Which is better for coding — DeepSeek-V3.2-Exp or Mercury 2?

Direct comparison on the SWE-Bench benchmark is not available. We recommend reviewing other metrics on the comparison page.

Which model is cheaper — DeepSeek-V3.2-Exp or Mercury 2?

API pricing data is available on the individual model pages.

Which has a larger context window — DeepSeek-V3.2-Exp or Mercury 2?

Context window data is available on the individual model pages.

DeepSeek-V3.2-Exp vs Mercury 2: Specs & Benchmark Comparison

Characteristic	DeepSeek-V3.2-Exp	Mercury 2
Company	DeepSeek	Inception
Release Date	September 28, 2025	February 1, 2026
Parameters	685B	—
Multimodal	No	No
Context (input)	164K	—
Context (output)	66K	—
Input Price / 1M	$0.27	—
Output Price / 1M	$0.41	—
Average Score	0.8	0.7
Benchmarks
GPQA	0.8	0.7
AIME 2025	0.9	0.9

Visual Benchmark Comparison

DeepSeek-V3.2-Exp

Mercury 2

GPQA0.8 vs 0.7

0.8

0.7

AIME 20250.9 vs 0.9

0.9

Verdict

Mercury 2 leads in 1 out of 2 comparison categories.

Overall Performance

Both models show comparable average scores: DeepSeek-V3.2-Exp — 0.8, Mercury 2 — 0.7.

Recency

Mercury 2 is newer: released 2/1/2026 vs 9/28/2025.

More About These Models

DeepSeek-V3.2-Exp

DeepSeek — specs, benchmarks, API

Mercury 2

Inception — specs, benchmarks, API

Related Comparisons

DeepSeek-V3.2-Exp vs DeepSeek-V3.2 (Thinking)DeepSeek-V3.2-Exp vs LongCat-Flash-Thinking DeepSeek-V3.2-Exp vs GLM-4.5 DeepSeek-V3.2-Exp vs MiMo-V2-Flash DeepSeek-V3.2-Exp vs LongCat-Flash-Chat DeepSeek-V3.2-Exp vs Qwen3.5 9B

All model comparisons →

The DeepSeek-V3.2-Exp and Mercury 2 comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the DeepSeek-V3.2-Exp or Mercury 2 page. See also the complete list of AI model comparisons.