LiquidAI
availableShows if the model has enough results for an index.LFM2.5-8B-A1B
LFM2.5-8B-A1B is a reasoning model from LiquidAI. 15 benchmarks count toward its score, in 6 categories.
IndexOverall score out of 100.32.0 ±7.2
CoverageShare of the index weight with results.70%
SpeedOutput tokens per second.335/s
Input / 1MUS dollars per 1M input tokens.Free
Output / 1MUS dollars per 1M output tokens.Free
ContextMaximum tokens in one request.128K
EloLMArena rating and rank.N/A
The index is a score out of 100. The ± range shows how much it can change.
CapabilitiesScore per category, out of 100.
Out of 100Results
15 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result as a score out of 100. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| Instruction-Following Eval | Instruction | 91.8% | 49.2 | — | — | Jeffrey Zhou et al. |
| MATH-500 Problem Set | Math | 88.8% | 41.0 | — | — | Dan Hendrycks et al. |
| τ²-Bench Tool-Agent-User Evaluation | Agentic | 88.1% | 62.0 | — | — | Victor Barres et al. |
| Instruction Following Benchmark | Instruction | 56.5% | 31.8 | — | — | Benchmark authors |
| Artificial Analysis IFBench | Instruction | 55.6% | 45.5 | — | — | Artificial Analysis |
| Artificial Analysis GPQA Diamond | Knowledge | 51.3% | 21.1 | — | — | Artificial Analysis |
| AIME 2026 | Math | 50.0% | 20.6 | — | — | Qwen |
| Berkeley Function Calling Leaderboard v4 | Agentic | 49.7% | 34.1 | — | — | Arcee AI |
| American Invitational Mathematics Examination 2025 | Math | 42.5% | 12.0 | — | — | Mathematical Association of America |
| EuroEval French | Multilingual | 29.6% | 39.3 | — | — | EuroEval |
| EuroEval Spanish | Multilingual | 24.1% | 32.5 | — | — | EuroEval |
| EuroEval Portuguese | Multilingual | 22.0% | 29.8 | — | — | EuroEval |
| EuroEval Dutch | Multilingual | 21.1% | 28.6 | — | — | EuroEval |
| EuroEval Italian | Multilingual | 20.8% | 28.3 | — | — | EuroEval |
| EuroEval German | Multilingual | 20.6% | 28.0 | — | — | EuroEval |
| EuroEval Swedish | Multilingual | 14.3% | 20.2 | — | — | EuroEval |
| EuroEval Polish | Multilingual | 10.8% | 15.8 | — | — | EuroEval |
| Artificial Analysis Omniscience Accuracy | Knowledge | 9.4% | 25.5 | — | — | Artificial Analysis |
| Artificial Analysis Intelligence Index | Knowledge | 7.2% | 31.4 | — | — | Artificial Analysis |
| Artificial Analysis Humanity's Last Exam | Knowledge | 6.9% | 32.0 | — | — | Artificial Analysis |
| Artificial Analysis Long Context Reasoning | Reasoning | 0.0% | 8.3 | — | — | Artificial Analysis |
| Critical Physics Tasks | Reasoning | 0.0% | 38.4 | — | — | Artificial Analysis |
15 benchmarks count, from 22 of 22 results. A grey row does not count. Too few models took that benchmark.