SurfMind Logosurfmind
chromeAdd to Chrome

Compare models

Put models side by side on price, context, capabilities, and benchmarks.

Browse modelsLeaderboard

DeepSeek V3.2 is DeepSeek's V3-generation model upgrade underlying both the deepseek-chat (non-thinking) and deepseek-reasoner (thinking) modes, improving efficiency and reasoning quality over V3.1. It is designed as a strong, low-cost general-purpose and reasoning model.

Mathematical#93Writing, Literature, & Language#106Life, Physical, & Social Science#111Medicine & Healthcare#117
Learn more
AuthorDeepSeek
Country🇨🇳 China
ReleasedDec 1, 2025
Overview
Cost rate
0.1x
Context
164K
Input
Output
Reasoning
Tool calling
Structured outputs
Pricing/M tokens
Input$0.28
Cached input$0.03
Output$0.42
Context
Context length163,840
Max output tokens65,536
Knowledge cutoff-
Performance
Throughput-
Latency-

Llama 4 Maverick is Meta's high-capability open-weight Mixture-of-Experts model, offering strong multimodal (text and image) understanding, reasoning, and coding at efficient inference cost. It targets general-purpose assistant and agentic use cases needing frontier-adjacent quality in an open model.

Image understanding#121Writing, Literature, & Language#240Legal & Government#240Medicine & Healthcare#240
Learn more
AuthorMeta
Country🇺🇸 United States
ReleasedApr 5, 2025
Overview
Cost rate
0.1x
Context
524K
Input
Output
Reasoning
Tool calling
Structured outputs
Pricing/M tokens
Input$0.19
Cached input$0.05
Output$0.65
Context
Context length524,288
Max output tokens16,384
Knowledge cutoff2024-08-31
Performance
Throughput43 tok/s
Latency1.15s

Benchmarks

Head-to-head scores across reasoning, coding, and agentic indices, plus per-domain rankings.

Intelligence

57.6
Claude Opus 5.5 (Max, Default Fallback)
56.0
Claude Sonnet 5.5 (Max, Default Fallback)
53.4
Claude Fable 5.1 (Max, Default Fallback)
52.7
GPT-6 Astra (Max)
16.0
DeepSeek V3.2
9.3
Llama 4 Maverick

Coding

81.6
Claude Fable 5.1 (Max, Default Fallback)
78.3
GPT-5.6 Sol (Xhigh)
78.0
Claude Opus 5 (Max)
77.1
GPT-6 Astra (High)
44.2
DeepSeek V3.2
16.3
Llama 4 Maverick

Automation & Tool Use

57.9
Claude Fable 5.1 (Max, Default Fallback)
56.5
Claude Opus 5 (Max)
56.0
Qwen3.8 Max (0902)
55.5
Muse Spark 1.3 (Max)
53.1
GLM-5.3 (Max)
0.6
Llama 4 Maverick

DeepSeek V3.2 has no data

Intelligence, coding & agentic scores from Artificial Analysis.

Software & IT Services

arena.ai
1562
Gemini 4 Argon (High)
1540
Claude Opus 4.7 (High)
1539
Claude Fable 5 (High)
1538
Claude Opus 5.5 (High)
1537
Claude Opus 4.6 (High)
1534
Muse Wonder (Max)
1531
Muse Spark 1.2 (xHigh)
1531
Claude Fable 5.1 (Max)
1464
DeepSeek V3.2
1358
Llama 4 Maverick

Popular comparisons