GLM 5.3 Flash vs Grok 4.7
Compare GLM 5.3 Flash and Grok 4.7 side-by-side.
Compare GLM 5.3 Flash 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
GLM 5.3 Flash vs Grok 4.7 on Vision Evals
Grok 4.7 scores higher on all six Vision Evals tasks.
The widest gap is Reasoning, where Grok 4.7 leads 64.2% to 51.0%.
Overall, GLM 5.3 Flash averages 66.3% (#34 of 54) against 71.9% (#22 of 54) for Grok 4.7.
GLM 5.3 Flash is both cheaper ($0.0005 vs $0.012 per sample) and faster (6.8s vs 23.6s per sample).
GLM 5.3 Flash vs Grok 4.7 Comparison Table
Evals updated September 22, 2026Pricing updated September 22, 2026
| Property | GLM 5.3 Flash | Grok 4.7 |
|---|---|---|
| Organization | Z.ai | SpaceXAI |
| Category | open | closed |
| Modality | multimodal | — |
| Release Date | Aug 2026 | Sep 2026 |
| Context Window | 1.0M | 500K |
| Parameters | 320B total, 18B active | |
| License | MIT | Proprietary |
| Pricing per 1M tokens | ||
| Input $/1M | $0.150 | $1.60 |
| Output $/1M | $0.500 | $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 | 66.3% | 71.9% |
| Avg cost / sample | $0.0005 | $0.012 |
| Avg speed / sample | 6.78s | 23.55s |
| By task | ||
| Object Detection (low) | 33.1% | 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) | 55.4% | 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) | 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) | 90.6% | 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) | 83.5% | 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) | 51.0% | 64.2% ±2.3, Mean of 3 runs, range 62.3 to 66.9 |
| Reasoning (high) | 59.6% | 66.9% ±1.3, Mean of 3 runs, range 65.6 to 68.2 |
GLM 5.3 Flash vs Grok 4.7: Overview
GLM-5.3-Flash is the first natively multimodal model in Z.ai's GLM-5 series, a mixture-of-experts transformer with roughly 320 billion total parameters and 18 billion activated per token. It routes each token through 8 of 288 experts across 45 language layers that interleave KDA linear attention with sparse multi-head latent attention, and pairs them with a 24-layer vision encoder that handles image and video input. The checkpoint declares a maximum context length of 1,048,576 tokens, ships in native FP8, and includes a multi-token prediction draft layer for speculative decoding. Z.ai reports that the hybrid attention design reduces attention computation by 3.01x and KV cache size by 4.44x relative to GLM-5.3.
The model starts from a newly trained base built on a 30 trillion token multimodal pre-training corpus and adopts Manifold-Constrained Hyper-Connections to improve scaling efficiency. Vision is integrated into the coding and agent loop, so the model can inspect interfaces, rendered output, and images while operating across code, browsers, and graphical user interfaces. Z.ai reports scores of 84.3 on Terminal-Bench 2.1, 63.4 on DeepSWE 1.1, 55.3 on Humanity's Last Exam with tools, and 48.8 on AutomationBench, and the model exposes low, high, and max thinking modes.
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 all six vision tasks and averages 71.9% (#22 of 54) against 66.3% (#34 of 54) for GLM 5.3 Flash. These scores measure vision capabilities only; either model may perform differently on work outside this benchmark's tasks.
No. On the Vision Evals Reasoning benchmark at low effort, Grok 4.7 leads with 64.2% against 51.0%. This is the widest gap between the two models across the benchmark's tasks.
GLM 5.3 Flash is cheaper to run. Across Roboflow's Vision Evals task mix it averaged $0.0005 per sample against $0.012. GLM 5.3 Flash is priced at $0.15 per 1M input tokens and $0.50 per 1M output; Grok 4.7 is priced at $1.60 per 1M input tokens and $4.80 per 1M output. Actual costs depend on your image sizes, prompts, and output length.
GLM 5.3 Flash is faster. Across Roboflow's Vision Evals it averaged 6.8s per inference against 23.6s. Latency varies with image size, prompt length, and provider load, so treat these as relative rather than guaranteed figures.