Skip to main content

Kimi K2.5 vs Qwen3.5 397B-A17B

SpecKimi K2.5Qwen3.5 397B-A17B
Respan Index29.3 (#95)29.5 (#93)
Blended price per 1M$0.9$0.387
Context window256K262K
Input / output per 1M$0.45 / $2.25$0.172 / $1.03
Max output--
Inputtext, vision, videotext, vision
Released2026-01-272026-02-15

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryKimi K2.5Qwen3.5 397B-A17B
Coding9.4 Kimi K2.511.2 Qwen3.5 397B-A17B
Agents31.2 Kimi K2.534.3 Qwen3.5 397B-A17B
Reasoning31.9 Kimi K2.530.8 Qwen3.5 397B-A17B
Knowledge & language33.5 Kimi K2.527.6 Qwen3.5 397B-A17B
Human preference52.1 Kimi K2.551.1 Qwen3.5 397B-A17B

How the Respan Index works

Benchmarks both report

Kimi K2.5 leads on 5 of the 7 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkKimi K2.5Qwen3.5 397B-A17B
LMArena Elo14501441
LMArena WebDev (LMArena)14361400
LMArena Vision (LMArena)12521246
AIME 202695.8%94.2%
Toolathlon-Verified (HKUST)33%40.7%
MMLU-Pro87.1%87.8%
SWE-bench Verified76.8%76.4%

FAQ

Is Kimi K2.5 better than Qwen3.5 397B-A17B?

Qwen3.5 397B-A17B scores 29.5 on the Respan Index (#93), ahead of Kimi K2.5 at 29.3 (#95). Kimi K2.5 leads on 5 of the 7 benchmarks both report.

Which is cheaper, Kimi K2.5 or Qwen3.5 397B-A17B?

Kimi K2.5 lists at $0.45 input and $2.25 output per 1M tokens; Qwen3.5 397B-A17B at $0.172 and $1.03. Qwen3.5 397B-A17B is 2.3x cheaper per token at list price.

Which has the larger context window?

Kimi K2.5 accepts 256K tokens and Qwen3.5 397B-A17B 262K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.