Model comparison
Claude Fable 5.1 vs GPT-5.5
Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 63.4 on the Noometry Index. GPT-5.5 costs 1.8× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.
Last verified . 47 shared benchmarks.
Summary
- They share 47 benchmarks with published results for both. Claude Fable 5.1 scores higher in 9 categories and GPT-5.5 in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Fable 5.1 leads 70.5 to 58.3.
- The biggest single-benchmark swing is MirrorCode: 73.3% for Claude Fable 5.1 and 10% for GPT-5.5.
- GPT-5.5 is cheaper at $5 / $30 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
- GPT-5.5 accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Fable 5.1 | GPT-5.5 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 68.5 | 63.4 |
| Released | 2026-09-01 | 2026-04-23 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $10 | $5 |
| Output $ / M tokens | $50 | $30 |
| Results tracked | 50 | 71 |
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: 70.5 (#2), GPT-5.5: 58.3 (#13)
| Benchmark | Claude Fable 5.1 | GPT-5.5 |
|---|---|---|
| FrontierCode | 50.9% | 43% |
| LMArena WebDev | 1753 | 1512 |
| SciCode | 63.1% | 56.1% |
| WeirdML | 92.9% | 84.9% |
| LMArena Coding | 1523 | 1494 |
| MirrorCode | 73.3% | 10% |
| ALE-Bench | 2,143 | 1,943 |
| SWE-bench Verified | — | 80.6% |
| DeepSWE | — | 67% |
| CursorBench | 51.8% | — |
| FrontierSWE | 56.3% | — |
| GSO | — | 40.2% |
Agentic & Tool Use Too close to call
Claude Fable 5.1: 50.8 (#5), GPT-5.5: 50.7 (#6)
| Benchmark | Claude Fable 5.1 | GPT-5.5 |
|---|---|---|
| APEX-Agents | 68.6% | 55.1% |
| Remote Labor Index | 17.9% | 6.3% |
| GDP.pdf | 29.6% | 26% |
| Vending-Bench 2 | 5,422 | 7,524 |
| Terminal-Bench | — | 84.7% |
| OSWorld 2.0 | — | 13% |
| τ²-bench Banking | — | 44.6% |
| DeepResearch Bench | — | 54% |
| PostTrainBench | — | 27.2% |
| ExploitBench | — | 47.4% |
| GBAEval | — | 53.2% |
| LMArena Search | — | 1242 |
Reasoning Claude Fable 5.1 leads
Claude Fable 5.1: 76.7 (#5), GPT-5.5: 72.7 (#8)
| Benchmark | Claude Fable 5.1 | GPT-5.5 |
|---|---|---|
| ARC-AGI-2 | 90% | 85% |
| NYT Connections (extended) | 90% | 96.2% |
| ARC-AGI-1 | 97.5% | 95% |
| CritPt | 31.1% | 27.1% |
| Chess Puzzles | 47% | 54% |
| EBR-Bench | 57.1% | 34.3% |
| LMArena Hard Prompts | 1526 | 1489 |
| Mystery Game Puzzles | 58% | 56% |
| DTBench | 97.6% | 96% |
| LMCA | 65.5% | 54.3% |
| Epoch Capabilities Index | 165 | 159.25 |
| SimpleBench | — | 69% |
| Kagi LLM Benchmark | — | 88.8% |
| Surface Evolver Bench | — | 88.1% |
| Bench to the Future 3 | — | 0.14 |
| ForecastBench | — | 60.6 |
Math Claude Fable 5.1 leads
Claude Fable 5.1: 89.5 (#3), GPT-5.5: 81.5 (#9)
| Benchmark | Claude Fable 5.1 | GPT-5.5 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 90.2% | 85.3% |
| FrontierMath Tier 4 | 87.8% | 72.5% |
