Claude Fable 5 vs GPT-5.5
Head to head on 39 shared benchmarks, with price, context window, and release dates.
Benchmark scores
53evals · sort by any column, ⤢ to expand fullscreen
| Model | ||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5 Anthropic | 17.4% | 38.6% | 71.8% | 90.0% | 1340elo | 1933elo | 83 | 78.0% | 56.3% | 29.3% | 29.8% | 1932elo | 92.6% | 66.0% | 55.5% | 63.5% | 13.3% | 81.4% | 78.6% | 80.0% | 59.9% | 88.5% | 93.9% | 87.3% | 56.1% | 88.5% | 68.9% | 85.0% | 95.0% | 51.9% | 60.2% | 80.3% | 76.9% | 88.0% | 62.9% | 66.0% | 74.2% | 90.4% | 98.5% | - | - | 83.9% | - | - | - | - | - | - | - | - | - | - | - | 69.4% |
| GPT-5.5 OpenAI | 12.9% | 36.2% | 68.4% | 86.0% | 1315elo | 1844elo | 78.2 | 34.0% | 51.8% | 5.7% | 24.9% | 1769elo | 76.8% | 51.8% | 13.7% | 46.1% | 2.1% | 84.7% | 82.5% | 81.1% | 73.0% | 87.7% | 96.3% | 87.7% | 49.1% | 86.9% | 68.8% | 78.7% | 50.0% | 51.5% | 47.3% | 58.6% | 75.0% | 83.4% | 49.2% | 57.4% | 68.1% | 69.8% | 69.3% | 86.2% | 54.2% | - | 90.0% | 100.0% | 51.7% | 44.8% | 15.1% | 92.8% | 88.6% | 45.3% | 100.0% | 4.2 | 75.7% | 61.9% |
2 / 2 models
| Attribute | Claude Fable 5 Anthropic | GPT-5.5 OpenAI |
|---|---|---|
| Description | Claude Fable 5 is Anthropic's most capable widely released model, built for the most demanding reasoning and long-horizon agentic work. Shares its base model with the invitation-only Claude Mythos 5. | GPT-5.5 is an AI model from OpenAI. |
| Family | Claude | GPT |
| Params | - | - |
| Open weights | closed | closed |
| License | - | proprietary |
| Released | 9 Jun 2026 | 23 Apr 2026 |
| Context | 1,000,000 | 1,050,000 |
| Input $/1M | $10.00 | $5.00 |
| Output $/1M | $50.00 | $30.00 |
| Cache read $/1M | $1.000 | $0.500 |
| Cache write $/1M | $12.500 | - |
| Speed | 66 tok/s | 0 tok/s |
| Latency | 49.62 s | 0.00 s |
| Modalities | text, image, file | file, image, text |
| Providers | - | - |
| Publisher | Anthropic | OpenAI |
| Reported scores | Finance Agent (v2)56.3% IFBench63.5% (AA) Swebenchpro80.3% LiveBench - Math93.9% (LiveBench) LiveBench - Coding78.6% (LiveBench) | GPQA Diamond76.8% (AA) Humanity's Last Exam (HLE)13.7% (AA) IFBench46.1% (AA) SciCode47.3% (AA) τ²-bench (Tau²-bench)69.3% (AA) |
FAQ
- Is Claude Fable 5 or GPT-5.5 better?
- Across the 39 benchmarks both models report on Sophon, Claude Fable 5 leads on 33 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do Claude Fable 5 and GPT-5.5 compare on GPQA Diamond?
- Claude Fable 5 scores 92.6% and GPT-5.5 scores 76.8% on GPQA Diamond.
- Which is cheaper, Claude Fable 5 or GPT-5.5?
- GPT-5.5 is cheaper at $30.00 per million output tokens against $50.00 for Claude Fable 5 - about 1.7x.
- When were Claude Fable 5 and GPT-5.5 released?
- Claude Fable 5 was released 9 Jun 2026 by Anthropic. GPT-5.5 was released 23 Apr 2026 by OpenAI.
Comparing something else? Build your own side-by-side.