Google model product
Gemma 4 26B A4B
8 billion activated parameters per token, with a 256K context window.
Updated Aug 12, 2026. Default version: Gemma 4 26B-A4B
LLMBoard score52.6Gemma 4 26B-A4B
Coverage80%12 benchmark families
Context window262.1KTokens
Official input priceN/AOfficial price unavailable
Gemma 4 26B A4B Specifications
Technical details for the model's default version.
- Version
- Gemma 4 26B-A4B
- Released
- Apr 2, 2026
- Knowledge cutoff
- Jan 1, 2025
- Parameters
- 25.2B
- Context window
- 262.1K
- Max output
- 32.8K
- Inputs
- image, text
- Outputs
- text
- Open weights
- Yes
- License
- Apache 2.0
Gemma 4 26B A4B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Gemma 4 26B A4B Benchmark Results
Benchmark scores for Gemma 4 26B-A4B.
| BIG-Bench Extra Hard | 64.8% | 02 | 11 | 90.0% | C | |
| MedXpertQA | 58.1% | 06 | 12 | 54.5% | C | |
| t2-bench | 85.5% | 06 | 23 | 77.3% | C | |
| MRCR v2 (8-needle) | 44.1% | 08 | 21 | 65.0% | C | |
| MathVision | 82.4% | 12 | 32 | 64.5% | C | |
| AIME 2026 | 88.3% | 13 | 18 | 29.4% | C | |
| LiveCodeBench v6 | 77.1% | 23 | 53 | 57.7% | C | |
| MMMLU | 86.3% | 24 | 49 | 52.1% | C | |
| MMLU-Pro | 82.6% | 34 | 129 | 74.2% | C | |
| MMMU-Pro | 73.8% | 36 | 66 | 46.1% | C | |
| Humanity's Last Exam | 17.2% | 65 | 93 | 30.4% | C | |
| GPQA | 82.3% | 74 | 234 | 68.7% | C |
Gemma 4 26B A4B Arena Results
Preference and agent-evaluation results for the default version.
| vision | overall | 41 | 1257.8 | 22,246 | N/A | |
| vision style control | overall | 48 | 1239.6 | 22,246 | N/A | |
| text factuality | overall | 63 | 1445.2 | 5,809 | N/A | |
| text | overall | 72 | 1434.6 | 5,811 | N/A | |
| webdev | overall | 74 | 1361.6 | 1,442 | N/A | |
| text style control | overall | 78 | 1438.3 | 5,811 | N/A |
Gemma 4 26B A4B Runtime Performance
Provider-specific output speed and catalog latency for Gemma 4 26B-A4B. Runtime does not affect the capability score.
| Novita | 5.881 tok/s | 8.09 s | 262.1K | 131.1K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Gemma 4 26B A4B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.05 input, $0.29 output per 1M via EmpirioLabs AI
- Tracked offerings
- 17
| EmpirioLabs AI | gemma-4-26b-a4b | global | $0.05 | $0.29 | 262.1K | |
| OrcaRouter | google/gemma-4-26b-a4b-it | global | $0.06 | $0.33 | 262.1K | |
| LLM Gateway | gemma-4-26b-a4b-it | global | $0.07 | $0.34 | 262.1K | |
| Kilo Gateway | google/gemma-4-26b-a4b-it | global | $0.07 | $0.34 | 262.1K | |
| Deep Infra | google/gemma-4-26B-A4B-it | global | $0.07 | $0.34 | 262.1K | |
| Cortecs | gemma-4-26b-a4b-it | global | $0.111 | $0.557 | 262K | |
| Charm Hyper | gemma-4-26b-a4b-it | global | $0.116 | $0.408 | 256K | |
| SiliconFlow | google/gemma-4-26B-A4B-it | global | $0.12 | $0.40 | 262.1K | |
| OpenRouter | google/gemma-4-26b-a4b-it | global | $0.12 | $0.40 | 262.1K | |
| NanoGPT | google/gemma-4-26b-a4b-it | global | $0.13 | $0.40 | 262.1K | |
| Merge Gateway | google/gemma-4-26b-a4b-it | global | $0.13 | $0.40 | 262.1K | |
| NovitaAI | google/gemma-4-26b-a4b-it | global | $0.13 | $0.40 | 262.1K | |
| Hugging Face | google/gemma-4-26B-A4B-it | global | $0.13 | $0.40 | 262.1K | |
| evroc | google/gemma-4-26B-A4B-it | global | $0.144 | $0.575 | 262.1K | |
| Vercel AI Gateway | google/gemma-4-26b-a4b-it | global | $0.15 | $0.60 | 262.1K | |
| Scaleway | gemma-4-26b-a4b-it | global | $0.25 | $0.50 | 256K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Gemma 4 26B A4B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Gemma 4 26B-A4B | 52.6 | 25.2B | 262.1K | 32.8K | Yes | Apache 2.0 |
What is Gemma 4 26B A4B?
Key information about Gemma 4 26B A4B and its available data.
8 billion activated parameters per token, with a 256K context window. Ranks #6 among open models on Arena AI, outcompeting models 20x its size. Achieves an estimated LMArena text score of 1441. Supports image and text inputs.
Data as of 2026-08-11.
Gemma 4 26B A4B vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Gemma 4 26B A4B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
GO
Google
Gemini 3.1 Flash Lite
GOGoogle
Gemini 2.5 Pro
GOGoogle
Gemini 3.5 Flash Lite
GOGoogle
Gemma 4 31B
GOGoogle
Gemini 3 Flash
GOGoogle
Gemma 4 12B
FAQ
Common questions about Gemma 4 26B A4B.
When was Gemma 4 26B A4B released?
Gemma 4 26B A4B's default version was released on Apr 2, 2026.
How much does Gemma 4 26B A4B cost?
No official standard PAYG price is currently available for Gemma 4 26B A4B. The lowest tracked third-party offer starts at $0.05 input and $0.29 output via EmpirioLabs AI.
Who created Gemma 4 26B A4B?
Gemma 4 26B A4B was created by Google.
What is the context window for Gemma 4 26B A4B?
The default version has a 262.1K token context window.
Is Gemma 4 26B A4B open weight?
Yes. The default version is marked as open weight under Apache 2.0.
How many API providers offer Gemma 4 26B A4B?
17 provider offerings are linked to the default version.
What models should I compare Gemma 4 26B A4B with?
Nearby ranked alternatives include MiniMax M2.1, Seed 2.0 Lite, MiMo V2 Omni.