Google · Open weights
Gemma 4 26B A4B
Google's Gemma 4 26B A4B instruction-tuned model built for scalable reasoning, coding, long-context, and multimodal workflows. This route is tuned for faster direct answers while preserving multimodal and structured output support. Requests containing video cost $0.10 per million input tokens and $0.40 per million output tokens.
- Reasoning
- Tools
- Vision
- Structured output
- Video input
- Input
- Text, Images, Video
- Output
- Text
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $0.09
- Output
- $0.30
- Cache read
- $0.05
Reference prices as published by the model provider. API example
Specifications
- Context window
- 262.1K
- Max output
- 131.1K
- Average output (7 days)
- 131 tokens
- Longer than 13% of 465 models
Side by side
Gemma 4 26B A4B compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| Gemma 4 26B A4BGoogleThis model | Gemma 3 12B ITGoogleRemove | |
|---|---|---|
| Provider | ||
| Discovery tier | Open weights | Open weights |
| Added | Apr 2, 2026 | Jan 1, 2024 |
| Limits | ||
| Context window | 262.14KBest | 131.07K |
| Max output | 131.07KBest | 16.38K |
| Average output | 131 tokens | 168 tokens |
| Pricing, USD per 1M tokens | ||
| Input | $0.09Best | $0.27 |
| Output | $0.30 | $0.27Best |
| Cache read | $0.05 | — |
| Performance | ||
| Throughput | 72.7 tok/s | — |
| Time to first token | 2.9 s | — |
| Request success (24h) | 100.0% | 100.0% |
| Benchmark indexes | ||
| Intelligence Index | 16.7Best | 3.8 |
| Coding Index | 39.3Best | 5.8 |
| Math Index | — | 18.3 |
| Capabilities | ||
| Reasoning | Yes | No |
| Tools | Yes | No |
| Vision | Yes | No |
| Structured output | Yes | No |
| PDF input | No | Yes |
| Video input | Yes | No |
| Reasoning effort | — | — |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- Gemma 4 26B A4B
- Gemma 3 12B IT
Intelligence Index
- Gemma 4 26B A4B16.7
- Gemma 3 12B IT3.8
Gemma 4 26B A4B: Better than 44% of 326 scored models
Indexes
Coding Index
Composite of the coding evaluations
- Gemma 4 26B A4B: 39.3Top
- Gemma 3 12B IT: 5.8
Math Index
Composite of the math evaluations
- Gemma 4 26B A4B: —
- Gemma 3 12B IT: 18.3
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- Gemma 4 26B A4B: 1.9%Top
- Gemma 3 12B IT: 0.2%
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- Gemma 4 26B A4B: 0.2%Top
- Gemma 3 12B IT: 0.0%
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- Gemma 4 26B A4B: 315 Elo
- Gemma 3 12B IT: —
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- Gemma 4 26B A4B: 565 Elo
- Gemma 3 12B IT: —
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- Gemma 4 26B A4B: —
- Gemma 3 12B IT: 1.0%
AA-LCRv1.1
Reasoning across long documents
- Gemma 4 26B A4B: 65.7%Top
- Gemma 3 12B IT: 8.3%
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- Gemma 4 26B A4B: 19.3%Top
- Gemma 3 12B IT: 4.2%
GPQA Diamond
Graduate-level science questions
- Gemma 4 26B A4B: 79.2%Top
- Gemma 3 12B IT: 34.9%
MMLU-Pro
Multi-subject knowledge and reasoning
- Gemma 4 26B A4B: —
- Gemma 3 12B IT: 59.5%
IFBench
Following precise output instructions
- Gemma 4 26B A4B: 72.4%Top
- Gemma 3 12B IT: 36.7%
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- Gemma 4 26B A4B: —
- Gemma 3 12B IT: 0.0%
SciCode
Scientific computing in Python
- Gemma 4 26B A4B: 40.0%Top
- Gemma 3 12B IT: 16.4%
LiveCodeBench
Recent competitive programming problems
- Gemma 4 26B A4B: —
- Gemma 3 12B IT: 13.7%
Math
AIME 2025
Competition mathematics, 2025 problems
- Gemma 4 26B A4B: —
- Gemma 3 12B IT: 18.3%
AIME
Competition mathematics
- Gemma 4 26B A4B: —
- Gemma 3 12B IT: 22.0%
MATH-500
Competition math problems
- Gemma 4 26B A4B: —
- Gemma 3 12B IT: 85.3%
Legacy evaluations
Terminal-Bench Hard
Earlier terminal task suite
- Gemma 4 26B A4B: 13.6%Top
- Gemma 3 12B IT: 0.8%
τ²-Bench Telecom
Tool use in a customer-support simulation
- Gemma 4 26B A4B: 43.6%Top
- Gemma 3 12B IT: 10.8%
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- Gemma 4 26B A4B: 65.7%Top
- Gemma 3 12B IT: 8.3%
Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis
- Gemma 4 26B A4B
- Gemma 3 12B IT
| Leaderboard | Gemma 4 26B A4B | Gemma 3 12B IT |
|---|---|---|
| Vision Style Control · Captioning | #5 · 1238.9 | Not in top 20 |
Ranks among Noumen catalog models on LMArena leaderboards. Only top-20 placements are listed.LMArena
Live routing data
Performance and reliability
Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.
- Throughput
- 72.7 tok/s
- Faster than 50% of 251 models
- Time to first token
- 2.9 s
- Quicker than 56% of 251 models
- Prompt cache hits
- 16.9%
- About $0.0832 per 1M input tokens with caching
- Request success (24h)
- 100.0%
- Reliable
Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.
- Healthy (98% or more)
- Degraded (90–98%)
- Down (under 90%)
- No requests
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemma-4-26b-a4b-it",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="google/gemma-4-26b-a4b-it",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)Related models
Other Google models, starting with the same family.