Compare / head-to-head
GLM-4.1V-9B-Thinkingvs
Phi-4-Reasoning-Vision-15B
GLM-4.1V-9B-Thinking leads 2 of 2 shared benchmarks. GLM-4.1V-9B-Thinking has the larger context window (64K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
2 – 0
GLM-4.1V-9B-Thinking leads
Cheaper per token
—
list price, input + output
Larger context
GLM-4.1V-9B-Thinking
64K tokens
Providers
2 providers
Z.ai · Microsoft
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
Phi-4-Reasoning-Vision-15B
Microsoft · released 2026-03-04
textvision
- Context
- 16K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 10 · 0 core
Quality
Benchmark matrix
2 shared · 11 only GLM-4.1V-9B-Thinking · 8 only Phi-4-Reasoning-Vision-15B| Benchmark | GLM-4.1V-9B-Thinking | Phi-4-Reasoning-Vision-15B | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 2 | ||||
| MMStar | 72.9% ↗ | 64.5% ↗ | +8.4 pt | GLM-4.1V-9B-Thinking |
| OCRBench | 84.2% ↗ | 76% ↗ | +8.2 pt | GLM-4.1V-9B-Thinking |
| Only GLM-4.1V-9B-Thinking reports · 11 | ||||
| AndroidWorld | 41.7% ↗ | not reported | — | — |
| ChartQAPro | 59.5% ↗ | not reported | — | — |
| Design2Code | 64.7% ↗ | 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 | — | — |
| OSWorld | 14.9% ↗ | not reported | — | — |
| VideoMME (w/o sub) | 68.2% ↗ | not reported | — | — |
| VideoMMMU | 61% ↗ | not reported | — | — |
| Only Phi-4-Reasoning-Vision-15B reports · 8 | ||||
| AI2D_TEST | not reported | 84.8% ↗ | — | — |
| ChartQA_TEST | not reported | 83.3% ↗ | — | — |
| HallusionBench | not reported | 64.4% ↗ | — | — |
| MathVerse_MINI | not reported | 44.9% ↗ | — | — |
| MathVision_MINI | not reported | 36.2% ↗ | — | — |
| MathVista_MINI | not reported | 75.2% ↗ | — | — |
| MMMU_VAL | not reported | 54.3% ↗ | — | — |
| ScreenSpot_v2 | not reported | 88.2% ↗ | — | — |
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 Phi-4-Reasoning-Vision-15B 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 | Phi-4-Reasoning-Vision-15B | Edge |
|---|---|---|---|
| Context window | 64K tokens | 16K tokens | GLM-4.1V-9B-Thinking |
| Max output | — | — | — |
| 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 | GLM-4.1V-9B-Thinking |
| Released | 2025-07-01 | 2026-03-04 | — |
| Cited benchmark scores | 13 | 10 | — |
Reliability
Provider status
Live from /statusMore matchups
GLM-4.1V-9B-Thinking vs …
Models sharing the most benchmarksMore matchups
Phi-4-Reasoning-Vision-15B 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 Phi-4-Reasoning-Vision-15B on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.