Gemini 3.7 Flash vs Gemma 4 31B
Compare Gemini 3.7 Flash and Gemma 4 31B side-by-side. See how these vision models stack up in Image Captioning, Open Prompt, Classification, OCR, and Object Detection.
Compare Gemini 3.7 Flash vs Gemma 4 31B live
Run the same image across every model that supports a task and compare their outputs side-by-side.
Detect and compare bounding boxes across models on the same image.
Upload an image
Drag and drop an image here, or click to browse
Models in this comparison
Gemini 3.7 Flash vs Gemma 4 31B on Vision Evals
Gemini 3.7 Flash scores higher on 5 of the six Vision Evals tasks.
The widest gap is Reasoning, where Gemini 3.7 Flash leads 80.8% to 52.8%.
Overall, Gemini 3.7 Flash averages 85.2% (#6 of 61) against 67.0% (#36 of 61) for Gemma 4 31B.
Gemma 4 31B is cheaper ($0.0015 vs $0.0031 per sample), while Gemini 3.7 Flash is faster (16.5s vs 34.4s per sample).
Gemini 3.7 Flash vs Gemma 4 31B Comparison Table
Evals updated September 29, 2026Pricing updated September 29, 2026
| Property | Gemini 3.7 Flash | Gemma 4 31B |
|---|---|---|
| Organization | ||
| Category | closed | open |
| Modality | multimodal | multimodal |
| Release Date | Aug 2026 | Apr 2026 |
| Context Window | 1.0M | 256K |
| Parameters | Undisclosed | 31B |
| License | Proprietary | Apache 2.0 |
| Pricing per 1M tokens | ||
| Input $/1M | $0.750 | $0.090 |
| Output $/1M | $3.75 | $0.340 |
| Vision Tasks | ||
| Captioning | Demo | Demo |
| Chart Question Answering | ||
| Classification | Demo | Demo |
| Document Question Answering | ||
| Image Tagging | ||
| Multi-Label Classification | ||
| Object Detection | Demo | Demo |
| OCR | Demo | Demo |
| Vision Language | ||
| Visual Question Answering | Demo | Demo |
| Model Features | ||
| Foundation Vision | ||
| LLMs with Vision Capabilities | ||
| Multimodal Vision | ||
Vision Evalsground-truth scores across 6 vision tasks, pooled at low effort | ||
| Overall | 85.2% | 67.0% |
| Quantizationsself-hosted | ||
| Avg cost / sample | $0.0031 | $0.0015 |
| Avg speed / sample | 16.50s | 34.36s |
| By task | ||
| Object Detection (low) | 71.0% ±0.9, Mean of 3 runs, range 69.8 to 71.6 | 47.5% ±0.6, Mean of 3 runs, range 46.8 to 48.0 |
| Object Detection (high) | 74.4% ±0.7, Mean of 3 runs, range 73.6 to 75.0 | – |
| Counting (low) | 78.4% ±1.4, Mean of 3 runs, range 77.0 to 79.7 | 51.4% ±2.7, Mean of 3 runs, range 48.6 to 54.0 |
| Counting (high) | 79.3% ±2.0, Mean of 3 runs, range 77.0 to 81.1 | – |
| Identification (low) | 96.9% ±0.0, Mean of 3 runs, range 96.9 to 96.9 | 79.2% ±1.6, Mean of 3 runs, range 78.1 to 81.3 |
| Identification (high) | 96.9% ±0.0, Mean of 3 runs, range 96.9 to 96.9 | – |
| OCR (low) | 88.2% ±1.6, Mean of 3 runs, range 86.9 to 90.0 | 90.8% ±0.6, Mean of 3 runs, range 90.2 to 91.5 |
| OCR (high) | 89.0% ±0.8, Mean of 3 runs, range 88.3 to 89.9 | – |
| Data Extraction (low) | 96.2% ±0.5, Mean of 3 runs, range 95.9 to 96.9 | 80.4% ±1.0, Mean of 3 runs, range 79.4 to 81.4 |
| Data Extraction (high) | 95.9% ±0.0, Mean of 3 runs, range 95.9 to 95.9 | – |
| Reasoning (low) | 80.8% ±2.0, Mean of 3 runs, range 78.8 to 82.8 | 52.8% ±1.3, Mean of 3 runs, range 51.7 to 54.3 |
| Reasoning (high) | 81.9% ±1.3, Mean of 3 runs, range 80.1 to 82.8 | – |
Gemini 3.7 Flash vs Gemma 4 31B: Overview
Gemini 3.7 Flash is a proprietary multimodal model from Google, positioned in the Flash branch of the Gemini 3 series that trades some of the capacity of the larger Pro models for lower latency and lower cost per token. It accepts interleaved text and image input alongside other modalities handled by the Gemini family and returns text, and it continues the series pattern of exposing a configurable thinking budget so that reasoning effort can be scaled up for harder problems or reduced for high throughput extraction, routing and classification work. The model is announced roughly three weeks after Gemini 3.6 Flash, part of an unusually fast iteration cadence within the Flash line.
Google reports gains concentrated in agentic coding and front end generation, citing a WebDev Arena Elo of 1588 for this release compared with 1538 for the preceding Flash model, and describes it as producing more functional layouts and more feature complete applications in fewer prompts. Weights are not published and the architecture, parameter count and training corpus are undisclosed, consistent with prior Gemini releases. Visual capability follows the Flash lineage, covering image and document understanding, chart and diagram interpretation, text recognition in images, and general visual question answering.
Gemma 4 31B is the largest dense model in Google's Gemma 4 family, built from the same research as Gemini 3 and released as open weights under the Apache 2.0 license. It supports a 256K token context window with text and image input, configurable thinking mode for step-by-step reasoning, and multilingual support across 140+ languages. The unquantized model fits on a single 80GB GPU.
For vision tasks, Gemma 4 31B supports image understanding with variable aspect ratios and resolutions, and can output structured bounding boxes for UI element detection, making it useful for document parsing and UI understanding. Compared to Gemma 3, it delivers stronger reasoning and multimodal performance. It is part of a four-size family alongside the 26B A4B MoE variant and two on-device models (E2B, E4B), with the 31B dense variant optimized for output quality and fine-tuning over inference speed.
Frequently Asked Questions
On Roboflow's Vision Evals, Gemini 3.7 Flash performed better. It scores higher on 5 of the six vision tasks and averages 85.2% (#6 of 61) against 67.0% (#36 of 61) for Gemma 4 31B. These scores measure vision capabilities only; either model may perform differently on work outside this benchmark's tasks.
Yes. On the Vision Evals Reasoning benchmark at low effort, Gemini 3.7 Flash leads with 80.8% against 52.8%. This is the widest gap between the two models across the benchmark's tasks.
Gemma 4 31B is cheaper to run. Across Roboflow's Vision Evals task mix it averaged $0.0015 per sample against $0.0031. Actual costs depend on your image sizes, prompts, and output length.
Gemini 3.7 Flash is faster. Across Roboflow's Vision Evals it averaged 16.5s per inference against 34.4s. Latency varies with image size, prompt length, and provider load, so treat these as relative rather than guaranteed figures.
Yes. The comparison demo on this page runs both models on the same image side by side for image captioning and open prompts in the free Roboflow Playground. You can try it instantly, and a free account unlocks unlimited runs.