Skip to main content
Launching the open-source gateway

Inkling-Small vs Qwen3.5 397B-A17B

SpecInkling-SmallQwen3.5 397B-A17B
Respan Index29.4 (#84)29.8 (#81)
Blended price per 1M$0.637$0.387
Context window1M262K
Input / output per 1M$0.45 / $1.2$0.172 / $1.03
Max output--
Inputtext, vision, audiotext, vision
Released2026-07-302026-02-15

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.

CategoryInkling-SmallQwen3.5 397B-A17B
Coding6.8 Inkling-Small11.4 Qwen3.5 397B-A17B
Agents41.1 Inkling-Small34.2 Qwen3.5 397B-A17B
Reasoning31.7 Inkling-Small31.3 Qwen3.5 397B-A17B
Knowledge & language19.1 Inkling-Small29.7 Qwen3.5 397B-A17B
Human preference50.6 Inkling-Small50.7 Qwen3.5 397B-A17B

How the Respan Index works

Benchmarks both report

Inkling-Small leads on 8 of the 11 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkInkling-SmallQwen3.5 397B-A17B
LMArena Elo14061441
LMArena WebDev (LMArena)14091400
LMArena Vision (LMArena)12091246
Chess Puzzles (Epoch AI)18%13%
FrontierMath Tiers 1-3 v2 (Epoch AI)46.3%31.2%
GPQA Diamond88.5%88.4%
Mystery Game Puzzles (Epoch AI)6%18%
OTIS Mock AIME 2024-2025 (Epoch AI)90%88.9%
AIME 202695.5%94.2%
SWE-bench Verified80.2%76.4%
Toolathlon-Verified (HKUST)54.4%40.7%

FAQ

Is Inkling-Small better than Qwen3.5 397B-A17B?

Qwen3.5 397B-A17B scores 29.8 on the Respan Index (#81), ahead of Inkling-Small at 29.4 (#84). Inkling-Small leads on 8 of the 11 benchmarks both report.

Which is cheaper, Inkling-Small or Qwen3.5 397B-A17B?

Inkling-Small lists at $0.45 input and $1.2 output per 1M tokens; Qwen3.5 397B-A17B at $0.172 and $1.03. Qwen3.5 397B-A17B is 1.6x cheaper per token at list price.

Which has the larger context window?

Inkling-Small accepts 1M tokens and Qwen3.5 397B-A17B 262K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.