max) vs DeepSeek V4 Pro head-to-head charts

DeepSeek V4 Pro (Max) leads 8 and DeepSeek V4 Pro leads 0 of 10 shared benchmarks. DeepSeek V4 Pro (Max) is cheaper on a defined 1M-input / 200K-output workload. Charts show only benchmarks both models publish.

DeepSeek V4 Pro (Max)DeepSeek V4 Pro

Overall

48.7DeepSeek V4 Pro (Max)

20.5DeepSeek V4 Pro

RWT

7.0DeepSeek V4 Pro (Max)

7.0DeepSeek V4 Pro

HLE

37.7DeepSeek V4 Pro (Max)

7.7DeepSeek V4 Pro

GPQA

90.1DeepSeek V4 Pro (Max)

72.9DeepSeek V4 Pro

MATH-500

64.5DeepSeek V4 Pro (Max)

64.5DeepSeek V4 Pro

SWE-bench

80.6DeepSeek V4 Pro (Max)

73.6DeepSeek V4 Pro

SWE-Pro

55.4DeepSeek V4 Pro (Max)

52.1DeepSeek V4 Pro

Terminal-Bench

67.9DeepSeek V4 Pro (Max)

59.1DeepSeek V4 Pro

MCP Atlas

73.6DeepSeek V4 Pro (Max)

69.4DeepSeek V4 Pro

MRCR

83.5DeepSeek V4 Pro (Max)

44.7DeepSeek V4 Pro

DeepSeek V4 Pro (Max)

Input$0.43

Output$0.87

Workload$0.61

Context1M

DeepSeek V4 Pro

Input$1.74

Output$3.48

Workload$2.44

Context1M

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

More DeepSeek V4 Pro (Max) and DeepSeek V4 Pro comparisons

Explore how DeepSeek V4 Pro (Max) and DeepSeek V4 Pro stack up against other top-ranked LLMs.

Claude Fable 5 vs DeepSeek V4 Pro (Max)Claude Fable 5 vs DeepSeek V4 Pro GPT-5.6 Sol vs DeepSeek V4 Pro (Max)GPT-5.6 Sol vs DeepSeek V4 Pro Claude Opus 4.8 vs DeepSeek V4 Pro (Max)Claude Opus 4.8 vs DeepSeek V4 Pro Grok 4.5 vs DeepSeek V4 Pro (Max)Grok 4.5 vs DeepSeek V4 Pro GPT-5.5 vs DeepSeek V4 Pro (Max)GPT-5.5 vs DeepSeek V4 Pro

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.