| OTIS Mock AIME 2024-2025 | 100% | 100% |
| ProofBench | 100% | 50% |
| LMArena Math | 1519 | 1486 |
| FrontierMath Erdős | 0% | 0% |
| MathArena Final-Answer Competitions | — | 94.3% |
| FrontierMath (Feb 2025 set) | — | 51.7% |
| FrontierMath Tier 4 (v1) | — | 35.4% |
Knowledge Claude Fable 5.1 leads
Claude Fable 5.1: 69.3 (#5), GPT-5.5: 64.4 (#14)
| Benchmark | Claude Fable 5.1 | GPT-5.5 |
|---|---|---|
| SimpleQA Verified | 70.8% | 63% |
| LMArena Expert | 1528 | 1508 |
| GPQA Diamond | — | 94% |
| Humanity's Last Exam | 46.5% | — |
| Vectara Hallucination Rate | — | 9.3% |
Multimodal Claude Fable 5.1 leads
Claude Fable 5.1: 54.1 (#4), GPT-5.5: 47.1 (#11)
| Benchmark | Claude Fable 5.1 | GPT-5.5 |
|---|---|---|
| LMArena Vision | 1319 | 1297 |
| Blueprint-Bench 2 | 41.9% | 36.2% |
| Furniture Assembly | 70% | 44.2% |
| LMArena Document | 1513 | 1486 |
Multilingual Claude Fable 5.1 leads
Claude Fable 5.1: 59.5 (#2), GPT-5.5: 56.5 (#19)
| Benchmark | Claude Fable 5.1 | GPT-5.5 |
|---|---|---|
| LMArena Non-English | 1509 | 1467 |
| LMArena Chinese | 1589 | 1535 |
| LMArena French | 1532 | 1486 |
| LMArena German | 1495 | 1478 |
| LMArena Japanese | 1565 | 1498 |
| LMArena Russian | 1525 | 1473 |
| LMArena Spanish | 1503 | 1469 |
| LMArena Korean | — | 1461 |
Instruction Following Claude Fable 5.1 leads
Claude Fable 5.1: 79.3 (#6), GPT-5.5: 77.7 (#18)
| Benchmark | Claude Fable 5.1 | GPT-5.5 |
|---|---|---|
| LMArena Instruction Following | 1515 | 1479 |
Long Context GPT-5.5 leads
Claude Fable 5.1: 46.8 (#19), GPT-5.5: 48.3 (#12)
| Benchmark | Claude Fable 5.1 | GPT-5.5 |
|---|---|---|
| LMArena Longer Query | 1524 | 1484 |
| CL-bench Life | — | 22.2% |
Writing & Preference Claude Fable 5.1 leads
Claude Fable 5.1: 79.3 (#1), GPT-5.5: 72.8 (#13)
| Benchmark | Claude Fable 5.1 | GPT-5.5 |
|---|---|---|
| LMArena Text | 1511 | 1471 |
| LMArena Creative Writing | 1507 | 1455 |
| EQ-Bench Creative Writing | 2162 | 1844 |
| LMArena Multi-Turn | 1492 | 1477 |
| EQ-Bench 4 | — | 1315 |
Frequently asked questions
Is Claude Fable 5.1 better than GPT-5.5?
Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 63.4 on the Noometry Index. GPT-5.5 costs 1.8× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.
Which is cheaper, Claude Fable 5.1 or GPT-5.5?
GPT-5.5 is cheaper. It lists at $5 per million input tokens and $30 per million output tokens; Claude Fable 5.1 lists at $10 and $50.
Is Claude Fable 5.1 or GPT-5.5 better for coding?
Claude Fable 5.1 scores higher on coding benchmarks: 70.5 versus 58.3 in the Noometry coding category.
Which has the bigger context window?
GPT-5.5 does, with 1.05M tokens against 1M.
How many benchmarks do Claude Fable 5.1 and GPT-5.5 share?
47 benchmarks have published results for both models. Claude Fable 5.1 has 50 scored results on Noometry and GPT-5.5 has 71.