Compare / head-to-head
Claude Fable 5vs
GLM-5.3-Flash
Claude Fable 5 leads 19 of 22 shared benchmarks. GLM-5.3-Flash is 92.3x cheaper per token. Both offer a 1M-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
19 – 2
Claude Fable 5 leads · 1 tied
Cheaper per token
GLM-5.3-Flash
92.3x cheaper, input + output
Larger context
Tie
both 1M tokens
Providers
2 providers
Anthropic · Z.ai
Claude Fable 5
Anthropic · released 2026-06-09
textvision
GLM-5.3-Flash
Z.ai · released 2026-08-26
textvision
Quality
Benchmark matrix
22 shared · 22 only Claude Fable 5 · 13 only GLM-5.3-Flash| Benchmark | Claude Fable 5 | GLM-5.3-Flash | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 22 | ||||
| GPQA Diamond | 85.9% ↗epoch run | 90.2% ↗epoch run | -4.3 pt | GLM-5.3-Flash |
| LMArena Elo | 1504.3 ↗ | 1471.9 ↗ | +32.4 | Claude Fable 5 |
| APEX-Agents (Mercor) | 63.6% ↗ | 52.8% ↗ | +10.8 pt | Claude Fable 5 |
| Chess Puzzles (Epoch AI run) | 41% ↗epoch run | 14% ↗epoch run | +27 pt | Claude Fable 5 |
| DeepSWE v1.1 (Datacurve) | 69.9% ↗ | 63.4% ↗ | +6.5 pt | Claude Fable 5 |
| FrontierMath Tier 4 v2 (Epoch AI run) | 90.2% ↗epoch run | 17.1% ↗epoch run | +73.1 pt | Claude Fable 5 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 87% ↗epoch run | 55.8% ↗epoch run | +31.2 pt | Claude Fable 5 |
| FrontierSWE V2 (Proximal Labs) | 47% ↗ | 18.1% ↗ | +28.9 pt | Claude Fable 5 |
| LiveBench Agentic Coding (LiveBench) | 62.2% ↗ | 56.8% ↗ | +5.4 pt | Claude Fable 5 |
| LiveBench Coding (LiveBench) | 86% ↗ | 79% ↗ | +7 pt | Claude Fable 5 |
| LiveBench Data Analysis (LiveBench) | 80.5% ↗ | 76.4% ↗ | +4.1 pt | Claude Fable 5 |
| LiveBench Instruction Following (LiveBench) | 75.8% ↗ | 52.8% ↗ | +23 pt | Claude Fable 5 |
| LiveBench Language (LiveBench) | 90.7% ↗ | 77.3% ↗ | +13.4 pt | Claude Fable 5 |
| LiveBench Mathematics (LiveBench) | 96% ↗ | 81.2% ↗ | +14.8 pt | Claude Fable 5 |
| LiveBench Reasoning (LiveBench) | 89.7% ↗ | 77.6% ↗ | +12.1 pt | Claude Fable 5 |
| LMArena Agent (LMArena) | 0.0821 ↗ | -0.0044 ↗ | +0.1 | Claude Fable 5 |
| LMArena Vision (LMArena) | 1308.8 ↗ | 1278.4 ↗ | +30.4 | Claude Fable 5 |
| LMArena WebDev (LMArena) | 1625.3 ↗ | 1615.6 ↗ | +9.7 | Claude Fable 5 |
| Mystery Game Puzzles (Epoch AI run) | 52% ↗epoch run | 8% ↗epoch run | +44 pt | Claude Fable 5 |
| OfficeQA Pro | 57.9% ↗ | 62.4% ↗ | -4.5 pt | GLM-5.3-Flash |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 100% ↗epoch run | 93.9% ↗epoch run | +6.1 pt | Claude Fable 5 |
| Terminal-Bench 2.1 | 84.3% ↗ | 84.3% ↗ | 0 | Tie |
| Only Claude Fable 5 reports · 22 | ||||
| SWE-bench Verified | 95% ↗ | not reported | — | — |
| AutomationBench | 17.4% ↗ | not reported | — | — |
| Blueprint-Bench 2 | 38.6% ↗ | not reported | — | — |
| CursorBench | 72.9% ↗ | not reported | — | — |
| EBR-bench (Epoch AI run) | 39.5% ↗epoch run | not reported | — | — |
