LiquidAI
partialShows if the model has enough results for an index.LFM2.5-VL-3B
LFM2.5-VL-3B is a non-reasoning model from LiquidAI. 7 benchmarks count toward its score, in 3 categories.
IndexOverall score out of 100.Unranked
CoverageShare of the index weight with results.35%
SpeedOutput tokens per second.—
Input / 1MUS dollars per 1M input tokens.Free
Output / 1MUS dollars per 1M output tokens.Free
ContextMaximum tokens in one request.32K
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
7 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. |
|---|---|---|---|---|---|---|
| RefCOCO average | Multimodal | 87.9% | — | — | — | RefCOCO dataset authors |
| CountBench | Multimodal | 87.3% | — | — | — | Qwen |
| Instruction-Following Eval | Instruction | 82.3% | 28.6 | — | — | Jeffrey Zhou et al. |
| RealWorldQA | Multimodal | 73.1% | 32.9 | — | — | Qwen |
| Massive Multi-discipline Multimodal Understanding | Multimodal | 48.4% | 18.5 | — | — | MMMU authors |
| OCRBench V2 | Multimodal | 47.5% | — | — | — | OCRBench authors |
| SimpleVQA | Multimodal | 35.4% | 21.4 | — | — | Z.AI |
| Berkeley Function Calling Leaderboard v4 | Agentic | 32.5% | 16.5 | — | — | Arcee AI |
| Massive Multi-discipline Multimodal Understanding Pro | Multimodal | 30.5% | 5.0 | — | — | MMMU-Pro authors |
| Instruction Following Benchmark | Instruction | 25.8% | 5.0 | — | — | Benchmark authors |
7 benchmarks count, from 7 of 10 results. A grey row does not count. Too few models took that benchmark.