Model comparison
LFM2.5-8B-A1B vs Nemotron 3 Nano Omni 30B A3B
Head-to-head evidence from 13 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: LFM2.5-8B-A1B #166 (Estimated); Nemotron 3 Nano Omni 30B A3B #151 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. LFM2.5-8B-A1B and Nemotron 3 Nano Omni 30B A3B share 13 comparable benchmark results. 1 of 8 categories are comparable. 4 results are unique to LFM2.5-8B-A1B; 16 to Nemotron 3 Nano Omni 30B A3B.
Updated July 23, 2026- Shared results
- 13
- LFM2.5-8B-A1B only
- 4
- Nemotron 3 Nano Omni 30B A3B only
- 16
- Comparable categories
- 1 / 8
Pick Nemotron 3 Nano Omni 30B A3B if you want the stronger benchmark profile. LFM2.5-8B-A1B only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.
Confidence note. This is a partial-evidence comparison with 13 shared benchmark results across 6 evidence categories; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Nemotron 3 Nano Omni 30B A3B has the cleaner BenchAlign overall profile here, landing at 44.24 versus 41.42. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
Nemotron 3 Nano Omni 30B A3B's sharpest advantage is in instruction following, where it averages 74.2 against 68.8. The single biggest benchmark swing on the page is IFBench, 56.5% to 74.2%.
Nemotron 3 Nano Omni 30B A3B gives you the larger context window at 256K, compared with 128K for LFM2.5-8B-A1B.
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 | LFM2.5-8B-A1B | Δ | Nemotron 3 Nano Omni 30B A3B |
|---|---|---|---|
| Inst. Following | LFM2.5-8B-A1B68.8 | Margin→ 5.4 | Nemotron 3 Nano Omni 30B A3B74.2 |
| Coding | LFM2.5-8B-A1BNot measured | MarginNo overlap | Nemotron 3 Nano Omni 30B A3B32.0 |
| Knowledge | LFM2.5-8B-A1BNot measured | MarginNo overlap | Nemotron 3 Nano Omni 30B A3B76.3 |
| Math | LFM2.5-8B-A1B50.0 | MarginNo overlap | Nemotron 3 Nano Omni 30B A3BNot measured |
| Multimodal | LFM2.5-8B-A1BNot measured | MarginNo overlap | Nemotron 3 Nano Omni 30B A3B76.3 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
IFBench
Inst. FollowingA 56.5%B 74.2%Winner: Nemotron 3 Nano Omni 30B A3BΔ 17.7IFBench: LFM2.5-8B-A1B scored 56.5%; Nemotron 3 Nano Omni 30B A3B scored 74.2%. Nemotron 3 Nano Omni 30B A3B wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | LFM2.5-8B-A1B | Nemotron 3 Nano Omni 30B A3B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | LFM2.5-8B-A1B$0 input / $0 output | Nemotron 3 Nano Omni 30B A3B$0 input / $0 output | Listed prices are equal. |
| Generation speedtokens per second | LFM2.5-8B-A1BNot available | Nemotron 3 Nano Omni 30B A3BNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | LFM2.5-8B-A1BNot available | Nemotron 3 Nano Omni 30B A3BNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | LFM2.5-8B-A1B128K | Nemotron 3 Nano Omni 30B A3B256K | Nemotron 3 Nano Omni 30B A3B lists the larger context window. |
Benchmark Deep Dive
Agentic5 benchmarks
Coding3 benchmarks
Reasoning2 benchmarks
Knowledge9 benchmarks
| Benchmark | LFM2.5-8B-A1B | Nemotron 3 Nano Omni 30B A3B | Result |
|---|---|---|---|
| AA-GPQA DiamondSource | 51.3% | 46.9% | LFM2.5-8B-A1B leads |
| AA-HLESource | 6.9% | 5.3% | LFM2.5-8B-A1B leads |
| AA-Omniscience IndexSource | -33.3% | -56.0% | LFM2.5-8B-A1B leads |
| AA-Omniscience AccuracySource | 9.4% | 14.8% | Nemotron 3 Nano Omni 30B A3B leads |
| AA-Omniscience Hallucination RateSource | 47.0% | 83.1% | LFM2.5-8B-A1B leads |
| Artificial Analysis Intelligence IndexSource | 8.3% | 14.9% | Nemotron 3 Nano Omni 30B A3B leads |
| MMLU-ProSource | — | 77.3% | Not comparable |
| GPQASource | — | 72.2% | Not comparable |
| GPQA-DSource | — | 72.2% | Not comparable |
Math3 benchmarks
Multimodal8 benchmarks
| Benchmark | LFM2.5-8B-A1B | Nemotron 3 Nano Omni 30B A3B | Result |
|---|---|---|---|
| MMMUSource | — | 70.8% | Not comparable |
| MMLongBench-DocSource | — | 57.5% | Not comparable |
| CharXivSource | — | 76.3% | Not comparable |
| ScreenSpot ProSource | — | 57.8% | Not comparable |
| Video-MME (w/o subtitle)Source | — | 72.2% | Not comparable |
| AI2D_TESTSource | — | 88.5% | Not comparable |
| RefCOCO (avg)Source | — | 90.5% | Not comparable |
| AA-MMMU-ProSource | — | 53.2% | Not comparable |
Frequently Asked Questions (2)
Which is better, LFM2.5-8B-A1B or Nemotron 3 Nano Omni 30B A3B?
Nemotron 3 Nano Omni 30B A3B is ahead on BenchLM's BenchAlign leaderboard, 44.24 to 41.42. The biggest single separator in this matchup is IFBench, where the scores are 56.5% and 74.2%.
Which is better for instruction following, LFM2.5-8B-A1B or Nemotron 3 Nano Omni 30B A3B?
Nemotron 3 Nano Omni 30B A3B has the edge for instruction following in this comparison, averaging 74.2 versus 68.8. Inside this category, IFBench is the benchmark that creates the most daylight between them.
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.