Claude Fable 5vsGPT-5.5
Across 11 shared benchmarks, Claude Fable 5 leads overall: Claude Fable 5 wins 10, GPT-5.5 wins 1, with 0 ties and an average score difference of +8.97.
Claude Fable 5
Anthropic · 2026-06-09 · Reasoning model
GPT-5.5
OpenAI · 2026-04-23 · Reasoning model
Claude Fable 510 wins(91%)(9%)1 winGPT-5.5
Benchmark scores
Grouped by capability, sorted by largest gap within each. 11 shared benchmarks.
AI Agent - Tool Usage
Claude Fable 5 3/3| Benchmark | Claude Fable 5 | GPT-5.5 | Diff |
|---|---|---|---|
| MCP-Atlas | 83.305 / 38Normal (With Tools) | 75.3021 / 38极高强度思考（工具） | +8 |
| OSWorld-Verified | 851 / 26Thinking High (With Tools) | 78.709 / 26Thinking High (With Tools) | +6.30 |
| Terminal-Bench 2.1 | 884 / 44Deep Thinking (With Tools) | 83.4013 / 44Thinking High (With Tools) | +4.60 |
Coding and Software Engineer
Claude Fable 5 3/3| Benchmark | Claude Fable 5 | GPT-5.5 | Diff |
|---|---|---|---|
| SWE-Bench Pro - Public | 80.301 / 57Deep Thinking (With Tools) | 58.6015 / 57Thinking High (With Tools) | +21.70 |
| WeirdML v2 | 87.853 / 52Thinking High (With Tools) | 67.1522 / 52Normal (With Tools) | +20.70 |
| DeepSWE | 702 / 27Deep Thinking (With Tools) | 677 / 27极高强度思考（工具） | +3 |
General Knowledge
Even 2/2| Benchmark | Claude Fable 5 | GPT-5.5 | Diff |
|---|---|---|---|
| HLE | 595 / 181Deep Thinking (No Tools) | 52.2022 / 181Thinking High (With Tools) | +6.80 |
| LiveBench | 78.315 / 115Deep Thinking (No Tools) | 80.711 / 115Deep Thinking (No Tools) | -2.40 |
Math and Reasoning
Claude Fable 5 2/2| Benchmark | Claude Fable 5 | GPT-5.5 | Diff |
|---|---|---|---|
| FrontierMath Tier 4 v2 | 87.801 / 34最高（无工具） | 72.505 / 34极高强度思考（无工具） | +15.30 |
| FrontierMath v2 | 87.023 / 34最高（无工具） | 85.266 / 34极高强度思考（无工具） | +1.75 |
Commonsense Reasoning
Claude Fable 5 1/1| Benchmark | Claude Fable 5 | GPT-5.5 | Diff |
|---|---|---|---|
| SimpleBench | 81.901 / 67Normal (No Tools) | 698 / 67Normal (No Tools) | +12.90 |
Specs
| Field | Claude Fable 5 | GPT-5.5 |
|---|---|---|
| Publisher | Anthropic | OpenAI |
| Release date | 2026-06-09 | 2026-04-23 |
| Model type | Reasoning model | Reasoning model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | 1M | 1000K |
| Max output | 128K | 128K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Claude Fable 5 | GPT-5.5 |
|---|---|---|
| Text input | $10 / 1M tokens | $0.5 / 1M tokens |
| Text output | $50 / 1M tokens | $30 / 1M tokens |
| Cache read | $1 / 1M tokens | $0.5 / 1M tokens |
| Cache write | $12.5 / 1M tokens | $6.25 / 1M tokens |
Summary
- Claude Fable 5leads in:AI Agent - Tool Usage (3/3), Coding and Software Engineer (3/3), Math and Reasoning (2/2), Commonsense Reasoning (1/1)
- Tied in:General Knowledge
On average across the 11 shared benchmarks, Claude Fable 5 scores 8.97 higher.
Largest single-benchmark gap: SWE-Bench Pro - Public — Claude Fable 5 80.30 vs GPT-5.5 58.60 (+21.70).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.