Model comparison
Claude Fable 5.1 vs Claude Opus 4
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 43.1 on the Noometry Index.
Last verified . 29 shared benchmarks.
Summary
- They share 29 benchmarks with published results for both. Claude Fable 5.1 scores higher in 10 categories and Claude Opus 4 in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Fable 5.1 leads 76.7 to 27.3.
- The biggest single-benchmark swing is ARC-AGI-2: 90% for Claude Fable 5.1 and 8.6% for Claude Opus 4.
- Claude Fable 5.1 is cheaper at $10 / $50 per million input/output tokens, against $15 / $75 for Claude Opus 4.
- Claude Fable 5.1 accepts more context: 1M tokens versus 200K.
Side by side
| Claude Fable 5.1 | Claude Opus 4 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 69.0 | 43.1 |
| Released | 2026-09-01 | 2025-05-22 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 200K |
| Max output | 128K | 32K |
| Input $ / M tokens | $10 | $15 |
| Output $ / M tokens | $50 | $75 |
| Results tracked | 52 | 56 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Fable 5.1 leads
Claude Fable 5.1: 74.7 (#1), Claude Opus 4: 47.2 (#62)
| Benchmark | Claude Fable 5.1 | Claude Opus 4 |
|---|---|---|
| GSO | 88.2% | 6.9% |
| WeirdML | 92.9% | 43.7% |
| LMArena Coding | 1528 | 1442 |
| SWE-bench Verified | — | 70.7% |
| FrontierCode | 50.9% | — |
| SWE-bench Verified (bash only) | — | 67.6% |
| Aider Polyglot | — | 72% |
| CursorBench | 51.8% | — |
| LMArena WebDev | 1744 | — |
| FrontierSWE | 56.3% | — |
| SciCode | 63.1% | — |
| MirrorCode | 73.3% | — |
| ALE-Bench | 2,143 | — |
| AlgoTune | — | 1.33 |
Agentic & Tool Use Claude Fable 5.1 leads
Claude Fable 5.1: 50.7 (#5), Claude Opus 4: 34.8 (#42)
| Benchmark | Claude Fable 5.1 | Claude Opus 4 |
|---|---|---|
| APEX-Agents | 68.6% | — |
| Remote Labor Index | 17.9% | — |
| Cybench | — | 38% |
| DeepResearch Bench | — | 46.8% |
| GDP.pdf | 29.6% | — |
| LMArena Search | — | 1127 |
| METR Time Horizons | — | 63.9% |
| Vending-Bench 2 | 5,422 | — |
Reasoning Claude Fable 5.1 leads
Claude Fable 5.1: 76.7 (#7), Claude Opus 4: 27.3 (#121)
| Benchmark | Claude Fable 5.1 | Claude Opus 4 |
|---|---|---|
| ARC-AGI-2 | 90% | 8.6% |
| ARC-AGI-1 | 97.5% | 35.7% |
| CritPt | 31.1% | 0.3% |
| LMArena Hard Prompts | 1526 | 1399 |
| DTBench | 97.6% | 81.6% |
| LMCA | 65.5% | 37.4% |
| Epoch Capabilities Index | 164.7 | 142.67 |
| SimpleBench | — | 58.8% |
| Kagi LLM Benchmark | — | 74.3% |
| NYT Connections (extended) | 90% | — |
| Chess Puzzles | 47% | — |
| EnigmaEval | — | 5.6% |
| EBR-Bench | 57.1% | — |
| Mystery Game Puzzles | 58% | — |
| ForecastBench | — | 61.1 |
Math Claude Fable 5.1 leads
Claude Fable 5.1: 89.6 (#4), Claude Opus 4: 42.0 (#86)
| Benchmark | Claude Fable 5.1 | Claude Opus 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 64.4% |
| LMArena Math | 1525 | 1390 |
| FrontierMath (Tiers 1-3) | 90.2% | — |
| FrontierMath Tier 4 | 87.8% | — |
| ProofBench | 100% | — |
| Omni-MATH | — | 61.6% |
| MATH Level 5 | — | 85% |
| FrontierMath (Feb 2025 set) | — | 4.5% |
| FrontierMath Erdős | 0% | — |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Claude Fable 5.1 leads
Claude Fable 5.1: 69.6 (#6), Claude Opus 4: 44.0 (#88)
| Benchmark | Claude Fable 5.1 | Claude Opus 4 |
|---|---|---|
| Humanity's Last Exam | 46.5% | 10.7% |
| LMArena Expert | 1535 | 1386 |
| GPQA Diamond | — | 76.3% |
| SimpleQA Verified | 70.8% | — |
| MMLU-Pro | — | 87.5% |
| Confabulations | — | 15.9% |
| Vectara Hallucination Rate | — | 12% |
| GPQA (HELM) | — | 70.8% |
Multimodal Claude Fable 5.1 leads
Claude Fable 5.1: 53.9 (#4), Claude Opus 4: 31.5 (#106)
| Benchmark | Claude Fable 5.1 | Claude Opus 4 |
|---|---|---|
| LMArena Vision | 1318 | 1192 |
| GeoBench | — | 49% |
| VPCT | — | 38% |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |
Multilingual Claude Fable 5.1 leads
Claude Fable 5.1: 59.1 (#3), Claude Opus 4: 48.8 (#138)
| Benchmark | Claude Fable 5.1 | Claude Opus 4 |
|---|---|---|
| LMArena Non-English | 1507 | 1362 |
| LMArena Chinese | 1586 | 1386 |
| LMArena French | 1525 | 1372 |
| LMArena German | 1500 | 1391 |
| LMArena Japanese | 1543 | 1331 |
| LMArena Korean | 1534 | 1321 |
| LMArena Russian | 1521 | 1392 |
| LMArena Spanish | 1516 | 1389 |
Instruction Following Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#6), Claude Opus 4: 77.1 (#28)
| Benchmark | Claude Fable 5.1 | Claude Opus 4 |
|---|---|---|
| LMArena Instruction Following | 1517 | 1406 |
| IFEval | — | 91.8% |
Long Context Claude Fable 5.1 leads
Claude Fable 5.1: 46.7 (#20), Claude Opus 4: 39.6 (#172)
| Benchmark | Claude Fable 5.1 | Claude Opus 4 |
|---|---|---|
| LMArena Longer Query | 1522 | 1422 |
| Fiction.LiveBench | — | 61.1% |
Writing & Preference Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#2), Claude Opus 4: 61.2 (#89)
| Benchmark | Claude Fable 5.1 | Claude Opus 4 |
|---|---|---|
| LMArena Text | 1510 | 1377 |
| LMArena Creative Writing | 1507 | 1387 |
| EQ-Bench Creative Writing | 2162 | 1580 |
| LMArena Multi-Turn | 1492 | 1396 |
| Short-Story Creative Writing | — | 83.6% |
| WildBench | — | 85.2% |
Frequently asked questions
Is Claude Fable 5.1 better than Claude Opus 4?
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 43.1 on the Noometry Index.
Which is cheaper, Claude Fable 5.1 or Claude Opus 4?
Claude Fable 5.1 is cheaper. It lists at $10 per million input tokens and $50 per million output tokens; Claude Opus 4 lists at $15 and $75.
Is Claude Fable 5.1 or Claude Opus 4 better for coding?
Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 47.2 in the Noometry coding category.
Which has the bigger context window?
Claude Fable 5.1 does, with 1M tokens against 200K.
How many benchmarks do Claude Fable 5.1 and Claude Opus 4 share?
29 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and Claude Opus 4 has 56.