Compare / head-to-head
Claude Fable 5vs
Inkling
Claude Fable 5 leads 23 of 24 shared benchmarks. Inkling is 11.9x 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
23 – 1
Claude Fable 5 leads
Cheaper per token
Inkling
11.9x cheaper, input + output
Larger context
Tie
both 1M tokens
Providers
2 providers
Anthropic · Thinking Machines Lab
Claude Fable 5
Anthropic · released 2026-06-09
textvision
Quality
Benchmark matrix
24 shared · 20 only Claude Fable 5 · 14 only Inkling| Benchmark | Claude Fable 5 | Inkling | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 24 | ||||
| SWE-bench Verified | 95% ↗ | 77.6% ↗ | +17.4 pt | Claude Fable 5 |
| GPQA Diamond | 85.9% ↗epoch run | 88.3% ↗epoch run | -2.4 pt | Inkling |
| LMArena Elo | 1504.3 ↗ | 1441.4 ↗ | +62.9 | Claude Fable 5 |
| APEX-Agents (Mercor) | 63.6% ↗ | 33.8% ↗ | +29.8 pt | Claude Fable 5 |
| Chess Puzzles (Epoch AI run) | 41% ↗epoch run | 21% ↗epoch run | +20 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 | 33.3% ↗epoch run | +53.7 pt | Claude Fable 5 |
| FrontierSWE V2 (Proximal Labs) | 47% ↗ | 4.1% ↗ | +42.9 pt | Claude Fable 5 |
| LiveBench Agentic Coding (LiveBench) | 62.2% ↗ | 49.4% ↗ | +12.8 pt | Claude Fable 5 |
| LiveBench Coding (LiveBench) | 86% ↗ | 71% ↗ | +15 pt | Claude Fable 5 |
| LiveBench Data Analysis (LiveBench) | 80.5% ↗ | 72.8% ↗ | +7.7 pt | Claude Fable 5 |
| LiveBench Instruction Following (LiveBench) | 75.8% ↗ | 70.1% ↗ | +5.7 pt | Claude Fable 5 |
| LiveBench Language (LiveBench) | 90.7% ↗ | 73.5% ↗ | +17.2 pt | Claude Fable 5 |
| LiveBench Mathematics (LiveBench) | 96% ↗ | 88.4% ↗ | +7.6 pt | Claude Fable 5 |
| LiveBench Reasoning (LiveBench) | 89.7% ↗ | 78.3% ↗ | +11.4 pt | Claude Fable 5 |
| LMArena Agent (LMArena) | 0.0821 ↗ | -0.1086 ↗ | +0.2 | Claude Fable 5 |
| LMArena WebDev (LMArena) | 1625.3 ↗ | 1412.6 ↗ | +212.7 | Claude Fable 5 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 100% ↗epoch run | 88.9% ↗epoch run | +11.1 pt | Claude Fable 5 |
| SAGE (Vals AI) | 51.9% ↗ | 36.6% ↗ | +15.3 pt | Claude Fable 5 |
| SimpleBench (SimpleBench) | 81.9% ↗ | 50% ↗ | +31.9 pt | Claude Fable 5 |
| SimpleQA Verified | 70.7% ↗epoch run | 43.9% ↗ | +26.8 pt | Claude Fable 5 |
| tau2-bench Banking Knowledge (Sierra) | 39.7% ↗ | 25% ↗ | +14.7 pt | Claude Fable 5 |
| Terminal-Bench 4.0 (Vals AI) | 41.4% ↗ | 0.5% ↗ | +40.9 pt | Claude Fable 5 |
| WeirdML (Håvard Tveit Ihle) | 91.9% ↗ | 32.3% ↗ | +59.6 pt | Claude Fable 5 |
| Only Claude Fable 5 reports · 20 | ||||
| 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 | — | — |
| 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 | — | — |
| LMArena Vision (LMArena) | 1308.8 ↗ | not reported | — | — |
| MirrorCode (Epoch AI run) | 63.9% ↗epoch run | not reported | — | — |
| Mystery Game Puzzles (Epoch AI run) | 52% ↗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 | — | — |
| Vending-Bench 2 (Andon Labs) | 5680.26 ↗ | not reported | — | — |
| Only Inkling reports · 14 | ||||
| AIME 2026 | not reported | 97.1% ↗ | — | — |
| Audio MC | not reported | 56.6% ↗ | — | — |
| BrowseComp (w/ ctx management) | not reported | 77.1% ↗ | — | — |
| CharXiv RQ | not reported | 78.1% ↗ | — | — |
| CharXiv RQ (with python) | not reported | 82% ↗ | — | — |
| Global-MMLU-Lite | not reported | 88.7% ↗ | — | — |
| IFBench | not reported | 79.8% ↗ | — | — |
| MCP Atlas | not reported | 76% ↗ | — | — |
| MMAU | not reported | 77.2% ↗ | — | — |
| SWE-bench Pro (public) | not reported | 54.3% ↗ | — | — |
| Terminal-Bench 2.1 (best harness) | not reported | 63.8% ↗ | — | — |
| Toolathlon Verified | not reported | 45.5% ↗ | — | — |
| Toolathlon-Verified (HKUST) | not reported | 45.5% ↗ | — | — |
| VoiceBench | not reported | 91.4% ↗ | — | — |
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 Inkling 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 | Inkling | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1M tokens | Tie |
| Max output | 128K tokens | — | — |
| Input price / 1M | $10 ↗ | $1 ↗ | Inkling |
| Output price / 1M | $50 ↗ | $4.05 ↗ | Inkling |
| Cached input / 1M | $1 ↗ | $0.17 ↗ | Inkling |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $60 | $5.05 | Inkling |
| Modalities | text · vision | text · vision · audio | Inkling |
| Released | 2026-06-09 | 2026-07-15 | — |
| Cited benchmark scores | 44 | 39 | — |
Reliability
Provider status
Live from /statusMore matchups
Claude Fable 5 vs …
Models sharing the most benchmarksMore matchups
Inkling 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 Inkling on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.