LFM2.5-24B-A2B vs MiniMax M3.1 Flash
LFM2.5-24B-A2B leads on 1 of 1 benchmarks where both are measured. Specs, per-token pricing and benchmark scores from our benchmark database.
Specs & pricing
| LFM2.5-24B-A2B | MiniMax M3.1 Flash | |
|---|---|---|
| Company | Liquid Ai | MiniMax |
| Released | Oct 2026 | Oct 2026 |
| Context window | 128K | 1.0M |
| Input /1M tokens | $0.05 | $0.15 |
| Output /1M tokens | $0.7 | $0.6 |
| Open weights | Yes | No |
Benchmarks
| Benchmark | LFM2.5-24B-A2B | MiniMax M3.1 Flash |
|---|---|---|
| GPQA | 74.4% | — |
| Hallucination Rate (lower is better) | — | 93.0% |
| SWE-bench Verified | 51.0% | — |
| Speed (tok/s) | 184 tok/s | 80 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.