LiquidAI · Model release
Data as of October 5, 2026 · How the score is built
Released Apr 8, 2026128K context
LFM2.5-VL-450M
Decision readingLFM2.5-VL-450M is tracked, but not publicly ranked yet. The profile exposes 7 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Released Apr 8, 2026 — see all recent releases
LFM2.5-VL-450M will be repriced, updated or retired. Get each notice with its source and date. Follow model changes
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Capability
Unranked
field median 51Not eligible for a public rank
Price
Self-hosted; infrastructure cost varies
input median $0.95No comparable first-party hosted token rate
Speed
Not measured
field median 90 tok/sTime to first token not measured
Context
128Ktokens
field median 256,000Reported for this model; direct source link not stored
Strongest published evidence
Published rows are visible, but no category has enough eligible evidence for a comparative rank.
Validate before choosing
7 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.
Source-linked · 7 displayable benchmark rows
Follow model changesCategory score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticWeight 22%1 benchmarkVerified | Score pending | 1 benchmark | Verified | |||
| CodingWeight 20%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MultimodalWeight 12%3 benchmarksVerified | Score pending | 3 benchmarks | Verified | |||
| KnowledgeRank Not rankedWeight 12%2 benchmarksVerified | 20.8 | 2 benchmarks | Verified | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingWeight 5%1 benchmarkVerified | Score pending | 1 benchmark | Verified | |||
| MathWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured |
7 of 649 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic1/1 verified
- CodingNot measured
- ReasoningNot measured
- Multimodal3/3 verified
- Knowledge2/2 verified
- MultilingualNot measured
- Inst. Following1/1 verified
- MathNot measured
Benchmark ledger
Agentic opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Agentic1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| BFCL v4Berkeley Function Calling Leaderboard v4 | Score21.1% | Versus best verified row Best verified: BTL-3 · 88.5% | Gap67.4 behind | Weight3% ref. weight | Provider exact |
Multimodal3 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| MMMUMassive Multi-discipline Multimodal Understanding | Score32.7% | Versus best verified row Best verified: Qwen3.6-27B · 82.9% | Gap50.2 behind | WeightDisplay only | Provider exact |
| RealWorldQA | Score58.4% | Versus best verified row Best verified: Qwen3.8-Flash-Next · 88.5% | Gap30.1 behind | WeightDisplay only | Provider exact |
| CountBench | Score73.3% | Versus best verified row Best verified: Qwen3.6-27B · 97.8% | Gap24.5 behind | WeightDisplay only | Provider exact |
Knowledge2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| MMLU-ProMassive Multitask Language Understanding Professional | Score19.3% | Versus best verified row Best verified: Qwen3.7 Max · 89.6% | Gap70.3 behind | Weight6% ref. weight | Provider exact |
| GPQAGraduate-Level Google-Proof Q&A | Score25.7% | Versus best verified row Best verified: GPT-6 Astra · 96% | Gap70.3 behind | Weight3% ref. weight | Provider exact |
Inst. Following1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| IFEvalInstruction-Following Eval | Score61.2% | Versus best verified row Best verified: Qwen3.5-27B · 95% | Gap33.8 behind | WeightDisplay only | Provider exact |
Bars run 0–100; the dark tick marks the best source-verified value
All 7 rowsLineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Vl
LFM2.5-VL-450M release history
Radar confirmed these at the source. Use LFM2.5-VL-450M in your work? Explore Radar to follow supported changes and choose your alerts.
Radar
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not published
- Context window
- 128K
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not sourced yet
- Availability
- Not sourced yet
- Cloud regions
- Not tracked yet
- Lifecycle
- Established
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing record
- Self-host
- Open weights available; hardware estimate not sourced
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track LFM2.5-VL-450M, but the public leaderboard excludes this profile until enough non-generated benchmark coverage is available. Only published rows appear above.
LFM2.5-VL-450M is a open weight model with a 128K context window. No explicit reasoning mode is documented in this profile.
Official exact-value snapshot from Liquid AI's April 8, 2026 LFM2.5-VL-450M launch post and matching Hugging Face model card. BenchLM maps only the directly comparable GPQA, MMLU-Pro, IFEval, BFCLv4, MMMU, RealWorldQA, and CountBench results. MMStar, MMBench, POPE, MMVet, BLINK, InfoVQA, OCRBench, MM-IFEval, MMMB, RefCOCO-M, and Multi-IF remain outside BenchLM's current exact benchmark schema.
7 of 649 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Last updated October 5, 2026. Runtime fields remain blank until a sourced snapshot exists.
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Published weights are available, but BenchLM does not yet have a sourced parameter and VRAM profile for this exact model. Hardware cost estimates stay unavailable until that sizing record is complete.
Estimate VRAM from known parametersQuestions
How does LFM2.5-VL-450M perform overall in AI benchmarks?
LFM2.5-VL-450M has 7 source-displayable benchmark rows, but it does not qualify for a public overall rank. The available rows remain visible by category without being converted into a site-wide score. Missing evidence stays blank instead of being estimated from an earlier model.
Is LFM2.5-VL-450M good for knowledge and understanding?
LFM2.5-VL-450M has source-displayable benchmark coverage for knowledge and understanding, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is LFM2.5-VL-450M good for agentic tool use and computer tasks?
LFM2.5-VL-450M has source-displayable benchmark coverage for agentic tool use and computer tasks, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is LFM2.5-VL-450M good for multimodal and grounded tasks?
LFM2.5-VL-450M has source-displayable benchmark coverage for multimodal and grounded tasks, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is LFM2.5-VL-450M good for instruction following?
LFM2.5-VL-450M has source-displayable benchmark coverage for instruction following, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is LFM2.5-VL-450M open source?
LFM2.5-VL-450M is an open-weight model from LiquidAI. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Does LFM2.5-VL-450M have full benchmark coverage on BenchLM?
No. LFM2.5-VL-450M currently has 7 source-displayable rows across 649 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of LFM2.5-VL-450M?
LFM2.5-VL-450M has a reported context window of 128K in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.