Compare / head-to-head
Claude Fable 5.1vsClaude Opus 4.7
Claude Fable 5.1 leads 5 of 5 shared benchmarks. Claude Opus 4.7 is 2x 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
5 – 0
Claude Fable 5.1 leads
Cheaper per token
Claude Opus 4.7
2x cheaper, input + output
Larger context
Tie
both 1M tokens
Provider uptime (30d)
100%
Anthropic
Claude Fable 5.1
Anthropic · released 2026-09-01
textvision
Claude Opus 4.7
Anthropic · released 2026-04-16
textvision
Quality
Benchmark matrix
5 shared · 3 only Claude Fable 5.1 · 12 only Claude Opus 4.7| Benchmark | Claude Fable 5.1 | Claude Opus 4.7 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 5 | ||||
| Humanity's Last Exam (no tools) | 60.9% ↗ | 46.9% ↗ | +14 pt | Claude Fable 5.1 |
| FrontierMath Tier 4 v2 (Epoch AI run) | 87.8% ↗epoch | 31.7% ↗epoch | +56.1 pt | Claude Fable 5.1 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 90.2% ↗epoch | 70.2% ↗epoch | +20 pt | Claude Fable 5.1 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 100% ↗epoch | 97.8% ↗epoch | +2.2 pt | Claude Fable 5.1 |
| SimpleQA Verified | 70.8% ↗epoch | 51.7% ↗epoch | +19.1 pt | Claude Fable 5.1 |
| Only Claude Fable 5.1 reports · 3 | ||||
| CursorBench 3.2.0 | 73.4% ↗ | not reported | — | — |
| GDPval-AA v2 | 1853 ↗ | not reported | — | — |
| Terminal-Bench Science 0.1 | 52.6% ↗ | not reported | — | — |
| Only Claude Opus 4.7 reports · 12 | ||||
| SWE-bench Verified | not reported | 87.6% ↗ | — | — |
| GPQA Diamond | not reported | 94.2% ↗ | — | — |
| AIME 2026 | not reported | 95.8% ↗matharena ⚠ | — | — |
| LMArena Elo | not reported | 1483.4 ↗ | — | — |
| BrowseComp | not reported | 79.8% ↗ | — | — |
| Humanity's Last Exam (with tools) | not reported | 54.7% ↗ | — | — |
| OSWorld-Verified | not reported | 82.8% ↗ | — | — |
| SWE-bench Multilingual | not reported | 80.5% ↗ | — | — |
| SWE-bench Multimodal | not reported | 34.5% ↗ | — | — |
| SWE-Bench Pro | not reported | 64.3% ↗ | — | — |
| SWE-bench Verified (Epoch AI run) | not reported | 83.5% ↗epoch | — | — |
| Terminal-Bench 2.1 | not reported | 66.1% ↗ | — | — |
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 5.1 minus Claude Opus 4.7 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 5.1 | Claude Opus 4.7 | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1M tokens | Tie |
| Max output | 128K tokens | 128K tokens | Tie |
| Input price / 1M | $10 ↗ | $5 ↗ | Claude Opus 4.7 |
| Output price / 1M | $50 ↗ | $25 ↗ | Claude Opus 4.7 |
| Cached input / 1M | $0.25 ↗ | $0.5 ↗ | Claude Fable 5.1 |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $60 | $30 | Claude Opus 4.7 |
| Modalities | text · vision | text · vision | Tie |
| Released | 2026-09-01 | 2026-04-16 | — |
| Cited benchmark scores | 8 | 18 | — |
Reliability
Anthropic status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Claude Fable 5.1 vs …
Models sharing the most benchmarksMore matchups
Claude Opus 4.7 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Claude Fable 5.1 and Claude Opus 4.7 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.