Gemma 4 26B A4B vs Grok 4.7
Compare Gemma 4 26B A4B and Grok 4.7 side-by-side.
Compare Gemma 4 26B A4B vs Grok 4.7 live
Run the same image across every model that supports a task and compare their outputs side-by-side.
These models don't share enough common tasks for a side-by-side demo. See the comparison table below for their capabilities.
Models in this comparison
Gemma 4 26B A4B vs Grok 4.7 on Vision Evals
Grok 4.7 scores higher on 5 of the six Vision Evals tasks.
The widest gap is Counting, where Grok 4.7 leads 61.7% to 43.2%.
Overall, Gemma 4 26B A4B averages 63.6% (#43 of 54) against 71.9% (#22 of 54) for Grok 4.7.
Gemma 4 26B A4B is cheaper ($0.0019 vs $0.012 per sample), while Grok 4.7 is faster (23.6s vs 27.8s per sample).
Gemma 4 26B A4B vs Grok 4.7 Comparison Table
Evals updated September 22, 2026Pricing updated September 22, 2026
| Property | Gemma 4 26B A4B | Grok 4.7 |
|---|---|---|
| Organization | SpaceXAI | |
| Category | open | closed |
| Modality | multimodal | — |
| Release Date | Apr 2026 | Sep 2026 |
| Context Window | 256K | 500K |
| Parameters | 25.2B | |
| License | Apache 2.0 | Proprietary |
| Pricing per 1M tokens | ||
| Input $/1M | $0.090 | $1.60 |
| Output $/1M | $0.300 | $4.80 |
| Vision Tasks | ||
| Captioning | Demo | |
| Chart Question Answering | ||
| Classification | Demo | |
| Document Question Answering | ||
| Image Tagging | ||
| Multi-Label Classification | ||
| Object Detection | Demo | |
| OCR | Demo | |
| Vision Language | ||
| Visual Question Answering | Demo | |
| Model Features | ||
| Foundation Vision | ||
| LLMs with Vision Capabilities | ||
| Multimodal Vision | ||
Vision Evalsground-truth scores across 6 vision tasks, pooled at low effort | ||
| Overall | 63.6% | 71.9% |
| Quantizationsself-hosted | ||
| Avg cost / sample | $0.0019 | $0.012 |
| Avg speed / sample | 27.84s | 23.55s |
| By task | ||
| Object Detection (low) | 44.2% ±0.7, Mean of 3 runs, range 43.5 to 44.8 | 40.4% ±0.6, Mean of 3 runs, range 39.8 to 41.0 |
| Object Detection (high) | – | 41.2% ±1.6, Mean of 3 runs, range 39.6 to 42.8 |
| Counting (low) | 43.2% ±2.0, Mean of 3 runs, range 41.9 to 46.0 | 61.7% ±1.3, Mean of 3 runs, range 60.8 to 63.5 |
| Counting (high) | – | 60.8% ±1.3, Mean of 3 runs, range 59.5 to 62.2 |
| Identification (low) | 81.3% ±3.1, Mean of 3 runs, range 78.1 to 84.4 | 87.5% ±3.1, Mean of 3 runs, range 84.4 to 90.6 |
| Identification (high) | – | 80.2% ±1.6, Mean of 3 runs, range 78.1 to 81.3 |
| OCR (low) | 88.7% ±1.3, Mean of 3 runs, range 87.6 to 90.2 | 92.6% ±0.7, Mean of 3 runs, range 92.1 to 93.4 |
| OCR (high) | – | 93.5% ±0.3, Mean of 3 runs, range 93.1 to 93.8 |
| Data Extraction (low) | 76.6% ±0.5, Mean of 3 runs, range 76.3 to 77.3 | 84.9% ±2.6, Mean of 3 runs, range 82.5 to 87.6 |
| Data Extraction (high) | – | 87.6% ±1.5, Mean of 3 runs, range 86.6 to 89.7 |
| Reasoning (low) | 47.7% ±2.0, Mean of 3 runs, range 45.0 to 49.0 | 64.2% ±2.3, Mean of 3 runs, range 62.3 to 66.9 |
| Reasoning (high) | – | 66.9% ±1.3, Mean of 3 runs, range 65.6 to 68.2 |
Gemma 4 26B A4B vs Grok 4.7: Overview
Gemma 4 26B A4B is the Mixture-of-Experts variant in Google's Gemma 4 family, with 25.2B total parameters but only 3.8B active per token. Built from the same Gemini 3 research as the 31B dense sibling and released as open weights under the Apache 2.0 license, it supports a 256K token context window with text and image input and configurable thinking mode. The "A4B" in the name refers to its approximately 4B active parameters. The MoE design makes it significantly faster at inference than the dense 31B, running nearly as fast as a 4B-parameter model while delivering roughly 97% of the dense model's quality.
For vision tasks, the 26B A4B shares the same multimodal capabilities as the 31B image understanding with variable aspect ratios and resolutions, and structured bounding box output for UI element detection. The tradeoff versus the 31B dense model is a small quality reduction in exchange for much faster inference and lower hardware requirements, fitting in 18GB of VRAM at 4-bit quantization. It ranked #6 among open models on the Arena AI text leaderboard at launch.
Grok 4.7 is a proprietary model from SpaceXAI, released on September 21, 2026. It accepts text and images as input and returns text. It extends Grok 4.6 and is listed at the same API price.
Its Vision Evals scores are on the leaderboard. Running it in the Playground is not available yet, because the inference workflow is not ready.
Frequently Asked Questions
On Roboflow's Vision Evals, Grok 4.7 performed better. It scores higher on 5 of the six vision tasks and averages 71.9% (#22 of 54) against 63.6% (#43 of 54) for Gemma 4 26B A4B. These scores measure vision capabilities only; either model may perform differently on work outside this benchmark's tasks.
No. On the Vision Evals Counting benchmark at low effort, Grok 4.7 leads with 61.7% against 43.2%. This is the widest gap between the two models across the benchmark's tasks.
Gemma 4 26B A4B is cheaper to run. Across Roboflow's Vision Evals task mix it averaged $0.0019 per sample against $0.012. Actual costs depend on your image sizes, prompts, and output length.
Grok 4.7 is faster. Across Roboflow's Vision Evals it averaged 23.6s per inference against 27.8s. Latency varies with image size, prompt length, and provider load, so treat these as relative rather than guaranteed figures.