Claude Fable 5 vs GPT-4.1 Nano
Head to head on 11 shared benchmarks, with price, context window, and release dates.
Benchmark scores
62evals · sort by any column, ⤢ to expand fullscreen
| Model | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5 Anthropic | 71.8% | 1933elo | 83 | 92.6% | 55.5% | 63.5% | 68.9% | 60.2% | 76.9% | 62.9% | 98.5% | - | - | - | - | 17.4% | - | 83.9% | - | 38.6% | - | - | - | 90.0% | 1340elo | 78.0% | 56.3% | 29.3% | - | - | 29.8% | 1932elo | - | 66.0% | - | 13.3% | 81.4% | 78.6% | 80.0% | 59.9% | 88.5% | 93.9% | 87.3% | - | - | - | 56.1% | 88.5% | - | 85.0% | 95.0% | 51.9% | - | 80.3% | 88.0% | - | - | 66.0% | 74.2% | 90.4% | - | - | 69.4% |
| GPT-4.1 Nano OpenAI | 42.1% | 944elo | 32.4 | 51.2% | 3.8% | 32.0% | 52.8% | 25.9% | 60.8% | 3.8% | 17.3% | 8.9% | 23.7% | 24.0% | 10.7% | - | 1.53 | - | -0.17 | - | 3.3% | 0.0% | 42.5% | - | - | - | - | - | 1.0% | 0.39 | - | - | 1.46 | - | 0.0% | - | - | - | - | - | - | - | - | 32.6% | 10.8% | 84.8% | - | - | 65.7% | - | - | - | 0.44 | - | - | 1.64 | 39.8% | - | - | - | 68.0% | 68.0% | 30.9% |
2 / 2 models
| Attribute | Claude Fable 5 Anthropic | GPT-4.1 Nano 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-4.1 Nano is an AI model from OpenAI. |
| Family | Claude | GPT |
| Params | - | - |
| Open weights | closed | closed |
| License | - | proprietary |
| Released | 9 Jun 2026 | 14 Apr 2025 |
| Context | 1,000,000 | 1,047,576 |
| Input $/1M | $10.00 | $0.10 |
| Output $/1M | $50.00 | $0.40 |
| Cache read $/1M | $1.000 | $0.025 |
| Cache write $/1M | $12.500 | - |
| Speed | 66 tok/s | 0 tok/s |
| Latency | 49.62 s | 0.00 s |
| Modalities | text, image, file | image, text, file |
| Providers | - | - |
| Publisher | Anthropic | OpenAI |
| Reported scores | Finance Agent (v2)56.3% IFBench63.5% (AA) Swebenchpro80.3% LiveBench - Math93.9% (LiveBench) LiveBench - Coding78.6% (LiveBench) |
FAQ
- Is Claude Fable 5 or GPT-4.1 Nano better?
- Across the 11 benchmarks both models report on Sophon, Claude Fable 5 leads on 11 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do Claude Fable 5 and GPT-4.1 Nano compare on GPQA Diamond?
- Claude Fable 5 scores 92.6% and GPT-4.1 Nano scores 51.2% on GPQA Diamond.
- Which is cheaper, Claude Fable 5 or GPT-4.1 Nano?
- GPT-4.1 Nano is cheaper at $0.40 per million output tokens against $50.00 for Claude Fable 5 - about 125.0x.
- When were Claude Fable 5 and GPT-4.1 Nano released?
- Claude Fable 5 was released 9 Jun 2026 by Anthropic. GPT-4.1 Nano was released 14 Apr 2025 by OpenAI.
Comparing something else? Build your own side-by-side.