Model comparison
LFM2.5-VL-1.6B-Extract vs LFM2.5-VL-450M-Extract
Head-to-head evidence from 3 shared benchmark results across 1 category. Overall scores shown here use the public BenchAlign v5 ranking lane.
Sibling matchup inside the LFM2.5-VL Extract family.
Evidence parity. LFM2.5-VL-1.6B-Extract and LFM2.5-VL-450M-Extract share 3 comparable benchmark results. 0 of 8 categories are comparable. 12 results are unique to LFM2.5-VL-1.6B-Extract; 0 to LFM2.5-VL-450M-Extract.
Updated July 23, 2026- Shared results
- 3
- LFM2.5-VL-1.6B-Extract only
- 12
- LFM2.5-VL-450M-Extract only
- 0
- Comparable categories
- 0 / 8
Benchmark data for LFM2.5-VL-1.6B-Extract and LFM2.5-VL-450M-Extract is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 3 shared benchmark results across 1 evidence category; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | LFM2.5-VL-1.6B-Extract | LFM2.5-VL-450M-Extract | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | LFM2.5-VL-1.6B-ExtractNot available | LFM2.5-VL-450M-ExtractNot available | A complete price comparison is not available. |
| Generation speedtokens per second | LFM2.5-VL-1.6B-ExtractNot available | LFM2.5-VL-450M-ExtractNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | LFM2.5-VL-1.6B-ExtractNot available | LFM2.5-VL-450M-ExtractNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | LFM2.5-VL-1.6B-Extract128K | LFM2.5-VL-450M-Extract128K | Listed context windows are equal. |
Benchmark Deep Dive
Agentic1 benchmarks
| Benchmark | LFM2.5-VL-1.6B-Extract | LFM2.5-VL-450M-Extract | Result |
|---|---|---|---|
| τ²-bench resultsSource | 8.5% | — | Not comparable |
Coding1 benchmarks
| Benchmark | LFM2.5-VL-1.6B-Extract | LFM2.5-VL-450M-Extract | Result |
|---|---|---|---|
| AA-SciCodeSource | 3.0% | — | Not comparable |
Reasoning2 benchmarks
Knowledge6 benchmarks
| Benchmark | LFM2.5-VL-1.6B-Extract | LFM2.5-VL-450M-Extract | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 1.0% | — | Not comparable |
| AA-GPQA DiamondSource | 28.9% | — | Not comparable |
| AA-HLESource | 5.1% | — | Not comparable |
| AA-Omniscience IndexSource | -83.9% | — | Not comparable |
| AA-Omniscience AccuracySource | 5.2% | — | Not comparable |
| AA-Omniscience Hallucination RateSource | 94.0% | — | Not comparable |
Multimodal4 benchmarks
| Benchmark | LFM2.5-VL-1.6B-Extract | LFM2.5-VL-450M-Extract | Result |
|---|---|---|---|
| Liquid Extract JSON ValiditySource | 99.6% | 98.9% | LFM2.5-VL-1.6B-Extract leads |
| Liquid Extract F1Source | 99.6% | 98.8% | LFM2.5-VL-1.6B-Extract leads |
| Liquid Extract VLM JudgeSource | 90.6% | 84.5% | LFM2.5-VL-1.6B-Extract leads |
| AA-MMMU-ProSource | 26.5% | — | Not comparable |
Inst. Following1 benchmarks
| Benchmark | LFM2.5-VL-1.6B-Extract | LFM2.5-VL-450M-Extract | Result |
|---|---|---|---|
| AA-IFBenchSource | 33.1% | — | Not comparable |
Frequently Asked Questions (2)
Can I compare LFM2.5-VL-1.6B-Extract and LFM2.5-VL-450M-Extract on BenchLM yet?
Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.
Why does this comparison show “coming soon”?
BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.
Related Comparisons
Explore More
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.