Agnes 2.5 Pro Beta vs Claude Opus 5
Agnes 2.5 Pro Beta 
Claude Opus 5 Verdict
- Claude Opus 5 (high) leads on quality: 70.2 vs 60.8.
- Agnes 2.5 Pro Beta is stronger in long context.
- Claude Opus 5 (high) is stronger in agents & tools, composite, knowledge, multimodal, reasoning, coding, human preference, maths.
- Agnes 2.5 Pro Beta is 67× cheaper ($0.150 vs $10.00 per 1M blended).
| Metric | Agnes 2.5 Pro Beta | Claude Opus 5 (high) |
|---|---|---|
| BenchLeader Index | 60.8 | 70.2 |
| Agents & tools score | 64.4 | 66.0 |
| Composite score | 73.7 | 90.2 |
| Knowledge score | 59.2 | 80.3 |
| Long context score | 68.0 | 65.9 |
| Multimodal score | 59.8 | 67.6 |
| Reasoning score | 72.2 | 75.6 |
| Coding score | – | 71.9 |
| Human preference score | – | 69.7 |
| Maths score | – | 72.3 |
| Blended price $/M | $0.150 | $10.00 |
| Output speed | – | 54 tok/s |
| Time to first answer | – | 16.7 s |
| Context window | 1M | 1M |
| Terminal-Bench | – | 50.3% |
| OSWorld-Verified 2.0 | – | 29.0% |
| SciCode | – | 54.3% |
| WeirdML | – | 91.6% |
| LMArena Text | – | 1493 |
| LMArena Hard Prompts | – | 1517 |
| LMArena Coding | – | 1533 |
| LMArena WebDev | – | 1660 |
| LMArena Vision | – | 1321 |
| LMArena Agent | – | 10.2 |
| AA Intelligence Index | 35.2 | 48.2 |
| AA-LCR | 83.0% | 79.0% |
| MMMU-Pro | 75.4% | 82.4% |
| AA-Omniscience | -10.5 | 33.7 |
| GPQA Diamond (AA) | 90.5% | 93.7% |
| Humanity's Last Exam (AA) | 37.5% | 52.8% |
| SciCode (AA) | 48.8% | 55.4% |
| ARC-AGI-1 | – | 97.5% |
| ARC-AGI-2 | – | 88.3% |
| ARC-AGI-3 | – | 30.2% |
| CritPt | 15.7% | 28.3% |
| GDPval (AA) | 43.8% | 56.5% |
| τ²-Bench Banking (AA) | 35.7% | 44.7% |
| LMArena Maths | – | 1525 |
| LMArena Creative Writing | – | 1474 |
| LMArena Instruction Following | – | 1499 |
| LMArena Multi-turn | – | 1484 |
| LMArena Longer Queries | – | 1508 |
| LMArena Document | – | 1490 |
| DeepSWE | – | 72.8% |
| CursorBench | – | 66.7% |
| ALE-Bench | – | 2164.6 |
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 Opus 5: questions
- Is Agnes 2.5 Pro Beta better than Claude Opus 5?
- Claude Opus 5 (high) leads on quality: 70.2 vs 60.8. The BenchLeader Index combines every independent quality benchmark; Claude Opus 5 (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 Opus 5 for agentic tasks?
- Claude Opus 5 scores higher in agentic tasks (66 vs 64 on the category index, where 50 is average).
- Which is cheaper, Agnes 2.5 Pro Beta or Claude Opus 5?
- Agnes 2.5 Pro Beta is cheaper: $0.150 against $10.00 per million tokens, blended at three input tokens per output token.
- Which has the larger context window?
- Both accept 1M tokens of context.