All Releases••

Open weights model

•

Released April 2026

Gemma 4 26B A4B: Intelligence, Performance & Price Analysis

Model summary

N/A
Artificial Analysis Intelligence Index
Unknown out of 4 units for Intelligence.
Time to first answer token 23.60sOutput speed 72 tok/s
N/A
Time per Intelligence Index task (minutes)
Unknown out of 4 units for Performance.
In $0.09Out $0.32Cache discount 44%
N/A
Cost per Intelligence Index task
Unknown out of 4 units for Cost.

Verbosity

N/A
Output tokens from Intelligence Index
Unknown out of 4 units for Verbosity.

Gemma 4 26B A4B (Reasoning) supports text, image, and video input, outputs text, and has a 256k tokens context window.

Pricing for Gemma 4 26B A4B (Reasoning) is $0.09 per 1M input tokens (moderately priced, median: $0.13) and $0.32 per 1M output tokens (somewhat expensive, median: $0.30).

Artificial Analysis Intelligence Index · Higher is better
No publicly available API
Inference time (minutes) per Intelligence Index task · Lower is better
No publicly available API
Weighted average cost (USD) per Intelligence Index task · Lower is better
No publicly available API

Intelligence

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v5.0.1 incorporates 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode-AA 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1

Artificial Analysis Intelligence Index by Open Weights / Proprietary

Artificial Analysis Intelligence Index v5.0.1 incorporates 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode-AA 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1

Intelligence Index vs. Cost per Task

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task
Most attractive quadrant
Pareto line

Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better
See more

Agentic knowledge work, Elo

Agentic SaaS workflows

Reasoning & knowledge

Agentic real-world work tasks, Elo

Kubernetes incident root-cause analysis

Visual reasoning

Openness Index

Artificial Analysis Openness Index: Score

Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open)

Cost

Cost per Intelligence Index Task

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

Cost to Run Artificial Analysis Intelligence Index

Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens)

Performance

Measured by time per task (minutes), output speed (tokens per second), time to first answer token and time to first token (seconds)

Time per Intelligence Index Task

Output tokens divided by end-to-end output speed (minutes per Intelligence Index task) · Speed at the model's own endpoint or the median across providers · Lower is better

Output Speed

Output tokens divided by total request time, including time to first token · Higher is better

Time to First Answer Token

Seconds to first answer token received · Accounts for reasoning model 'thinking' time

Context Window

Context Window

Context window: tokens limit · Higher is better

Model Size (Open Weights Models Only)

Model Size: Total and Active Parameters

Comparison between total model parameters and parameters active during inference (billions)

Further details

Weights
Gemma 4 26B A4B (Reasoning)
Google logoGoogle
-
25.2B
3.8B active at inference time
256k
$0.085
-
72
CoreWeaveDeepInfraGoogle
+3
Gemma 4 26B A4B (Non-reasoning)
Google logoGoogle
-
25.2B
3.8B active at inference time
256k
$0.11
-
71
CoreWeaveDeepInfraMakora
+4

Frequently Asked Questions

Common questions about Gemma 4 26B A4B