Benchmarks · reasoning
PPBench
Score: max success rate. Collected by Jake Boggs' benchmark dashboard.
53 models · 57 results · data as of 2026-10-29 · ppbench.com ↗
Leaderboard
Fable 5 max
All results
57 rows| # | Model | Effort | PPBench |
|---|---|---|---|
| 1 | Fable 5 | max | 97.6% |
| 2 | GPT-5.5 | xhigh | 83.3% |
| 3 | GPT-5.4 | xhigh | 70.2% |
| 4 | GPT-5.2 | xhigh | 56.0% |
| 5 | Opus 4.7 | max | 50.0% |
| 6 | Gemini 3.5 Flash | high | 41.9% |
| 7 | Qwen 3.7 Max | max | 40.0% |
| 8 | Opus 4.6 | max | 36.7% |
| 9 | GPT-5.2 | high | 36.7% |
| 10 | Gemini 3.1 Pro | high | 33.3% |
| 11 | Sonnet 4.6 | max | 26.7% |
| 12 | GLM 5.2 | max | 26.7% |
| 13 | GPT-5.2 Pro | xhigh | 26.7% |
| 14 | GPT-5.2 | medium | 23.3% |
| 15 | Kimi K2.6 | max | 20.0% |
| 16 | Gemini 3 Pro | high | 16.7% |
| 17 | Kimi K2.7 Code | max | 16.7% |
| 18 | Qwen 3.7 Plus | high | 16.7% |
| 19 | GPT-5.2 | low | 10.0% |
| 20 | Qwen 3.6 Plus | max | 10.0% |
| 21 | GPT-5.1 | medium | 7.7% |
| 22 | MiniMax M3 | max | 7.1% |
| 23 | Opus 4.5 | high | 6.7% |
| 24 | Gemini 3 Flash | high | 6.7% |
| 25 | Grok 4.20 | xhigh | 6.7% |
| 26 | GPT-5 | medium | 6.0% |
| 27 | Kimi K2.5 | max | 6.0% |
| 28 | Grok 4.1 Fast | high | 5.7% |
| 29 | DeepSeek V4 Pro | max | 4.0% |
| 30 | Sonnet 4.5 | high | 3.3% |