Coding and agents
Task-specific coding and agentic benchmark leaders.
Last validated snapshot: October 27, 2026
Agentic
Artificial Analysis Agentic Index · Higher is better
- Eligible
- 167
- Candidates
- 715
- Coverage
- 23.4%
| Rank | Model | Creator | Artificial Analysis Agentic Index | Since prior snapshot |
|---|---|---|---|---|
| 1 | Claude Fable 5.1 (Max, Default Fallback) | Anthropic | 57.9 | No change |
| 2 | Claude Fable 5.1 (Xhigh, Default Fallback) | Anthropic | 57.2 | No change |
| 3 | Claude Opus 5 (Max) | Anthropic | 56.5 | No change |
Coding
Artificial Analysis Coding Index · Higher is better
- Eligible
- 258
- Candidates
- 715
- Coverage
- 36.1%
| Rank | Model | Creator | Artificial Analysis Coding Index | Since prior snapshot |
|---|---|---|---|---|
| 1 | Claude Fable 5.1 (Max, Default Fallback) | Anthropic | 81.6 | No change |
| 2 | Claude Fable 5.1 (Xhigh, Default Fallback) | Anthropic | 80.7 | No change |
| 3 | Claude Fable 5.1 (High, Default Fallback) | Anthropic | 79.1 | No change |
Data source: Artificial Analysis .