Compare / head-to-head
GLM-4.1V-9B-ThinkingvsGLM-5V-Turbo
GLM-5V-Turbo leads 3 of 3 shared benchmarks. GLM-5V-Turbo has the larger context window (200K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 3
GLM-5V-Turbo leads
Cheaper per token
—
list price, input + output
Larger context
GLM-5V-Turbo
200K tokens
Providers
Z.ai
same provider
GLM-4.1V-9B-Thinking
Z.ai · released 2025-07-01
textvisionvideo
- Context
- 64K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 13 · 0 core
GLM-5V-Turbo
Z.ai · released 2026-04-02
textvisionvideo
- Context
- 200K
- Max out
- 128K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 18 · 3 core
Quality
Benchmark matrix
3 shared · 10 only GLM-4.1V-9B-Thinking · 15 only GLM-5V-Turbo| Benchmark | GLM-4.1V-9B-Thinking | GLM-5V-Turbo | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 3 | ||||
| AndroidWorld | 41.7% ↗ | 75.7% ↗ | -34 pt | GLM-5V-Turbo |
| Design2Code | 64.7% ↗ | 94.8% ↗ | -30.1 pt | GLM-5V-Turbo |
| OSWorld | 14.9% ↗ | 62.3% ↗ | -47.4 pt | GLM-5V-Turbo |
| Only GLM-4.1V-9B-Thinking reports · 10 | ||||
| ChartQAPro | 59.5% ↗ | not reported | — | — |
| MathVision | 54.4% ↗ | not reported | — | — |
| MathVista | 80.7% ↗ | not reported | — | — |
| MMBench v1.1 | 85.8% ↗ | not reported | — | — |
| MMMU (val) | 68% ↗ | not reported | — | — |
| MMMU Pro | 57.1% ↗ | not reported | — | — |
| MMStar | 72.9% ↗ | not reported | — | — |
| OCRBench | 84.2% ↗ | not reported | — | — |
| VideoMME (w/o sub) | 68.2% ↗ | not reported | — | — |
| VideoMMMU | 61% ↗ | not reported | — | — |
| Only GLM-5V-Turbo reports · 15 | ||||
| LMArena Elo | not reported | 1433.5 ↗ | — | — |
| BrowseComp-VL | not reported | 51.9% ↗ | — | — |
| CC-Backend | not reported | 22.8% ↗ | — | — |
| CC-Frontend | not reported | 68.4% ↗ | — | — |
| CC-Repo-Exploration | not reported | 72.2% ↗ | — | — |
| Flame-VLM-Code | not reported | 93.8% ↗ | — | — |
| ImageMining | not reported | 30.7% ↗ | — | — |
| LMArena Vision (LMArena) | not reported | 1230.1 ↗ | — | — |
| LMArena WebDev (LMArena) | not reported | 1399.8 ↗ | — | — |
| MMSearch | not reported | 72.9% ↗ | — | — |
| MMSearch-Plus | not reported | 30% ↗ | — | — |
| SimpleVQA | not reported | 78.2% ↗ | — | — |
| V* | not reported | 89% ↗ | — | — |
| Vision2Web | not reported | 31% ↗ | — | — |
| WebVoyager | not reported | 88.5% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is GLM-4.1V-9B-Thinking minus GLM-5V-Turbo in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | GLM-4.1V-9B-Thinking | GLM-5V-Turbo | Edge |
|---|---|---|---|
| Context window | 64K tokens | 200K tokens | GLM-5V-Turbo |
| Max output | — | 128K tokens | — |
| Input price / 1M | — | — | — |
| Output price / 1M | — | — | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | — | — |
| Modalities | text · vision · video | text · vision · video | Tie |
| Released | 2025-07-01 | 2026-04-02 | — |
| Cited benchmark scores | 13 | 18 | — |
Reliability
Z.ai status
Live from /statusMore matchups
GLM-4.1V-9B-Thinking vs …
Models sharing the most benchmarksMore matchups
GLM-5V-Turbo vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run GLM-4.1V-9B-Thinking and GLM-5V-Turbo on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.