Compare / head-to-head
GLM-4.1V-9B-ThinkingvsGLM-4.6V
GLM-4.6V leads 8 of 8 shared benchmarks. GLM-4.6V has the larger context window (128K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 8
GLM-4.6V leads
Cheaper per token
—
list price, input + output
Larger context
GLM-4.6V
128K 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
Quality
Benchmark matrix
8 shared · 5 only GLM-4.1V-9B-Thinking · 9 only GLM-4.6V| Benchmark | GLM-4.1V-9B-Thinking | GLM-4.6V | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 8 | ||||
| AndroidWorld | 41.7% ↗ | 57% ↗ | -15.3 pt | GLM-4.6V |
| ChartQAPro | 59.5% ↗ | 65.5% ↗ | -6 pt | GLM-4.6V |
| Design2Code | 64.7% ↗ | 88.6% ↗ | -23.9 pt | GLM-4.6V |
| MathVista | 80.7% ↗ | 85.2% ↗ | -4.5 pt | GLM-4.6V |
| MMStar | 72.9% ↗ | 75.9% ↗ | -3 pt | GLM-4.6V |
| OCRBench | 84.2% ↗ | 86.5% ↗ | -2.3 pt | GLM-4.6V |
| OSWorld | 14.9% ↗ | 37.2% ↗ | -22.3 pt | GLM-4.6V |
| VideoMMMU | 61% ↗ | 74.7% ↗ | -13.7 pt | GLM-4.6V |
| Only GLM-4.1V-9B-Thinking reports · 5 | ||||
| MathVision | 54.4% ↗ | not reported | — | — |
| MMBench v1.1 | 85.8% ↗ | not reported | — | — |
| MMMU (val) | 68% ↗ | not reported | — | — |
| MMMU Pro | 57.1% ↗ | not reported | — | — |
| VideoMME (w/o sub) | 68.2% ↗ | not reported | — | — |
| Only GLM-4.6V reports · 9 | ||||
| LMArena Elo | not reported | 1378.7 ↗ | — | — |
| CharXiv_Val-Reasoning | not reported | 63.2% ↗ | — | — |
| LMArena Vision (LMArena) | not reported | 1161.5 ↗ | — | — |
| MMBench V1.1 | not reported | 88.8% ↗ | — | — |
| MMBrowseComp | not reported | 7.6% ↗ | — | — |
| MMLongBench-Doc | not reported | 54.9% ↗ | — | — |
| MMMU (Val) | not reported | 76% ↗ | — | — |
| MMMU_Pro | not reported | 66% ↗ | — | — |
| WebVoyager | not reported | 81% ↗ | — | — |
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-4.6V 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-4.6V | Edge |
|---|---|---|---|
| Context window | 64K tokens | 128K tokens | GLM-4.6V |
| Max output | — | 32K tokens | — |
| Input price / 1M | — | $0.3 ↗ | — |
| Output price / 1M | — | $0.9 ↗ | — |
| Cached input / 1M | — | $0.05 ↗ | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | $1.2 | — |
| Modalities | text · vision · video | text · vision · video | Tie |
| Released | 2025-07-01 | 2025-12-08 | — |
| Cited benchmark scores | 13 | 17 | — |
Reliability
Z.ai status
Live from /statusMore matchups
GLM-4.1V-9B-Thinking vs …
Models sharing the most benchmarksMore matchups
GLM-4.6V 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-4.6V on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.