Model comparison
Claude 3 Opus vs Claude Fable 5.1
Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 29.3 on the Noometry Index.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and Claude Fable 5.1 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5.1 leads 89.5 to 13.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 100% for Claude Fable 5.1.
Side by side
| Claude 3 Opus | Claude Fable 5.1 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 29.3 | 68.5 |
| Released | 2024-02-29 | 2026-09-01 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 128K |
| Input $ / M tokens | — | $10 |
| Output $ / M tokens | — | $50 |
| Results tracked | 46 | 50 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Fable 5.1 leads
Claude 3 Opus: 32.4 (#261), Claude Fable 5.1: 70.5 (#2)
| Benchmark | Claude 3 Opus | Claude Fable 5.1 |
|---|---|---|
| WeirdML | 19.2% | 92.9% |
| LMArena Coding | 1264 | 1523 |
| FrontierCode | — | 50.9% |
| CursorBench | — | 51.8% |
| LMArena WebDev | — | 1753 |
| FrontierSWE | — | 56.3% |
| SciCode | — | 63.1% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| MirrorCode | — | 73.3% |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 2,143 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Claude Fable 5.1 leads
Claude 3 Opus: 24.3 (#110), Claude Fable 5.1: 50.8 (#5)
| Benchmark | Claude 3 Opus | Claude Fable 5.1 |
|---|---|---|
| APEX-Agents | — | 68.6% |
| Remote Labor Index | — | 17.9% |
| Cybench | 10% | — |
| GDP.pdf | — | 29.6% |
| METR Time Horizons | 29.5% | — |
| Vending-Bench 2 | — | 5,422 |
Reasoning Claude Fable 5.1 leads
Claude 3 Opus: 14.2 (#318), Claude Fable 5.1: 76.7 (#5)
| Benchmark | Claude 3 Opus | Claude Fable 5.1 |
|---|---|---|
| Chess Puzzles | 5% | 47% |
| LMArena Hard Prompts | 1246 | 1526 |
| DTBench | 61.6% | 97.6% |
| LMCA | 17% | 65.5% |
| Epoch Capabilities Index | 126.91 | 165 |
| ARC-AGI-2 | — | 90% |
| SimpleBench | 23.5% | — |
| NYT Connections (extended) | — | 90% |
| ARC-AGI-1 | — | 97.5% |
| CritPt | — | 31.1% |
| EnigmaEval | 0.8% | — |
| EBR-Bench | — | 57.1% |
| LiveBench Reasoning | 40.6% | — |
| Mystery Game Puzzles | — | 58% |
| LiveBench Data Analysis | 57.9% | — |
| ForecastBench | 58.4 | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math Claude Fable 5.1 leads
Claude 3 Opus: 13.9 (#293), Claude Fable 5.1: 89.5 (#3)
| Benchmark | Claude 3 Opus | Claude Fable 5.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 100% |
| LMArena Math | 1273 | 1519 |
| FrontierMath (Tiers 1-3) | — | 90.2% |
| FrontierMath Tier 4 | — | 87.8% |
| ProofBench | — | 100% |
| LiveBench Math | 43.6% | — |
| MATH Level 5 | 37.5% | — |
| FrontierMath Erdős | — | 0% |
Knowledge Claude Fable 5.1 leads
Claude 3 Opus: 24.5 (#262), Claude Fable 5.1: 69.3 (#5)
| Benchmark | Claude 3 Opus | Claude Fable 5.1 |
|---|---|---|
| SimpleQA Verified | 12.6% | 70.8% |
| LMArena Expert | 1223 | 1528 |
| GPQA Diamond | 47.2% | — |
| Humanity's Last Exam | — | 46.5% |
| Confabulations | 22.7% | — |
| MMLU | 84.6% | — |
Multimodal Claude Fable 5.1 leads
Claude 3 Opus: 26.6 (#112), Claude Fable 5.1: 54.1 (#4)
| Benchmark | Claude 3 Opus | Claude Fable 5.1 |
|---|---|---|
| LMArena Vision | 1023 | 1319 |
| Blueprint-Bench 2 | — | 41.9% |
| Furniture Assembly | — | 70% |
| LMArena Document | — | 1513 |
Multilingual Claude Fable 5.1 leads
Claude 3 Opus: 41.6 (#202), Claude Fable 5.1: 59.5 (#2)
| Benchmark | Claude 3 Opus | Claude Fable 5.1 |
|---|---|---|
| LMArena Non-English | 1258 | 1509 |
| LMArena Chinese | 1248 | 1589 |
| LMArena French | 1274 | 1532 |
| LMArena German | 1258 | 1495 |
| LMArena Japanese | 1204 | 1565 |
| LMArena Russian | 1280 | 1525 |
| LMArena Spanish | 1246 | 1503 |
| LMArena Korean | 1187 | — |
Instruction Following Claude Fable 5.1 leads
Claude 3 Opus: 64.3 (#223), Claude Fable 5.1: 79.3 (#6)
| Benchmark | Claude 3 Opus | Claude Fable 5.1 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1515 |
| LiveBench Instruction Following | 63.9% | — |
Long Context Claude Fable 5.1 leads
Claude 3 Opus: 38.2 (#197), Claude Fable 5.1: 46.8 (#19)
| Benchmark | Claude 3 Opus | Claude Fable 5.1 |
|---|---|---|
| LMArena Longer Query | 1259 | 1524 |
Writing & Preference Claude Fable 5.1 leads
Claude 3 Opus: 47.4 (#208), Claude Fable 5.1: 79.3 (#1)
| Benchmark | Claude 3 Opus | Claude Fable 5.1 |
|---|---|---|
| LMArena Text | 1262 | 1511 |
| LMArena Creative Writing | 1235 | 1507 |
| LMArena Multi-Turn | 1275 | 1492 |
| EQ-Bench Creative Writing | — | 2162 |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than Claude Fable 5.1?
Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 29.3 on the Noometry Index.
Is Claude 3 Opus or Claude Fable 5.1 better for coding?
Claude Fable 5.1 scores higher on coding benchmarks: 70.5 versus 32.4 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Claude Fable 5.1 share?
24 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Claude Fable 5.1 has 50.