Compare / head-to-head
Claude Fable 5vsClaude Opus 4.5
Claude Fable 5 leads 23 of 25 shared benchmarks. Claude Opus 4.5 is 2x cheaper per token. Claude Fable 5 has the larger context window (1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
23 – 2
Claude Fable 5 leads
Cheaper per token
Claude Opus 4.5
2x cheaper, input + output
Larger context
Claude Fable 5
1M tokens
Providers
Anthropic
same provider
Claude Fable 5
Anthropic · released 2026-06-09
textvision
Claude Opus 4.5
Anthropic · released 2025-11-24
textvision
Quality
Benchmark matrix
25 shared · 19 only Claude Fable 5 · 13 only Claude Opus 4.5| Benchmark | Claude Fable 5 | Claude Opus 4.5 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 25 | ||||
| SWE-bench Verified | 95% ↗ | 80.9% ↗ | +14.1 pt | Claude Fable 5 |
| GPQA Diamond | 85.9% ↗epoch run | 87% ↗ | -1.1 pt | Claude Opus 4.5 |
| LMArena Elo | 1504.3 ↗ | 1473.6 ↗ | +30.7 | Claude Fable 5 |
| Chess Puzzles (Epoch AI run) | 41% ↗epoch run | 12% ↗epoch run | +29 pt | Claude Fable 5 |
| EBR-bench (Epoch AI run) | 39.5% ↗epoch run | 14.3% ↗epoch run | +25.2 pt | Claude Fable 5 |
| FrontierMath Tier 4 v2 (Epoch AI run) | 90.2% ↗epoch run | 4.9% ↗epoch run | +85.3 pt | Claude Fable 5 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 87% ↗epoch run | 34.4% ↗epoch run | +52.6 pt | Claude Fable 5 |
| Furniture Assembly (Epoch AI run) | 35.8% ↗epoch run | 28.3% ↗epoch run | +7.5 pt | Claude Fable 5 |
| GSO Opt@1 (GSO) | 76.5% ↗ | 24.5% ↗ | +52 pt | Claude Fable 5 |
| LiveBench Agentic Coding (LiveBench) | 62.2% ↗ | 39.7% ↗ | +22.5 pt | Claude Fable 5 |
| LiveBench Coding (LiveBench) | 86% ↗ | 79.7% ↗ | +6.3 pt | Claude Fable 5 |
| LiveBench Data Analysis (LiveBench) | 80.5% ↗ | 74.4% ↗ | +6.1 pt | Claude Fable 5 |
| LiveBench Instruction Following (LiveBench) | 75.8% ↗ | 62.5% ↗ | +13.3 pt | Claude Fable 5 |
| LiveBench Language (LiveBench) | 90.7% ↗ | 81.3% ↗ | +9.4 pt | Claude Fable 5 |
| LiveBench Mathematics (LiveBench) | 96% ↗ | 90.4% ↗ | +5.6 pt | Claude Fable 5 |
| LiveBench Reasoning (LiveBench) | 89.7% ↗ | 80.1% ↗ | +9.6 pt | Claude Fable 5 |
| LMArena WebDev (LMArena) | 1625.3 ↗ | 1493.3 ↗ | +132 | Claude Fable 5 |
| Mystery Game Puzzles (Epoch AI run) | 52% ↗epoch run | 22% ↗epoch run | +30 pt | Claude Fable 5 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 100% ↗epoch run | 86.1% ↗epoch run | +13.9 pt | Claude Fable 5 |
| SAGE (Vals AI) | 51.9% ↗ | 52.1% ↗ | -0.2 pt | Claude Opus 4.5 |
| SimpleBench (SimpleBench) | 81.9% ↗ | 62% ↗ | +19.9 pt | Claude Fable 5 |
| SimpleQA Verified | 70.7% ↗epoch run | 45.7% ↗epoch run | +25 pt | Claude Fable 5 |
| tau2-bench Banking Knowledge (Sierra) | 39.7% ↗ | 24.7% ↗ | +15 pt | Claude Fable 5 |
| Vending-Bench 2 (Andon Labs) | 5680.26 ↗ | 4967.06 ↗ | +713.2 | Claude Fable 5 |
| WeirdML (Håvard Tveit Ihle) | 91.9% ↗ | 63.7% ↗ | +28.2 pt | Claude Fable 5 |
| Only Claude Fable 5 reports · 19 | ||||
