Agnes 2.5 Pro Alpha
Not yet ranked: too few independent results so far. Released 24 Jul 2026.
- Blended price
- $0.563/M
- $0.450 in · $0.900 out
- Output speed
- 174 tok/s
- First answer
- 14 s
- Context
- 1M
- Knowledge52
- Long context64
- Composite63
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | default | Source |
|---|---|---|
| GPQA Diamond (AA)not in index | 87.6%#95 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 33.6%#89 | Artificial Analysis |
Coding
| Benchmark | default | Source |
|---|---|---|
| SciCode (AA)not in index | 42.9%#101 | Artificial Analysis |
Knowledge
| Benchmark | default | Source |
|---|---|---|
| AA-Omniscience | -25.1#199 | Artificial Analysis |
Long context
| Benchmark | default | Source |
|---|---|---|
| AA-LCR | 75.7%#107 | Artificial Analysis |
Composite
| Benchmark | default | Source |
|---|---|---|
| AA Intelligence Index | 26.8#103 | Artificial Analysis |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0005 | – | 16.1 s |
| Summarise a 30-page report | 12,000 / 600 | $0.0059 | – | 17.9 s |
| Code edit | 6,000 / 1,500 | $0.0041 | – | 23.1 s |
| Agentic coding session | 60,000 / 4,000 | $0.031 | – | 37.5 s |
| Structured extraction | 2,000 / 200 | $0.0011 | – | 15.6 s |
See also
Data as of 9 Sept 2026. Compare with another model.