Liquid AILFM2.5-2.6B
Not yet ranked: too few independent results so far. Released 4 Aug 2026.
- Blended price
- –
- Output speed
- 199 tok/s
- First answer
- 14 s
- Context
- 128k
- Knowledge59
- Long context28
- Composite40
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 | 55.8%#381 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 6.2%#327 | Artificial Analysis |
Coding
| Benchmark | default | Source |
|---|---|---|
| SciCode (AA)not in index | 14.3%#162 | Artificial Analysis |
Knowledge
| Benchmark | default | Source |
|---|---|---|
| AA-Omniscience | -10.9#148 | Artificial Analysis |
Long context
| Benchmark | default | Source |
|---|---|---|
| AA-LCR | 5.7%#413 | Artificial Analysis |
Composite
| Benchmark | default | Source |
|---|---|---|
| AA Intelligence Index | 8.4#361 | 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 | – | – | 15.1 s |
| Summarise a 30-page report | 12,000 / 600 | – | – | 16.6 s |
| Code edit | 6,000 / 1,500 | – | – | 21.1 s |
| Agentic coding session | 60,000 / 4,000 | – | – | 33.6 s |
| Structured extraction | 2,000 / 200 | – | – | 14.6 s |
See also
Data as of 9 Sept 2026. Compare with another model.