| APEX-Agents (Mercor) | 63.6% ↗ | not reported | — | — |
| AutomationBench | 17.4% ↗ | not reported | — | — |
| Blueprint-Bench 2 | 38.6% ↗ | not reported | — | — |
| CursorBench | 72.9% ↗ | not reported | — | — |
| DeepSWE v1.1 (Datacurve) | 69.9% ↗ | not reported | — | — |
| FrontierCode (Diamond) | 29.3% ↗ | not reported | — | — |
| FrontierSWE V2 (Proximal Labs) | 47% ↗ | not reported | — | — |
| GDP.pdf | 29.8% ↗ | not reported | — | — |
| Legal Agent Benchmark (Harvey's Held-Out Set) | 13.3% ↗ | not reported | — | — |
| LMArena Agent (LMArena) | 0.0821 ↗ | not reported | — | — |
| LMArena Vision (LMArena) | 1308.8 ↗ | not reported | — | — |
| MirrorCode (Epoch AI run) | 63.9% ↗epoch run | not reported | — | — |
| OfficeQA Pro | 57.9% ↗ | not reported | — | — |
| OSWorld-Verified | 85% ↗ | not reported | — | — |
| OSWorld-Verified (XLANG) | 86% ↗ | not reported | — | — |
| SWE-Bench Pro | 80% ↗ | not reported | — | — |
| SWE-rebench 2026-05-15 to 2026-07-01 (Nebius) | 64.5% ↗ | not reported | — | — |
| Terminal-Bench 2.1 | 84.3% ↗ | not reported | — | — |
| Terminal-Bench 4.0 (Vals AI) | 41.4% ↗ | not reported | — | — |
| Only Claude Opus 4.5 reports · 13 | ||||
| ARC-AGI-2 (Verified) | not reported | 37.6% ↗ | — | — |
| BALROG (BALROG) | not reported | 43.5% ↗ | — | — |
| MCP Atlas | not reported | 62.3% ↗ | — | — |
| MMMLU | not reported | 90.8% ↗ | — | — |
| MMMU (validation) | not reported | 80.7% ↗ | — | — |
| OSWorld | not reported | 66.3% ↗ | — | — |
| SWE-bench Verified (Epoch AI run) | not reported | 76.7% ↗epoch run | — | — |
| tau2-bench Airline (Sierra) | not reported | 84% ↗ | — | — |
| tau2-bench Retail (Sierra) | not reported | 79.6% ↗ | — | — |
| tau2-bench Telecom (Sierra) | not reported | 92.3% ↗ | — | — |
| Terminal-Bench 2.0 | not reported | 59.3% ↗ | — | — |
| τ2-bench (Retail) | not reported | 88.9% ↗ | — | — |
| τ2-bench (Telecom) | not reported | 98.2% ↗ | — | — |
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 Claude Fable 5 minus Claude Opus 4.5 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 | Claude Opus 4.5 | Edge |
|---|---|---|---|
| Context window | 1M tokens | 200K tokens | Claude Fable 5 |
| Max output | 128K tokens | 64K tokens | Claude Fable 5 |
| Input price / 1M | $10 ↗ | $5 ↗ | Claude Opus 4.5 |
| Output price / 1M | $50 ↗ | $25 ↗ | Claude Opus 4.5 |
| Cached input / 1M | $1 ↗ | $0.5 ↗ | Claude Opus 4.5 |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $60 | $30 | Claude Opus 4.5 |
| Modalities | text · vision | text · vision | Tie |
| Released | 2026-06-09 | 2025-11-24 | — |
| Cited benchmark scores | 44 | 39 | — |
Reliability
Anthropic status
Live from /statusMore matchups
Claude Fable 5 vs …
Models sharing the most benchmarksMore matchups
Claude Opus 4.5 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 Claude Opus 4.5 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.