Compare / head-to-head
GLM-4.5Vvs
Phi-4 Multimodal Instruct
GLM-4.5V leads 1 of 1 shared benchmark. Phi-4 Multimodal Instruct has the larger context window (128K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
1 – 0
GLM-4.5V leads
Cheaper per token
—
list price, input + output
Larger context
Phi-4 Multimodal Instruct
128K tokens
Providers
2 providers
Z.ai · Microsoft
GLM-4.5V
Z.ai · released 2025-08-11
textvisionvideo
Phi-4 Multimodal Instruct
Microsoft · released 2025-02-26
textvisionaudio
- Context
- 128K
- Max out
- 4K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 19 · 0 core
Quality
Benchmark matrix
1 shared · 16 only GLM-4.5V · 18 only Phi-4 Multimodal Instruct| Benchmark | GLM-4.5V | Phi-4 Multimodal Instruct | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 1 | ||||
| OCRBench | 86.5% ↗ | 84.4% ↗ | +2.1 pt | GLM-4.5V |
| Only GLM-4.5V reports · 16 | ||||
| LMArena Elo | 1352.4 ↗ | not reported | — | — |
| AndroidWorld | 57% ↗ | not reported | — | — |
| ChartQAPro | 64% ↗ | not reported | — | — |
| Design2Code | 82.2% ↗ | not reported | — | — |
| LMArena Vision (LMArena) | 1152.7 ↗ | not reported | — | — |
| MathVision | 65.6% ↗ | not reported | — | — |
| MathVista | 84.6% ↗ | not reported | — | — |
| MMBench v1.1 | 88.2% ↗ | not reported | — | — |
| MMLongBench-Doc | 44.7% ↗ | not reported | — | — |
| MMMU (val) | 75.4% ↗ | not reported | — | — |
| MMMU Pro | 65.2% ↗ | not reported | — | — |
| MMStar | 75.3% ↗ | not reported | — | — |
| OSWorld | 35.8% ↗ | not reported | — | — |
| VideoMME (w/o sub) | 74.6% ↗ | not reported | — | — |
| VideoMMMU | 72.4% ↗ | not reported | — | — |
| WebVoyagerSom | 84.4% ↗ | not reported | — | — |
| Only Phi-4 Multimodal Instruct reports · 18 | ||||
| AI2D | not reported | 82.3% ↗ | — | — |
| BLINK | not reported | 61.3% ↗ | — | — |
| ChartQA | not reported | 81.4% ↗ | — | — |
| DocVQA | not reported | 93.2% ↗ | — | — |
| InfoVQA | not reported | 72.7% ↗ | — | — |
| InterGPS | not reported | 48.6% ↗ | — | — |
| MathVista testmini | not reported | 62.4% ↗ | — | — |
| MMBench (dev-en) | not reported | 86.7% ↗ | — | — |
| MMMU | not reported | 55.1% ↗ | — | — |
| MMMU-Pro (standard/vision) | not reported | 38.5% ↗ | — | — |
| POPE | not reported | 85.6% ↗ | — | — |
| ScienceQA Visual | not reported | 97.5% ↗ | — | — |
| Speech AI2D | not reported | 68.9% ↗ | — | — |
| Speech ChartQA | not reported | 69% ↗ | — | — |
| Speech DocVQA | not reported | 87.3% ↗ | — | — |
| Speech InfoVQA | not reported | 63.7% ↗ | — | — |
| TextVQA (val) | not reported | 75.6% ↗ | — | — |
| Video-MME (16 frames) | not reported | 55% ↗ | — | — |
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-4.5V minus Phi-4 Multimodal Instruct 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-4.5V | Phi-4 Multimodal Instruct | Edge |
|---|---|---|---|
| Context window | 64K tokens | 128K tokens | Phi-4 Multimodal Instruct |
| Max output | 16K tokens | 4K tokens | GLM-4.5V |
| Input price / 1M | $0.6 ↗ | — | — |
| Output price / 1M | $1.8 ↗ | — | — |
| Cached input / 1M | $0.11 ↗ | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $2.4 | — | — |
| Modalities | text · vision · video | text · vision · audio | Tie |
| Released | 2025-08-11 | 2025-02-26 | — |
| Cited benchmark scores | 17 | 19 | — |
Reliability
Provider status
Live from /statusMore matchups
GLM-4.5V vs …
Models sharing the most benchmarksMore matchups
Phi-4 Multimodal Instruct vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run GLM-4.5V and Phi-4 Multimodal Instruct on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.