Claude Fable 5 vs GPT-5.4
Head to head on 26 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% | 71.8% | 90.0% | 1340elo | 1933elo | 83 | 92.6% | 55.5% | 63.5% | 81.4% | 78.6% | 80.0% | 59.9% | 88.5% | 93.9% | 87.3% | 56.1% | 88.5% | 68.9% | 95.0% | 51.9% | 60.2% | 76.9% | 62.9% | 90.4% | 98.5% | 83.9% | 38.6% | - | - | - | 78.0% | 56.3% | 29.3% | - | 29.8% | 1932elo | - | 66.0% | - | - | 13.3% | - | - | - | 85.0% | - | - | 80.3% | 88.0% | - | 66.0% | 74.2% | 69.4% |
| GPT-5.4 OpenAI | 13.1% | 65.3% | 81.0% | 1272elo | 1836elo | 78.3 | 74.8% | 11.3% | 48.4% | 82.0% | 77.5% | 79.3% | 70.2% | 82.6% | 94.1% | 88.1% | 41.3% | 77.5% | 68.3% | 56.0% | 43.3% | 47.1% | 74.0% | 37.9% | 67.4% | 36.0% | - | - | 1.47 | 34.1% | 9.0% | - | - | - | 47.6% | - | - | 87.2% | - | 78.5% | 92063 | - | 82.8% | 86 | 52.2% | - | -0.61 | 40.8 | - | - | 80 | - | - | 60.3% |
2 / 2 models
| Attribute | Claude Fable 5 Anthropic | GPT-5.4 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-5.4 is an AI model from OpenAI. |
| Family | Claude | GPT |
| Params | - | - |
| Open weights | closed | closed |
| License | - | proprietary |
| Released | 9 Jun 2026 | 5 Mar 2026 |
| Context | 1,000,000 | 1,050,000 |
| Input $/1M | $10.00 | $2.50 |
| Output $/1M | $50.00 | $15.00 |
| Cache read $/1M | $1.000 | $0.250 |
| Cache write $/1M | $12.500 | - |
| Speed | 66 tok/s | 0 tok/s |
| Latency | 49.62 s | 0.00 s |
| Modalities | text, image, file | text, image, 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) | GPQA Diamond74.8% (AA) SciCode47.1% (AA) τ²-bench (Tau²-bench)36.0% (AA) Terminal-Bench (Hard)37.9% (AA) Vibe Code Bench v1.167.4% |
FAQ
- Is Claude Fable 5 or GPT-5.4 better?
- Across the 26 benchmarks both models report on Sophon, Claude Fable 5 leads on 22 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do Claude Fable 5 and GPT-5.4 compare on GPQA Diamond?
- Claude Fable 5 scores 92.6% and GPT-5.4 scores 74.8% on GPQA Diamond.
- Which is cheaper, Claude Fable 5 or GPT-5.4?
- GPT-5.4 is cheaper at $15.00 per million output tokens against $50.00 for Claude Fable 5 - about 3.3x.
- When were Claude Fable 5 and GPT-5.4 released?
- Claude Fable 5 was released 9 Jun 2026 by Anthropic. GPT-5.4 was released 5 Mar 2026 by OpenAI.
Comparing something else? Build your own side-by-side.