TestsBenchmarks · Coding
CursorBench (pre-3.2, legacy)
CursorBench as reported in June 2026 system cards (version not stated); not comparable to later versions.
Measured by independent testersIndependent Reported by the makerVendor-reported
| Thinking levelSetting | |||||||
|---|---|---|---|---|---|---|---|
| 1 | Claude Fable 5 | Anthropic | 72.9% | Maxadaptive thinking, effort=max | Maker's own figureVendor-reportedAnthropic ↗ | Cursor agent | 9 Jun 2026 |
| 2 | Claude Opus 4.8 | Anthropic | 63.8% | Maxadaptive thinking, effort=max | Maker's own figureVendor-reportedAnthropic ↗ | Cursor agent | 30 Jun 2026 |
| 3 | Claude Sonnet 5 | Anthropic | 61.2% | Maxadaptive thinking, effort=max | Maker's own figureVendor-reportedAnthropic ↗ | Cursor agent | 30 Jun 2026 |
| 4 | Claude Sonnet 4.6 | Anthropic | 49.0% | Maxadaptive thinking, effort=max | Maker's own figureVendor-reportedAnthropic ↗ | Cursor agent | 30 Jun 2026 |