Agnes 2.5 Pro Beta vs Claude Fable 5.1
Agnes 2.5 Pro Beta 
Claude Fable 5.1 Verdict
- Claude Fable 5.1 (high) leads on quality: 72.0 vs 60.8.
- Agnes 2.5 Pro Beta is stronger in multimodal.
- Claude Fable 5.1 (high) is stronger in agents & tools, composite, knowledge, long context, reasoning, coding.
- Agnes 2.5 Pro Beta is 133× cheaper ($0.150 vs $20.00 per 1M blended).
| Metric | Agnes 2.5 Pro Beta | Claude Fable 5.1 (high) |
|---|---|---|
| BenchLeader Index | 60.8 | 72.0 |
| Agents & tools score | 64.4 | 66.6 |
| Composite score | 73.7 | 94.0 |
| Knowledge score | 59.2 | 83.7 |
| Long context score | 68.0 | 68.4 |
| Multimodal score | 59.8 | – |
| Reasoning score | 72.2 | 81.0 |
| Coding score | – | 74.1 |
| Blended price $/M | $0.150 | $20.00 |
| Output speed | – | 55 tok/s |
| Time to first answer | – | 14.7 s |
| Context window | 1M | 1M |
| Terminal-Bench | – | 54.5% |
| SciCode | – | 57.6% |
| WeirdML | – | 92.3% |
| APEX-Agents | – | 44.4% |
| AA Intelligence Index | 35.2 | 51.2 |
| AA-LCR | 83.0% | 83.7% |
| MMMU-Pro | 75.4% | – |
| AA-Omniscience | -10.5 | 40.8 |
| GPQA Diamond (AA) | 90.5% | 90.6% |
| Humanity's Last Exam (AA) | 37.5% | 55.9% |
| SciCode (AA) | 48.8% | 58.7% |
| ARC-AGI-1 | – | 96.0% |
| ARC-AGI-2 | – | 88.8% |
| CritPt | 15.7% | 30.3% |
| GDPval (AA) | 43.8% | 57.5% |
| τ²-Bench Banking (AA) | 35.7% | 43.1% |
| MirrorCode | – | 73.3% |
| CursorBench | – | 69.4% |
| ALE-Bench | – | 2143.2 |
Data as of 2026-09-19. Best configuration of each model; every score links to its source on the model pages.
Agnes 2.5 Pro Beta vs Claude Fable 5.1: questions
- Is Agnes 2.5 Pro Beta better than Claude Fable 5.1?
- Claude Fable 5.1 (high) leads on quality: 72.0 vs 60.8. The BenchLeader Index combines every independent quality benchmark; Claude Fable 5.1 (high) is ahead overall as of 2026-09-19, but check the category scores for your use.
- Is Agnes 2.5 Pro Beta better than Claude Fable 5.1 for agentic tasks?
- Claude Fable 5.1 scores higher in agentic tasks (67 vs 64 on the category index, where 50 is average).
- Which is cheaper, Agnes 2.5 Pro Beta or Claude Fable 5.1?
- Agnes 2.5 Pro Beta is cheaper: $0.150 against $20.00 per million tokens, blended at three input tokens per output token.
- Which has the larger context window?
- Both accept 1M tokens of context.