Gemma 4 26B-A4B vs Inkling-Small
Inkling-Small leads the LLM Stats Score 38.1 to 29.5. Gemma 4 26B-A4B is 3.8x cheaper per token.
Google · Thinking Machines Lab · Updated for 2026
Which is better?
Inkling-Small leads the overall LLM Stats Score 38.1 to 29.5, ranking #77 overall.
In the 4 individual benchmarks reported for both models, Inkling-Small wins 4; this is a narrower head-to-head signal than the composite indexes.
On price, Gemma 4 26B-A4B is roughly 3.8x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
Gemma 4 26B-A4B also accepts a larger context window (262,144 input tokens), making it the stronger choice for long documents and large codebases.
Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.
Choose Gemma 4 26B-A4B
- cost matters — it's about 3.8x cheaper per token
- you process long inputs — it offers a 262,144 token context window
Choose Inkling-Small
- overall performance matters — it scores 38.1 and ranks #77 on LLM Stats
- your work emphasizes reasoning — it leads those capability indexes
- you value its reported benchmark strengths — it wins 4 of 4 exact shared results
- you want the most recent training data — it shipped Jul 2026
At a glance
The differences that matter most.
Capability indexes
Additional strengths measured across groups of related public benchmarks
Individual benchmarks
12 reported for Gemma 4 26B-A4B · 24 for Inkling-Small
Gemma 4 26B-A4B outperforms in 0 benchmarks, while Inkling-Small is better at 4 benchmarks (AIME 2026, GPQA, Humanity's Last Exam, MMMU-Pro).
Inkling-Small significantly outperforms across most benchmarks.
Human preference
Blind head-to-head votes and playground preference scores
Pricing Analysis
Price comparison per million tokens
For input processing, Gemma 4 26B-A4B ($0.07/1M tokens) is 4.3x cheaper than Inkling-Small ($0.30/1M tokens).
For output processing, Gemma 4 26B-A4B ($0.34/1M tokens) is 3.5x cheaper than Inkling-Small ($1.20/1M tokens).
In conclusion, Inkling-Small is more expensive than Gemma 4 26B-A4B.*
* Using a 3:1 ratio of input to output tokens
Model Size
Parameter count comparison
Inkling-Small has 250.8B more parameters than Gemma 4 26B-A4B, making it 995.2% larger.
Context Window
Maximum input and output token capacity
Gemma 4 26B-A4B accepts 262,144 input tokens compared to Inkling-Small's 256,000 tokens. Gemma 4 26B-A4B can generate longer responses up to 262,144 tokens, while Inkling-Small is limited to 256,000 tokens.
Input capabilities
Documented input modalities across available providers
Both Gemma 4 26B-A4B and Inkling-Small support multimodal inputs.
They are both capable of processing various types of data, offering versatility in application.
Gemma 4 26B-A4B
Inkling-Small
License
Usage and distribution terms
Both models are licensed under Apache 2.0.
Both models share the same licensing terms, providing consistent usage rights.
Apache 2.0
Open weights
Apache 2.0
Open weights
Release Timeline
When each model was launched
Gemma 4 26B-A4B was released on 2026-04-02, while Inkling-Small was released on 2026-07-30.
Inkling-Small is 4 months newer than Gemma 4 26B-A4B.
Apr 2, 2026
6 months ago
Jul 30, 2026
2 months ago
3mo newerKnowledge Cutoff
When training data ends
Gemma 4 26B-A4B has a documented knowledge cutoff of 2025-01-01, while Inkling-Small's cutoff date is not specified.
We can confirm Gemma 4 26B-A4B's training data extends to 2025-01-01, but cannot make a direct comparison without Inkling-Small's cutoff date.
Jan 2025
—
Provider Availability
Gemma 4 26B-A4B is available from DeepInfra, Novita. Inkling-Small is available from Thinking Machines Lab, DeepInfra.
Gemma 4 26B-A4B
Inkling-Small
Outputs Comparison
Judge for yourself.
Run your own prompts against Gemma 4 26B-A4B and Inkling-Small side-by-side, then vote on the output you prefer.
FAQ
Common questions about Gemma 4 26B-A4B vs Inkling-Small.