Compare / head-to-head
Claude Opus 4.5vs
GLM-4.6V-Flash
Claude Opus 4.5 leads 1 of 1 shared benchmark. Claude Opus 4.5 has the larger context window (200K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
1 – 0
Claude Opus 4.5 leads
Cheaper per token
GLM-4.6V-Flash
list price, input + output
Larger context
Claude Opus 4.5
200K tokens
Providers
2 providers
Anthropic · Z.ai
Claude Opus 4.5
Anthropic · released 2025-11-24
textvision
GLM-4.6V-Flash
Z.ai · released 2025-12-08
textvisionvideo
Quality
Benchmark matrix
1 shared · 37 only Claude Opus 4.5 · 14 only GLM-4.6V-Flash| Benchmark | Claude Opus 4.5 | GLM-4.6V-Flash | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 1 | ||||
| OSWorld | 66.3% ↗ | 21.1% ↗ | +45.2 pt | Claude Opus 4.5 |
| Only Claude Opus 4.5 reports · 37 | ||||
| SWE-bench Verified | 80.9% ↗ | not reported | — | — |
| GPQA Diamond | 87% ↗ | not reported | — | — |
| LMArena Elo | 1473.6 ↗ | not reported | — | — |
| ARC-AGI-2 (Verified) | 37.6% ↗ | not reported | — | — |
| BALROG (BALROG) | 43.5% ↗ | not reported | — | — |
| Chess Puzzles (Epoch AI run) | 12% ↗epoch run | not reported | — | — |
| EBR-bench (Epoch AI run) | 14.3% ↗epoch run | not reported | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | 4.9% ↗epoch run | not reported | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 34.4% ↗epoch run | not reported | — | — |
| Furniture Assembly (Epoch AI run) | 28.3% ↗epoch run | not reported | — | — |
| GSO Opt@1 (GSO) | 24.5% ↗ | not reported | — | — |
| LiveBench Agentic Coding (LiveBench) | 39.7% ↗ | not reported | — | — |
| LiveBench Coding (LiveBench) | 79.7% ↗ | not reported | — | — |
| LiveBench Data Analysis (LiveBench) | 74.4% ↗ | not reported | — | — |
| LiveBench Instruction Following (LiveBench) | 62.5% ↗ | not reported | — | — |
| LiveBench Language (LiveBench) | 81.3% ↗ | not reported | — | — |
| LiveBench Mathematics (LiveBench) | 90.4% ↗ | not reported | — | — |
| LiveBench Reasoning (LiveBench) | 80.1% ↗ | not reported | — | — |
| LMArena WebDev (LMArena) | 1493.3 ↗ | not reported | — | — |
| MCP Atlas | 62.3% ↗ | not reported | — | — |
| MMMLU | 90.8% ↗ | not reported | — | — |
| MMMU (validation) | 80.7% ↗ | not reported | — | — |
| Mystery Game Puzzles (Epoch AI run) | 22% ↗epoch run | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 86.1% ↗epoch run | not reported | — | — |
| SAGE (Vals AI) | 52.1% ↗ | not reported | — | — |
| SimpleBench (SimpleBench) | 62% ↗ | not reported | — | — |
| SimpleQA Verified | 45.7% ↗epoch run | not reported | — | — |
| SWE-bench Verified (Epoch AI run) | 76.7% ↗epoch run | not reported | — | — |
| tau2-bench Airline (Sierra) | 84% ↗ | not reported | — | — |
| tau2-bench Banking Knowledge (Sierra) | 24.7% ↗ | not reported | — | — |
| tau2-bench Retail (Sierra) | 79.6% ↗ | not reported | — | — |
| tau2-bench Telecom (Sierra) | 92.3% ↗ | not reported | — | — |
| Terminal-Bench 2.0 | 59.3% ↗ | not reported | — | — |
| Vending-Bench 2 (Andon Labs) | 4967.06 ↗ | not reported | — | — |
| WeirdML (Håvard Tveit Ihle) | 63.7% ↗ | not reported | — | — |
| τ2-bench (Retail) | 88.9% ↗ | not reported | — | — |
| τ2-bench (Telecom) | 98.2% ↗ | not reported | — | — |
| Only GLM-4.6V-Flash reports · 14 | ||||
| AndroidWorld | not reported | 42.7% ↗ | — | — |
| ChartQAPro | not reported | 62.6% ↗ | — | — |
| CharXiv_Val-Reasoning | not reported | 59.6% ↗ | — | — |
| Design2Code | not reported | 69.8% ↗ | — | — |
| MathVista | not reported | 82.7% ↗ | — | — |
| MMBench V1.1 | not reported | 86.9% ↗ | — | — |
| MMBrowseComp | not reported | 7.1% ↗ | — | — |
| MMLongBench-Doc | not reported | 53% ↗ | — | — |
| MMMU (Val) | not reported | 71.1% ↗ | — | — |
| MMMU_Pro | not reported | 60.6% ↗ | — | — |
| MMStar | not reported | 74.7% ↗ | — | — |
| OCRBench | not reported | 84.7% ↗ | — | — |
| VideoMMMU | not reported | 70.1% ↗ | — | — |
| WebVoyager | not reported | 71.8% ↗ | — | — |
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 Claude Opus 4.5 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
Official pricing pages and model cards| Spec | Claude Opus 4.5 | GLM-4.6V-Flash | Edge |
|---|---|---|---|
| Context window | 200K tokens | 128K tokens | Claude Opus 4.5 |
| Max output | 64K tokens | 32K tokens | Claude Opus 4.5 |
| Input price / 1M | $5 ↗ | $0 ↗ | GLM-4.6V-Flash |
| Output price / 1M | $25 ↗ | $0 ↗ | GLM-4.6V-Flash |
| Cached input / 1M | $0.5 ↗ | $0 ↗ | GLM-4.6V-Flash |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $30 | $0 | GLM-4.6V-Flash |
| Modalities | text · vision | text · vision · video | GLM-4.6V-Flash |
| Released | 2025-11-24 | 2025-12-08 | — |
| Cited benchmark scores | 39 | 15 | — |
Reliability
Provider status
Live from /statusMore matchups
Claude Opus 4.5 vs …
Models sharing the most benchmarksMore matchups
GLM-4.6V-Flash vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Claude Opus 4.5 and GLM-4.6V-Flash on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.