Model comparison
Claude Fable 5.1 vs GPT-4.5
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 37.2 on the Noometry Index.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. Claude Fable 5.1 scores higher in 10 categories and GPT-4.5 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 13.9.
- The biggest single-benchmark swing is ARC-AGI-2: 90% for Claude Fable 5.1 and 0.8% for GPT-4.5.
Side by side
| Claude Fable 5.1 | GPT-4.5 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 69.0 | 37.2 |
| Released | 2026-09-01 | 2025-02-27 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Max output | 128K | — |
| Input $ / M tokens | $10 | — |
| Output $ / M tokens | $50 | — |
| Results tracked | 52 | 42 |
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), GPT-4.5: 42.2 (#109)
| Benchmark | Claude Fable 5.1 | GPT-4.5 |
|---|---|---|
| WeirdML | 92.9% | 39.4% |
| LMArena Coding | 1528 | 1396 |
| FrontierCode | 50.9% | — |
| Aider Polyglot | — | 44.9% |
| CursorBench | 51.8% | — |
| LMArena WebDev | 1744 | — |
| FrontierSWE | 56.3% | — |
| SciCode | 63.1% | — |
| GSO | 88.2% | — |
| LiveBench Coding | — | 75.2% |
| MirrorCode | 73.3% | — |
| ALE-Bench | 2,143 | — |
Agentic & Tool Use Claude Fable 5.1 leads
Claude Fable 5.1: 50.7 (#5), GPT-4.5: 27.9 (#97)
| Benchmark | Claude Fable 5.1 | GPT-4.5 |
|---|---|---|
| APEX-Agents | 68.6% | — |
| Remote Labor Index | 17.9% | — |
| Cybench | — | 17.5% |
| GDP.pdf | 29.6% | — |
| Vending-Bench 2 | 5,422 | — |
Reasoning Claude Fable 5.1 leads
Claude Fable 5.1: 76.7 (#7), GPT-4.5: 13.9 (#330)
| Benchmark | Claude Fable 5.1 | GPT-4.5 |
|---|---|---|
| ARC-AGI-2 | 90% | 0.8% |
| ARC-AGI-1 | 97.5% | 10.3% |
| LMArena Hard Prompts | 1526 | 1403 |
| Epoch Capabilities Index | 164.7 | 136.74 |
| SimpleBench | — | 34.5% |
| NYT Connections (extended) | 90% | — |
| CritPt | 31.1% | — |
| Chess Puzzles | 47% | — |
| EnigmaEval | — | 3.2% |
| EBR-Bench | 57.1% | — |
| LiveBench Reasoning | — | 71.1% |
| Mystery Game Puzzles | 58% | — |
| DTBench | 97.6% | — |
| LiveBench Data Analysis | — | 64.3% |
| LMCA | 65.5% | — |
| ForecastBench | — | 61.7 |
| LiveBench | — | 69% |
Math Claude Fable 5.1 leads
Claude Fable 5.1: 89.6 (#4), GPT-4.5: 32.6 (#211)
| Benchmark | Claude Fable 5.1 | GPT-4.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 37.8% |
| LMArena Math | 1525 | 1412 |
| FrontierMath (Tiers 1-3) | 90.2% | — |
| FrontierMath Tier 4 | 87.8% | — |
| ProofBench | 100% | — |
| LiveBench Math | — | 69.3% |
| MATH Level 5 | — | 78.6% |
| FrontierMath Erdős | 0% | — |
Knowledge Claude Fable 5.1 leads
Claude Fable 5.1: 69.6 (#6), GPT-4.5: 32.5 (#211)
| Benchmark | Claude Fable 5.1 | GPT-4.5 |
|---|---|---|
| Humanity's Last Exam | 46.5% | 5.4% |
| LMArena Expert | 1535 | 1394 |
| GPQA Diamond | — | 68.7% |
| SimpleQA Verified | 70.8% | — |
| Confabulations | — | 13.6% |
Multimodal Claude Fable 5.1 leads
Claude Fable 5.1: 53.9 (#4), GPT-4.5: 37.6 (#71)
| Benchmark | Claude Fable 5.1 | GPT-4.5 |
|---|---|---|
| LMArena Vision | 1318 | 1195 |
| VPCT | — | 45% |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |
Multilingual Claude Fable 5.1 leads
Claude Fable 5.1: 59.1 (#3), GPT-4.5: 52.5 (#83)
| Benchmark | Claude Fable 5.1 | GPT-4.5 |
|---|---|---|
| LMArena Non-English | 1507 | 1413 |
| LMArena Chinese | 1586 | 1421 |
| LMArena French | 1525 | 1418 |
| LMArena German | 1500 | 1457 |
| LMArena Japanese | 1543 | 1416 |
| LMArena Korean | 1534 | 1392 |
| LMArena Russian | 1521 | 1419 |
| LMArena Spanish | 1516 | — |
Instruction Following Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#6), GPT-4.5: 72.6 (#134)
| Benchmark | Claude Fable 5.1 | GPT-4.5 |
|---|---|---|
| LMArena Instruction Following | 1517 | 1404 |
| LiveBench Instruction Following | — | 72.3% |
Long Context Claude Fable 5.1 leads
Claude Fable 5.1: 46.7 (#20), GPT-4.5: 40.4 (#155)
| Benchmark | Claude Fable 5.1 | GPT-4.5 |
|---|---|---|
| LMArena Longer Query | 1522 | 1406 |
| Fiction.LiveBench | — | 63.9% |
Writing & Preference Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#2), GPT-4.5: 56.9 (#134)
| Benchmark | Claude Fable 5.1 | GPT-4.5 |
|---|---|---|
| LMArena Text | 1510 | 1417 |
| LMArena Creative Writing | 1507 | 1394 |
| EQ-Bench Creative Writing | 2162 | 1258 |
| LMArena Multi-Turn | 1492 | 1444 |
| Short-Story Creative Writing | — | 75.6% |
| LiveBench Language | — | 61.5% |
Frequently asked questions
Is Claude Fable 5.1 better than GPT-4.5?
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 37.2 on the Noometry Index.
Is Claude Fable 5.1 or GPT-4.5 better for coding?
Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 42.2 in the Noometry coding category.
How many benchmarks do Claude Fable 5.1 and GPT-4.5 share?
24 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and GPT-4.5 has 42.