DeepSeek V4.1 Flash 1017 vs LFM2.5-24B-A2B
DeepSeek V4.1 Flash 1017 leads on 1 of 1 benchmarks where both are measured. Specs, per-token pricing and benchmark scores from our benchmark database.
Specs & pricing
| DeepSeek V4.1 Flash 1017 | LFM2.5-24B-A2B | |
|---|---|---|
| Company | DeepSeek | Liquid Ai |
| Released | Oct 2026 | Oct 2026 |
| Context window | 1.0M | 128K |
| Input /1M tokens | $0.15 | $0.05 |
| Output /1M tokens | $0.6 | $0.7 |
| Open weights | Yes | Yes |
Benchmarks
| Benchmark | DeepSeek V4.1 Flash 1017 | LFM2.5-24B-A2B |
|---|---|---|
| GPQA | — | 74.4% |
| SWE-bench Verified | — | 51.0% |
| Speed (tok/s) | 214 tok/s | 184 tok/s |
Scores come from independent evaluators and developers' own announcements; each one links to its source on the benchmarks page. Pricing via vendor pages and OpenRouter.