Kimi K2vsQwen3.8-Max

Kimi K2
Qwen3.8-Max
Specifications
Parameters
1T
2.4T
Context window
128k
1M
Benchmarks
Nonsense detection
BullshitBench v2
10%
Agentic coding
SWE-Bench Pro
67.7%
Coding
SWE-Bench Verified
65.8%
Research reproduction
PaperBench
93%
Agentic terminal coding
Terminal-Bench 2.1
86.6%
Professional tool use
JobBench
53.4%
Science
GPQA Diamond
75.1%
Agentic computer use
OSWorld-Verified
86.1%
Chart reasoning
CharXiv Reasoning
88.4%
Visual reasoning
BabyVision
82%
Overview
CompanyMoonshot AIQwen
Release dateJul 11 2025Aug 3 2026
AccessOpen WeightProprietary

Which is better: Kimi K2 or Qwen3.8-Max?

Kimi K2 and Qwen3.8-Max don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Kimi K2 shipped 388 days before Qwen3.8-Max, so benchmark comparisons should account for the intervening progress.

Kimi K2 has 1T parameters, while Qwen3.8-Max has 2.4T. Context windows are 128k (Kimi K2) vs 1M (Qwen3.8-Max). Kimi K2 is open weight, while Qwen3.8-Max is proprietary.

Direct benchmark comparisons are unavailable — Kimi K2 and Qwen3.8-Max don't publish scores on any of the same benchmarks.

Frequently asked questions

Kimi K2 was released by Moonshot AI on Jul 11 2025.

Qwen3.8-Max was released by Qwen on Aug 3 2026.

Kimi K2 has a 128k context window; Qwen3.8-Max has 1M.

Kimi K2 is an open weight model released by Moonshot AI. Qwen3.8-Max is a proprietary model released by Qwen.

Other comparisons