ModelsIndexCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

GLM-4.6VvsGLM-4.6V-Flash

GLM-4.6V leads 15 of 15 shared benchmarks. Both offer a 128K-token context window.

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
15 – 0
GLM-4.6V leads
Cheaper per token
GLM-4.6V-Flash
list price, input + output
Larger context
Tie
both 128K tokens
Providers
Z.ai
same provider
GLM-4.6V
Z.ai · released 2025-12-08
textvisionvideo
Context
128K
Max out
32K
Input /1M
$0.3 ↗
Output /1M
$0.9 ↗
Cached /1M
$0.05
Scores
17 · 2 core
GLM-4.6V-Flash
Z.ai · released 2025-12-08
textvisionvideo
Context
128K
Max out
32K
Input /1M
$0 ↗
Output /1M
$0 ↗
Cached /1M
$0
Scores
15 · 0 core
Quality

Benchmark matrix

BenchmarkGLM-4.6VGLM-4.6V-FlashΔEdge
Reported by both · 15
AndroidWorld57% ↗42.7% ↗+14.3 ptGLM-4.6V
ChartQAPro65.5% ↗62.6% ↗+2.9 ptGLM-4.6V
CharXiv_Val-Reasoning63.2% ↗59.6% ↗+3.6 ptGLM-4.6V
Design2Code88.6% ↗69.8% ↗+18.8 ptGLM-4.6V
MathVista85.2% ↗82.7% ↗+2.5 ptGLM-4.6V
MMBench V1.188.8% ↗86.9% ↗+1.9 ptGLM-4.6V
MMBrowseComp7.6% ↗7.1% ↗+0.5 ptGLM-4.6V
MMLongBench-Doc54.9% ↗53% ↗+1.9 ptGLM-4.6V
MMMU (Val)76% ↗71.1% ↗+4.9 ptGLM-4.6V
MMMU_Pro66% ↗60.6% ↗+5.4 ptGLM-4.6V
MMStar75.9% ↗74.7% ↗+1.2 ptGLM-4.6V
OCRBench86.5% ↗84.7% ↗+1.8 ptGLM-4.6V
OSWorld37.2% ↗21.1% ↗+16.1 ptGLM-4.6V
VideoMMMU74.7% ↗70.1% ↗+4.6 ptGLM-4.6V
WebVoyager81% ↗71.8% ↗+9.2 ptGLM-4.6V
Only GLM-4.6V reports · 2
LMArena Elo1378.7 ↗not reported——
LMArena Vision (LMArena)1161.5 ↗not reported——
Only GLM-4.6V-Flash reports · 0
GLM-4.6V-Flash reports nothing GLM-4.6V does not.
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-4.6V minus GLM-4.6V-Flash 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

SpecGLM-4.6VGLM-4.6V-FlashEdge
Context window128K tokens128K tokensTie
Max output32K tokens32K tokensTie
Input price / 1M$0.3 ↗$0 ↗GLM-4.6V-Flash
Output price / 1M$0.9 ↗$0 ↗GLM-4.6V-Flash
Cached input / 1M$0.05 ↗$0 ↗GLM-4.6V-Flash
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$1.2$0GLM-4.6V-Flash
Modalitiestext · vision · videotext · vision · videoTie
Released2025-12-082025-12-08—
Cited benchmark scores1715—
Reliability

Z.ai status

All providers →
Z.ai
loading…
More matchups

GLM-4.6V vs …

vs GLM-4.5Vvs GLM-4.1V-9B-Thinkingvs GLM-5V-Turbovs Qwen3-VL 235B-A22B Thinkingvs Kimi K2.5vs Qwen3-VL 235B-A22B Instruct
More matchups

GLM-4.6V-Flash vs …

vs GLM-4.5Vvs GLM-4.1V-9B-Thinkingvs GLM-5V-Turbovs Qwen3-VL 235B-A22B Thinkingvs Phi-4-Reasoning-Vision-15Bvs Claude Opus 4.5
Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run GLM-4.6V and GLM-4.6V-Flash on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.

Learn about Respan ↗