Skip to main content
Launching the open-source gateway

Inkling-Small vs Kimi K2.5

SpecInkling-SmallKimi K2.5
Respan Index29.4 (#84)29.1 (#85)
Blended price per 1M$0.637$1
Context window1M256K
Input / output per 1M$0.45 / $1.2$0.5 / $2.5
Max output--
Inputtext, vision, audiotext, vision, video
Released2026-07-302026-01-27

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.

CategoryInkling-SmallKimi K2.5
Coding6.8 Inkling-Small9.7 Kimi K2.5
Agents41.1 Inkling-Small31.6 Kimi K2.5
Reasoning31.7 Inkling-Small30.7 Kimi K2.5
Knowledge & language19.1 Inkling-Small33.9 Kimi K2.5
Human preference50.6 Inkling-Small51.6 Kimi K2.5

How the Respan Index works

Benchmarks both report

Kimi K2.5 leads on 6 of the 8 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkInkling-SmallKimi K2.5
LMArena Elo14061450
LMArena WebDev (LMArena)14091436
LMArena Vision (LMArena)12091252
SAGE (Vals AI)32.7%49.9%
SimpleQA Verified20.6%34.3%
AIME 202695.5%95.8%
SWE-bench Verified80.2%76.8%
Toolathlon-Verified (HKUST)54.4%33%

FAQ

Is Inkling-Small better than Kimi K2.5?

Inkling-Small scores 29.4 on the Respan Index (#84), ahead of Kimi K2.5 at 29.1 (#85). Kimi K2.5 leads on 6 of the 8 benchmarks both report.

Which is cheaper, Inkling-Small or Kimi K2.5?

Inkling-Small lists at $0.45 input and $1.2 output per 1M tokens; Kimi K2.5 at $0.5 and $2.5. Inkling-Small is 1.6x cheaper per token at list price.

Which has the larger context window?

Inkling-Small accepts 1M tokens and Kimi K2.5 256K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.