LFM2.5-VL-3B
LiquidAI · Open Weight · bench-align-v5
Self-hostedCapability shape
Seven axes from the ranking source. A missing axis is drawn as a gap.
Runtime service evidence
Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim.
Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.
Evidence key: ObservedUnavailable
| Measurement | Value | Observed | Last good | Evidence |
|---|---|---|---|---|
| Time to first token | Unavailable | Unavailable | Unavailable | |
| Throughput | Unavailable | Unavailable | Unavailable |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
Endpoint and price matrix
Every published price component, including cache reads and writes.
Workload-aware monthly cost example
10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. This uses the same calculator as the cost simulator, so an unavailable applicable rate makes the example unavailable too.
Benchmark record
10 matched benchmark rows with their published value, unit, and provenance.
Instruction Following
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| IFEval Instruction-Following Eval | 82.3 | 541 prompts across 25 instruction types | Instruction precision | Instruction-Following Evaluation for Large Language Models |
| IFBench Instruction Following Benchmark | 25.8 | — | — | BenchLM |
Agentic
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| BFCL v4 Berkeley Function Calling Leaderboard v4 | 32.5 | Function-calling tasks | Advanced tool use | Trinity-Large-Thinking: Scaling an Open Source Frontier Agent |
Multimodal & Grounded
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| MMMU Massive Multi-discipline Multimodal Understanding | 48.4 | Multimodal academic reasoning | Frontier multimodal | MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI |
| MMMU-Pro Massive Multi-discipline Multimodal Understanding Pro | 30.5 | Multimodal academic reasoning | Frontier multimodal | MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark |
| OCRBench V2 OCRBench V2 | 47.5 | Image OCR tasks | Native visual text understanding | OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning |
| RealWorldQA RealWorldQA | 73.1 | Real-world visual question answering | General visual reasoning | Qwen3.6 launch benchmarks |
| CountBench CountBench | 87.3 | Visual counting tasks | Fine-grained visual perception | Qwen3.6 launch benchmarks |
| RefCOCO (avg) RefCOCO average | 87.9 | Referring-expression grounding | Fine-grained visual grounding | RefCOCO referring expression datasets |
| SimpleVQA SimpleVQA | 35.4 | Visual QA tasks | General visual understanding | GLM-5V-Turbo |
Lifecycle and limitations log
Lifecycle events the source associates with this model, plus what this profile does not claim.
That is not evidence the model has no lifecycle plan — only that this source published none.