How do Gemini 3.1 Pro and DeepSeek V4 Pro (Max) compare on coding benchmarks?

The comparison table shows SWE-bench, SWE-Pro, SWE-Atlas, Terminal-Bench, DeepSWE, and coding agent index scores for both Gemini 3.1 Pro and DeepSeek V4 Pro (Max) when publicly disclosed.

LLM Comparison

Gemini 3.1 Pro vs DeepSeek V4 Pro (Max): benchmark scores, pricing & comparison.

Q: Which is better: Gemini 3.1 Pro or DeepSeek V4 Pro (Max)?

AskClash compares Gemini 3.1 Pro and DeepSeek V4 Pro (Max) 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 Gemini 3.1 Pro vs DeepSeek V4 Pro (Max) 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 Gemini 3.1 Pro model page DeepSeek V4 Pro (Max) model page

Rank #24 vs #27AskClash overall scores 51.9 vs 48.7.

Pricing $2.00/$12.0 vs $0.43/$0.87Input and output token prices per 1M tokens when published.

Proprietary vs Open WeightGoogle vs DeepSeek.

Gemini 3.1 Pro vs DeepSeek V4 Pro (Max) benchmark comparison

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

Metric	Gemini 3.1 Pro	DeepSeek V4 Pro (Max)
Overall Score	51.9	48.7
Leaderboard Rank	#24	#27
RWT	—	7.0
Coding Agent Index	42.7	—
HLE	51.4	37.7
GPQA	94.3	90.1
MATH-500	—	64.5
SWE-bench	80.6	80.6
SWE-Pro	54.2	55.4
Terminal-Bench	68.5	67.9
DeepSWE	11.8	—
MCP Atlas	69.2	73.6
Finance Agent	43.0	—
CharXiv	80.2	—
MMMU-Pro	83.9	—
ARC-AGI 2	77.1	—
Tau2	99.3	96.2
MRCR	84.9	83.5
Input Price (per 1M tokens)	$2.00	$0.43
Output Price (per 1M tokens)	$12.0	$0.87
Context Window	1M	1M
Benchmarks Published	16	9

Gemini 3.1 Pro vs DeepSeek V4 Pro (Max) head-to-head charts

Gemini 3.1 Pro leads 6 and DeepSeek V4 Pro (Max) leads 2 of 9 shared benchmarks. DeepSeek V4 Pro (Max) is cheaper on a defined 1M-input / 200K-output workload. Charts show only benchmarks both models publish.

Gemini 3.1 ProDeepSeek V4 Pro (Max)

Overall

51.9Gemini 3.1 Pro

48.7DeepSeek V4 Pro (Max)

HLE

51.4Gemini 3.1 Pro

37.7DeepSeek V4 Pro (Max)

GPQA

94.3Gemini 3.1 Pro

90.1DeepSeek V4 Pro (Max)

SWE-bench

80.6Gemini 3.1 Pro

80.6DeepSeek V4 Pro (Max)

SWE-Pro

54.2Gemini 3.1 Pro

55.4DeepSeek V4 Pro (Max)

Terminal-Bench

68.5Gemini 3.1 Pro

67.9DeepSeek V4 Pro (Max)

MCP Atlas

69.2Gemini 3.1 Pro

73.6DeepSeek V4 Pro (Max)

Tau2

99.3Gemini 3.1 Pro

96.2DeepSeek V4 Pro (Max)

MRCR

84.9Gemini 3.1 Pro

83.5DeepSeek V4 Pro (Max)

Gemini 3.1 Pro

Input$2.00

Output$12.0

Workload$4.40

Context1M

DeepSeek V4 Pro (Max)

Input$0.43

Output$0.87

Workload$0.61

Context1M

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

More Gemini 3.1 Pro and DeepSeek V4 Pro (Max) comparisons

Explore how Gemini 3.1 Pro and DeepSeek V4 Pro (Max) stack up against other top-ranked LLMs.

Claude Fable 5 vs Gemini 3.1 Pro Claude Fable 5 vs DeepSeek V4 Pro (Max)GPT-5.6 Sol vs Gemini 3.1 Pro GPT-5.6 Sol vs DeepSeek V4 Pro (Max)Claude Opus 4.8 vs Gemini 3.1 Pro Claude Opus 4.8 vs DeepSeek V4 Pro (Max)Grok 4.5 vs Gemini 3.1 Pro Grok 4.5 vs DeepSeek V4 Pro (Max)GPT-5.5 vs Gemini 3.1 Pro GPT-5.5 vs DeepSeek V4 Pro (Max)

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.