Model comparison
DeepSeek V3 vs LFM2.5-VL-1.6B-Extract
Head-to-head evidence from 11 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: DeepSeek V3 #147 (Supported); LFM2.5-VL-1.6B-Extract unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. DeepSeek V3 and LFM2.5-VL-1.6B-Extract share 11 comparable benchmark results. 0 of 8 categories are comparable. 11 results are unique to DeepSeek V3; 4 to LFM2.5-VL-1.6B-Extract.
Updated July 23, 2026- Shared results
- 11
- DeepSeek V3 only
- 11
- LFM2.5-VL-1.6B-Extract only
- 4
- Comparable categories
- 0 / 8
Benchmark data for DeepSeek V3 and LFM2.5-VL-1.6B-Extract is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 11 shared benchmark results across 5 evidence categories; 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.
| Category | DeepSeek V3 | Δ | LFM2.5-VL-1.6B-Extract |
|---|---|---|---|
| Coding | DeepSeek V338.9 | MarginNo overlap | LFM2.5-VL-1.6B-ExtractNot measured |
| Knowledge | DeepSeek V372.7 | MarginNo overlap | LFM2.5-VL-1.6B-ExtractNot measured |
| Math | DeepSeek V31.7 | MarginNo overlap | LFM2.5-VL-1.6B-ExtractNot measured |
| Inst. Following | DeepSeek V386.1 | MarginNo overlap | LFM2.5-VL-1.6B-ExtractNot measured |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | DeepSeek V3 | LFM2.5-VL-1.6B-Extract | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | DeepSeek V3$0.27 input / $1.1 output | LFM2.5-VL-1.6B-ExtractNot available | A complete price comparison is not available. |
| Generation speedtokens per second | DeepSeek V3Not available | LFM2.5-VL-1.6B-ExtractNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | DeepSeek V3Not available | LFM2.5-VL-1.6B-ExtractNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | DeepSeek V3128K | LFM2.5-VL-1.6B-Extract128K | Listed context windows are equal. |
Benchmark Deep Dive
Agentic4 benchmarks
Coding4 benchmarks
Reasoning2 benchmarks
Knowledge8 benchmarks
| Benchmark | DeepSeek V3 | LFM2.5-VL-1.6B-Extract | Result |
|---|---|---|---|
| GPQASource | 59.1% | — | Not comparable |
| MMLU-ProSource | 75.9% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 14.2% | 1.0% | DeepSeek V3 leads |
| AA-GPQA DiamondSource | 55.7% | 28.9% | DeepSeek V3 leads |
| AA-HLESource | 3.6% | 5.1% | LFM2.5-VL-1.6B-Extract leads |
| AA-Omniscience IndexSource | -41.3% | -83.9% | DeepSeek V3 leads |
| AA-Omniscience AccuracySource | 25.4% | 5.2% | DeepSeek V3 leads |
| AA-Omniscience Hallucination RateSource | 89.4% | 94.0% | DeepSeek V3 leads |
Math1 benchmarks
| Benchmark | DeepSeek V3 | LFM2.5-VL-1.6B-Extract | Result |
|---|---|---|---|
| FrontierMath v2 (Tiers 1-3)Source | 1.724% | — | Not comparable |
Multimodal5 benchmarks
Frequently Asked Questions (3)
Can I compare DeepSeek V3 and LFM2.5-VL-1.6B-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.
What data is available for DeepSeek V3 and LFM2.5-VL-1.6B-Extract today?
DeepSeek V3: $0.27 input / $1.10 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
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.