Model comparison
Claude Fable 5 vs Inkling
Claude Fable 5 is the stronger model overall, scoring 66.8 to 44.1 on the Noometry Index. Inkling costs 7.8× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.
Last verified . 41 shared benchmarks.
Summary
- They share 41 benchmarks with published results for both. Claude Fable 5 scores higher in 9 categories and Inkling in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5 leads 88.5 to 31.3.
- The biggest single-benchmark swing is ProofBench: 95% for Claude Fable 5 and 0% for Inkling.
- Inkling is cheaper at $1.87 / $4.68 per million input/output tokens, against $10 / $50 for Claude Fable 5.
- Claude Fable 5 accepts more context: 1M tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| Claude Fable 5 | Inkling | |
|---|---|---|
| Provider | Anthropic | Thinking Machines Lab |
| Noometry Index | 66.8 | 44.1 |
| Released | 2026-06-07 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 1M | 66K |
| Max output | 128K | 66K |
| Input $ / M tokens | $10 | $1.87 |
| Output $ / M tokens | $50 | $4.68 |
| Results tracked | 62 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Fable 5 leads
Claude Fable 5: 70.6 (#4), Inkling: 34.5 (#234)
| Benchmark | Claude Fable 5 | Inkling |
|---|---|---|
| FrontierCode | 53.5% | 14% |
| LMArena WebDev | 1625 | 1413 |
| FrontierSWE | 47% | 4.1% |
| SciCode | 61% | 47% |
| WeirdML | 91.9% | 32.3% |
| LMArena Coding | 1519 | 1464 |
| ALE-Bench | 2,041 | 946 |
| DeepSWE | 69.9% | — |
| GSO | 78.4% | — |
| MirrorCode | 63.9% | — |
Agentic & Tool Use Claude Fable 5 leads
Claude Fable 5: 54.0 (#2), Inkling: 29.6 (#85)
| Benchmark | Claude Fable 5 | Inkling |
|---|---|---|
| APEX-Agents | 63.6% | 33.8% |
| τ²-bench Banking | 39.7% | 25% |
| Remote Labor Index | 16.1% | — |
| PostTrainBench | 41.8% | — |
| GBAEval | 74.5% | — |
| GDP.pdf | 30% | — |
| LMArena Search | 1230 | — |
| Vending-Bench 2 | 5,680 | — |
Reasoning Claude Fable 5 leads
Claude Fable 5: 76.8 (#6), Inkling: 40.4 (#56)
| Benchmark | Claude Fable 5 | Inkling |
|---|---|---|
| ARC-AGI-2 | 89.2% | 36.5% |
| SimpleBench | 81.9% | 50% |
| ARC-AGI-1 | 98.5% | 79.5% |
| CritPt | 28.6% | 5.4% |
| Chess Puzzles | 41% | 21% |
| LMArena Hard Prompts | 1508 | 1451 |
| DTBench | 98.4% | 87.5% |
| LMCA | 61.1% | 37.6% |
| Epoch Capabilities Index | 162.06 | 148.54 |
| Kagi LLM Benchmark | 91.4% | — |
| NYT Connections (extended) | 92.7% | — |
| EnigmaEval | 39.3% | — |
| EBR-Bench | 39.5% | — |
| Mystery Game Puzzles | 52% | — |
| Surface Evolver Bench | 95% | — |
| Bench to the Future 3 | 0.13 | — |
Math Claude Fable 5 leads
Claude Fable 5: 88.5 (#5), Inkling: 31.3 (#225)
| Benchmark | Claude Fable 5 | Inkling |
|---|---|---|
| FrontierMath (Tiers 1-3) | 87% | 33.3% |
| FrontierMath Tier 4 | 90.2% | 4.9% |
| OTIS Mock AIME 2024-2025 | 100% | 88.9% |
| ProofBench | 95% | 0% |
| LMArena Math | 1519 | 1479 |
| FrontierMath Erdős | 0% | — |
Knowledge Claude Fable 5 leads
Claude Fable 5: 62.2 (#25), Inkling: 55.1 (#49)
| Benchmark | Claude Fable 5 | Inkling |
|---|---|---|
| GPQA Diamond | 85.9% | 88.3% |
| SimpleQA Verified | 70.7% | 40.3% |
| LMArena Expert | 1534 | 1465 |
Multimodal Not comparable
Claude Fable 5: 45.3 (#17), Inkling: —
| Benchmark | Claude Fable 5 | Inkling |
|---|---|---|
| LMArena Vision | 1324 | — |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 35.8% | — |
| LMArena Document | 1496 | — |
Multilingual Claude Fable 5 leads
Claude Fable 5: 57.3 (#9), Inkling: 54.0 (#52)
| Benchmark | Claude Fable 5 | Inkling |
|---|---|---|
| LMArena Non-English | 1481 | 1434 |
| LMArena Chinese | 1543 | 1490 |
| LMArena French | 1505 | 1458 |
| LMArena German | 1486 | 1446 |
| LMArena Japanese | 1506 | 1429 |
| LMArena Korean | 1488 | 1404 |
| LMArena Russian | 1504 | 1429 |
| LMArena Spanish | 1498 | 1448 |
Instruction Following Claude Fable 5 leads
Claude Fable 5: 78.6 (#8), Inkling: 75.1 (#71)
| Benchmark | Claude Fable 5 | Inkling |
|---|---|---|
| LMArena Instruction Following | 1502 | 1426 |
Long Context Claude Fable 5 leads
Claude Fable 5: 46.3 (#23), Inkling: 43.8 (#86)
| Benchmark | Claude Fable 5 | Inkling |
|---|---|---|
| LMArena Longer Query | 1509 | 1434 |
Writing & Preference Claude Fable 5 leads
Claude Fable 5: 75.9 (#5), Inkling: 65.2 (#51)
| Benchmark | Claude Fable 5 | Inkling |
|---|---|---|
| LMArena Text | 1491 | 1441 |
| LMArena Creative Writing | 1494 | 1387 |
| EQ-Bench Creative Writing | 1943 | 1611 |
| EQ-Bench 4 | 1340 | 1226 |
| LMArena Multi-Turn | 1504 | 1436 |
Frequently asked questions
Is Claude Fable 5 better than Inkling?
Claude Fable 5 is the stronger model overall, scoring 66.8 to 44.1 on the Noometry Index. Inkling costs 7.8× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.
Which is cheaper, Claude Fable 5 or Inkling?
Inkling is cheaper. It lists at $1.87 per million input tokens and $4.68 per million output tokens; Claude Fable 5 lists at $10 and $50.
Is Claude Fable 5 or Inkling better for coding?
Claude Fable 5 scores higher on coding benchmarks: 70.6 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
Claude Fable 5 does, with 1M tokens against 66K.
How many benchmarks do Claude Fable 5 and Inkling share?
41 benchmarks have published results for both models. Claude Fable 5 has 62 scored results on Noometry and Inkling has 41.