Claude Sonnet 5.5 vs Gemini 3.7 Flash
Compare Claude Sonnet 5.5 and Gemini 3.7 Flash side-by-side.
Compare Claude Sonnet 5.5 vs Gemini 3.7 Flash 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
Claude Sonnet 5.5 vs Gemini 3.7 Flash on Vision Evals
Claude Sonnet 5.5 scores higher on 3 of the six Vision Evals tasks.
The widest gap is Data Extraction, where Gemini 3.7 Flash leads 96.2% to 90.7%.
Overall, Claude Sonnet 5.5 averages 83.8% (#7 of 60) against 85.2% (#4 of 60) for Gemini 3.7 Flash.
Gemini 3.7 Flash is cheaper ($0.0031 vs $0.0065 per sample), while Claude Sonnet 5.5 is faster (10.8s vs 16.5s per sample).
Claude Sonnet 5.5 vs Gemini 3.7 Flash Comparison Table
Evals updated September 28, 2026Pricing updated September 28, 2026
| Property | Claude Sonnet 5.5 | Gemini 3.7 Flash |
|---|---|---|
| Organization | Anthropic | |
| Category | closed | closed |
| Modality | multimodal | multimodal |
| Release Date | Sep 2026 | Aug 2026 |
| Context Window | 1.0M | 1.0M |
| Parameters | Undisclosed | |
| License | Proprietary | Proprietary |
| Pricing per 1M tokens | ||
| Input $/1M | $0.750 | |
| Output $/1M | $3.75 | |
| 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 | 83.8% | 85.2% |
| Avg cost / sample | $0.0065 | $0.0031 |
| Avg speed / sample | 10.78s | 16.50s |
| By task | ||
| Object Detection (low) | 74.3% ±0.9, Mean of 3 runs, range 73.5 to 75.3 | 70.5% ±1.1, Mean of 3 runs, range 69.4 to 71.5 |
| Object Detection (high) | 76.8% ±0.4, Mean of 3 runs, range 76.5 to 77.3 | 74.3% ±0.8, Mean of 3 runs, range 73.3 to 75.0 |
| Counting (low) | 79.3% ±0.7, Mean of 3 runs, range 78.4 to 79.7 | 78.4% ±1.4, Mean of 3 runs, range 77.0 to 79.7 |
| Counting (high) | 82.9% ±1.4, Mean of 3 runs, range 81.1 to 83.8 | 79.3% ±2.0, Mean of 3 runs, range 77.0 to 81.1 |
| Identification (low) | 91.7% ±3.1, Mean of 3 runs, range 87.5 to 93.8 | 96.9% ±0.0, Mean of 3 runs, range 96.9 to 96.9 |
| Identification (high) | 90.6% ±0.0, Mean of 3 runs, range 90.6 to 90.6 | 96.9% ±0.0, Mean of 3 runs, range 96.9 to 96.9 |
| OCR (low) | 90.6% ±0.9, Mean of 3 runs, range 90.0 to 91.7 | 88.2% ±1.6, Mean of 3 runs, range 86.9 to 90.0 |
| OCR (high) | 90.9% ±1.5, Mean of 3 runs, range 89.2 to 92.3 | 89.0% ±0.8, Mean of 3 runs, range 88.3 to 89.9 |
| Data Extraction (low) | 90.7% ±1.5, Mean of 3 runs, range 89.7 to 92.8 | 96.2% ±0.5, Mean of 3 runs, range 95.9 to 96.9 |
| Data Extraction (high) | 93.1% ±0.5, Mean of 3 runs, range 92.8 to 93.8 | 95.9% ±0.0, Mean of 3 runs, range 95.9 to 95.9 |
| Reasoning (low) | 76.4% ±0.7, Mean of 3 runs, range 75.5 to 76.8 | 80.8% ±2.0, Mean of 3 runs, range 78.8 to 82.8 |
| Reasoning (high) | 83.9% ±1.7, Mean of 3 runs, range 82.1 to 85.4 | 81.9% ±1.3, Mean of 3 runs, range 80.1 to 82.8 |
Claude Sonnet 5.5 vs Gemini 3.7 Flash: Overview
Claude Sonnet 5.5 is a proprietary multimodal language model from Anthropic and the second release in the Claude 5.5 family, following Claude Opus 5.5. It accepts interleaved text and image input and returns text, operating with a 1M token context window and a maximum output of 128K tokens per request. The model uses adaptive thinking by default, allocating variable reasoning effort per request rather than exposing a manual extended thinking toggle, and its training data cutoff is June 2026. Anthropic positions it as a faster, lower cost complement to Opus 5.5 for well scoped everyday tasks, bug fixing, and producing documents, slides, and spreadsheets.
On visual and agentic evaluations reported at launch, Sonnet 5.5 scores 61.6% on Chartography, a chart recognition test, compared with 15.6% for Claude Sonnet 5, and 80.1% on OSWorld 2.1, a computer use benchmark measuring screenshot driven control of a desktop environment, compared with 57.0% for Sonnet 5. It reports 70.6% on Terminal-Bench 4.0 for agentic coding. Anthropic describes it as the first Sonnet model able to complete Pokemon Red from screenshots alone, and it generates output more than 30% faster than Sonnet 5 while using fewer tokens for equivalent work.
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.
Frequently Asked Questions
On Roboflow's Vision Evals, Gemini 3.7 Flash performed slightly better overall. The two split the six vision tasks 3 to 3, but Gemini 3.7 Flash averages 85.2% (#4 of 60) against 83.8% (#7 of 60) for Claude Sonnet 5.5. These scores measure vision capabilities only; either model may perform differently on work outside this benchmark's tasks.
No. On the Vision Evals Data Extraction benchmark at low effort, Gemini 3.7 Flash leads with 96.2% against 90.7%. This is the widest gap between the two models across the benchmark's tasks.
Gemini 3.7 Flash is cheaper to run. Across Roboflow's Vision Evals task mix it averaged $0.0031 per sample against $0.0065. Actual costs depend on your image sizes, prompts, and output length.
Claude Sonnet 5.5 is faster. Across Roboflow's Vision Evals it averaged 10.8s per inference against 16.5s. Latency varies with image size, prompt length, and provider load, so treat these as relative rather than guaranteed figures.