Model comparison
LFM2.5-8B-A1B vs Muse Spark
Head-to-head evidence from 12 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
BenchAlign evidence: LFM2.5-8B-A1B estimated; Muse Spark supported. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. LFM2.5-8B-A1B and Muse Spark share 12 comparable benchmark results. 1 of 8 categories are comparable. 6 results are unique to LFM2.5-8B-A1B; 29 to Muse Spark.
Updated July 16, 2026- Shared results
- 12
- LFM2.5-8B-A1B only
- 6
- Muse Spark only
- 29
- Comparable categories
- 1 / 8
Pick Muse Spark if you want the stronger benchmark profile. LFM2.5-8B-A1B only becomes the better choice if mathematics is the priority.
Confidence note. This is a partial-evidence comparison with 12 shared benchmark results across 5 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
Muse Spark is clearly ahead on the provisional aggregate, 63 to 37. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Muse Spark gives you the larger context window at 262K, 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 | Muse Spark |
|---|---|---|---|
| Math | LFM2.5-8B-A1B50.0 | Margin← 17.1 | Muse Spark32.9 |
| Agentic | LFM2.5-8B-A1BNot measured | MarginNo overlap | Muse Spark59.0 |
| Coding | LFM2.5-8B-A1BNot measured | MarginNo overlap | Muse Spark67.8 |
| Reasoning | LFM2.5-8B-A1BNot measured | MarginNo overlap | Muse Spark42.5 |
| Knowledge | LFM2.5-8B-A1BNot measured | MarginNo overlap | Muse Spark50.4 |
| Multimodal | LFM2.5-8B-A1BNot measured | MarginNo overlap | Muse Spark82.5 |
| Inst. Following | LFM2.5-8B-A1B68.8 | MarginNo overlap | Muse SparkNot measured |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | LFM2.5-8B-A1B | Muse Spark | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | LFM2.5-8B-A1B$0 input / $0 output | Muse SparkNot available | A complete price comparison is not available. |
| Generation speedtokens per second | LFM2.5-8B-A1BNot available | Muse SparkNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | LFM2.5-8B-A1BNot available | Muse SparkNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | LFM2.5-8B-A1B128K | Muse Spark262K | Muse Spark lists the larger context window. |
Benchmark Deep Dive
Agentic9 benchmarks
| Benchmark | LFM2.5-8B-A1B | Muse Spark | Result |
|---|---|---|---|
| BFCL v4Source | 49.7% | — | Not comparable |
| τ²-bench resultsSource | 16.1% | 91.5% | Muse Spark leads |
| Terminal-Bench 2.0Source | — | 59% | Not comparable |
| DeepSearchQASource | — | 74.8% | Not comparable |
| CyberGymSource | — | 43.5% | Not comparable |
| Claw-EvalSource | — | 63.8% | Not comparable |
| AA Agentic IndexSource | — | 28.7% | Not comparable |
| GDPval-AASource | — | 32.2% | Not comparable |
| GDPval-AASource | — | 1144 | Not comparable |
Coding7 benchmarks
| Benchmark | LFM2.5-8B-A1B | Muse Spark | Result |
|---|---|---|---|
| Terminal-Bench HardSource | 4.5% | 45.5% | Muse Spark leads |
| AA-SciCodeSource | 7.8% | 51.5% | Muse Spark leads |
| SWE-bench VerifiedSource | — | 77.4% | Not comparable |
| SWE-bench ProSource | — | 52.4% | Not comparable |
| LiveCodeBench ProSource | — | 80.0% | Not comparable |
| Vibe Code BenchSource | — | 19.67% | Not comparable |
| AA Coding IndexSource | — | 58.6% | Not comparable |
Reasoning3 benchmarks
Knowledge11 benchmarks
| Benchmark | LFM2.5-8B-A1B | Muse Spark | Result |
|---|---|---|---|
| AA-GPQA DiamondSource | 51.3% | 88.4% | Muse Spark leads |
| AA-HLESource | 6.9% | 39.9% | Muse Spark leads |
| AA-Omniscience IndexSource | -33.3% | 4.1% | Muse Spark leads |
| AA-Omniscience AccuracySource | 9.4% | 44.6% | Muse Spark leads |
| AA-Omniscience Hallucination RateSource | 47.0% | 73.2% | LFM2.5-8B-A1B leads |
| Artificial Analysis Intelligence IndexSource | 8.3% | 43.1% | Muse Spark leads |
| GPQA-DSource | — | 89.5% | Not comparable |
| HLESource | — | 50.4% | Not comparable |
| HLE w/o toolsSource | — | 42.8% | Not comparable |
| HealthBench HardSource | — | 42.8% | Not comparable |
| MedXpertQA (Text)Source | — | 52.6% | Not comparable |
MathLFM2.5-8B-A1B wins5 benchmarks
Multimodal9 benchmarks
| Benchmark | LFM2.5-8B-A1B | Muse Spark | Result |
|---|---|---|---|
| CharXivSource | — | 86.4% | Not comparable |
| MMMU-ProSource | — | 80.4% | Not comparable |
| ERQASource | — | 64.7% | Not comparable |
| SimpleVQASource | — | 71.3% | Not comparable |
| ScreenSpot ProSource | — | 84.1% | Not comparable |
| ZeroBenchSource | — | 33.0% | Not comparable |
| MedXpertQA (MM)Source | — | 78.4% | Not comparable |
| GDPval-AASource | — | 1444 | Not comparable |
| AA-MMMU-ProSource | — | 80.5% | Not comparable |
Frequently Asked Questions (2)
Which is better, LFM2.5-8B-A1B or Muse Spark?
Muse Spark is ahead on BenchLM's provisional leaderboard, 63 to 37.
Which is better for math, LFM2.5-8B-A1B or Muse Spark?
LFM2.5-8B-A1B has the edge for math in this comparison, averaging 50 versus 32.9. Muse Spark stays close enough that the answer can still flip depending on your workload.
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.