| FrontierCode (Diamond) | 29.3% ↗ | not reported | — | — |
| Furniture Assembly (Epoch AI run) | 35.8% ↗epoch run | not reported | — | — |
| GDP.pdf | 29.8% ↗ | not reported | — | — |
| GSO Opt@1 (GSO) | 76.5% ↗ | not reported | — | — |
| Legal Agent Benchmark (Harvey's Held-Out Set) | 13.3% ↗ | not reported | — | — |
| MirrorCode (Epoch AI run) | 63.9% ↗epoch run | not reported | — | — |
| OSWorld-Verified | 85% ↗ | not reported | — | — |
| OSWorld-Verified (XLANG) | 86% ↗ | not reported | — | — |
| SAGE (Vals AI) | 51.9% ↗ | not reported | — | — |
| SimpleBench (SimpleBench) | 81.9% ↗ | not reported | — | — |
| SimpleQA Verified | 70.7% ↗epoch run | not reported | — | — |
| SWE-Bench Pro | 80% ↗ | not reported | — | — |
| SWE-rebench 2026-05-15 to 2026-07-01 (Nebius) | 64.5% ↗ | not reported | — | — |
| tau2-bench Banking Knowledge (Sierra) | 39.7% ↗ | not reported | — | — |
| Terminal-Bench 4.0 (Vals AI) | 41.4% ↗ | not reported | — | — |
| Vending-Bench 2 (Andon Labs) | 5680.26 ↗ | not reported | — | — |
| WeirdML (Håvard Tveit Ihle) | 91.9% ↗ | not reported | — | — |
| Only GLM-5.3-Flash reports · 13 | ||||
| Agents' Last Exam (ALE-CLI) | not reported | 26.3% ↗ | — | — |
| AutomationBench v1.0.6 | not reported | 48.8% ↗ | — | — |
| BabyVision | not reported | 53.4% ↗ | — | — |
| Chartography (with tools) | not reported | 78% ↗ | — | — |
| CharXiv Reasoning (with tools) | not reported | 89.4% ↗ | — | — |
| DeepSWE v1.1 | not reported | 63.4% ↗ | — | — |
| GDPval-AA v2 | not reported | 1773 ↗ | — | — |
| HLE (with tools) | not reported | 55.3% ↗ | — | — |
| MMVU | not reported | 80.5% ↗ | — | — |
| MVBench | not reported | 77.8% ↗ | — | — |
| NL2Repo | not reported | 56.3% ↗ | — | — |
| Toolathlon Verified | not reported | 78.4% ↗ | — | — |
| Toolathlon-Verified (HKUST) | not reported | 78.4% ↗ | — | — |
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 Fable 5 minus GLM-5.3-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 Fable 5 | GLM-5.3-Flash | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1M tokens | Tie |
| Max output | 128K tokens | 131K tokens | GLM-5.3-Flash |
| Input price / 1M | $10 ↗ | $0.15 ↗ | GLM-5.3-Flash |
| Output price / 1M | $50 ↗ | $0.5 ↗ | GLM-5.3-Flash |
| Cached input / 1M | $1 ↗ | $0.03 ↗ | GLM-5.3-Flash |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $60 | $0.65 | GLM-5.3-Flash |
| Modalities | text · vision | text · vision | Tie |
| Released | 2026-06-09 | 2026-08-26 | — |
| Cited benchmark scores | 44 | 40 | — |
Reliability
Provider status
Live from /statusMore matchups
Claude Fable 5 vs …
Models sharing the most benchmarksMore matchups
GLM-5.3-Flash vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Claude Fable 5 and GLM-5.3-Flash on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.