Model comparison
LFM2.5-8B-A1B vs ZAYA1-74B-Preview
Head-to-head evidence from 1 shared benchmark result across 1 category. Overall scores shown here use the public BenchAlign v5 ranking lane.
BenchAlign evidence: LFM2.5-8B-A1B estimated; ZAYA1-74B-Preview not scored. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. LFM2.5-8B-A1B and ZAYA1-74B-Preview share 1 comparable benchmark result. 1 of 8 categories are comparable. 17 results are unique to LFM2.5-8B-A1B; 6 to ZAYA1-74B-Preview.
Updated July 16, 2026- Shared results
- 1
- LFM2.5-8B-A1B only
- 17
- ZAYA1-74B-Preview only
- 6
- Comparable categories
- 1 / 8
Pick ZAYA1-74B-Preview 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 1 shared benchmark result across 1 evidence category; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
ZAYA1-74B-Preview is clearly ahead on the provisional aggregate, 55 to 37. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
ZAYA1-74B-Preview's sharpest advantage is in mathematics, where it averages 76.4 against 50. The single biggest benchmark swing on the page is AIME26, 50.0% to 76.4%.
ZAYA1-74B-Preview 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 | ZAYA1-74B-Preview |
|---|---|---|---|
| Math | LFM2.5-8B-A1B50.0 | Margin→ 26.4 | ZAYA1-74B-Preview76.4 |
| Coding | LFM2.5-8B-A1BNot measured | MarginNo overlap | ZAYA1-74B-Preview53.2 |
| Knowledge | LFM2.5-8B-A1BNot measured | MarginNo overlap | ZAYA1-74B-Preview66.1 |
| Inst. Following | LFM2.5-8B-A1B68.8 | MarginNo overlap | ZAYA1-74B-PreviewNot measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
AIME26
MathA 50.0%B 76.4%Winner: ZAYA1-74B-PreviewΔ 26.4AIME26: LFM2.5-8B-A1B scored 50.0%; ZAYA1-74B-Preview scored 76.4%. ZAYA1-74B-Preview 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 | ZAYA1-74B-Preview | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | LFM2.5-8B-A1B$0 input / $0 output | ZAYA1-74B-Preview$0 input / $0 output | Listed prices are equal. |
| Generation speedtokens per second | LFM2.5-8B-A1BNot available | ZAYA1-74B-PreviewNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | LFM2.5-8B-A1BNot available | ZAYA1-74B-PreviewNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | LFM2.5-8B-A1B128K | ZAYA1-74B-Preview256K | ZAYA1-74B-Preview lists the larger context window. |
Benchmark Deep Dive
Agentic3 benchmarks
Coding4 benchmarks
Reasoning2 benchmarks
Knowledge9 benchmarks
| Benchmark | LFM2.5-8B-A1B | ZAYA1-74B-Preview | Result |
|---|---|---|---|
| AA-GPQA DiamondSource | 51.3% | — | Not comparable |
| AA-HLESource | 6.9% | — | Not comparable |
| AA-Omniscience IndexSource | -33.3% | — | Not comparable |
| AA-Omniscience AccuracySource | 9.4% | — | Not comparable |
| AA-Omniscience Hallucination RateSource | 47.0% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 8.3% | — | Not comparable |
| MMLU-ProSource | — | 68.1% | Not comparable |
| GPQASource | — | 57.3% | Not comparable |
| GPQA-DSource | — | 57.3% | Not comparable |
MathZAYA1-74B-Preview wins3 benchmarks
Frequently Asked Questions (2)
Which is better, LFM2.5-8B-A1B or ZAYA1-74B-Preview?
ZAYA1-74B-Preview is ahead on BenchLM's provisional leaderboard, 55 to 37. The biggest single separator in this matchup is AIME26, where the scores are 50.0% and 76.4%.
Which is better for math, LFM2.5-8B-A1B or ZAYA1-74B-Preview?
ZAYA1-74B-Preview has the edge for math in this comparison, averaging 76.4 versus 50. Inside this category, AIME26 is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
The AI models change fast. We track them for you.
A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.