FrontierCode 2.0 leaderboard
As of November 14, 2026, among the results listed here, Anthropic Claude Fable 5.2 has the highest reported FrontierCode 2.0 score, 49.1% (Xhigh effort), published by Anthropic, ahead of Anthropic Claude Opus 5.5 at 45.5%. 4 models have a FrontierCode 2.0 result in our records.
Scores as the model makers published them, not re-run by us; each row links to its announcement.
Best reported score
49.1%
Reported by Anthropic, November 9, 2026 · Xhigh effort
4 models ranked · 2 makers
| Rank | Model | Score | Setting | Reported by | Date |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.2 | 49.1% | Xhigh effort | Anthropic | November 9, 2026 (model release) |
| 2 | Claude Opus 5.5 | 45.5% | Not published | Anthropic | November 9, 2026 (model release) |
| 3 | Claude Fable 5.1 | 32.4% | Xhigh effort | Anthropic | November 9, 2026 (model release) |
| 4 | Mistral Large 4 | 19.7% | Not published | Mistral AI | October 29, 2026 |
How much to trust these numbers
- Source
- Reported by the model makers themselves. Not re-run by LLMBenchmark or anyone independent.
- Settings
- Settings differ between makers. Check the Setting column before comparing two scores.
- Spread
- 49.1% to 19.7% across 4 models.
- Freshness
- Newest result published November 9, 2026; oldest October 29, 2026.
What FrontierCode 2.0 measures
It tests whether models produce mergeable code changes beyond explicit specifications, with higher scores indicating better performance on these tasks. Source: FrontierCode Leaderboard