Compare / EXAONE 4.0 1.2B vs LFM2.5 1.2B Thinking
EXAONE 4.0 1.2B vs LFM2.5 1.2B Thinking
Updated November 2026
Verdict
EXAONE 4.0 1.2B scores higher on the Small LM Index: 36.1 vs 30.1, although their likely ranges overlap, so the lead is not certain. On the 5 benchmarks both labs report, EXAONE 4.0 1.2B wins 3 and LFM2.5 1.2B Thinking wins 2. Both need about 1.8 GB of memory at 4-bit quantization. Neither model has a hosted API on OpenRouter, so you would run both yourself.
Pick EXAONE 4.0 1.2B if…
- you want the strongest model overall
- you need math and reasoning
- you work with long documents
Pick LFM2.5 1.2B Thinking if…
- you need precise instruction following
- you build agents that call tools
Specifications
| EXAONE 4.0 1.2B | LFM2.5 1.2B Thinking | |
|---|---|---|
| Small LM Index | 36.1 (likely 33–40) | 30.1 (likely 27–34) |
| Lab | LG AI Research (EXAONE) · Rest of Asia | Liquid AI · United States |
| Released | 2025-07-15 | 2026-01-20 |
| Parameters | 1.3B (dense) | 1.2B (dense) |
| Memory at 4-bit | ~1.8 GB | ~1.3 GB |
| Context window | 64K tokens | 32K tokens |
| Input | text | text |
| Reasoning | Hybrid (thinking on/off) | Always thinks |
| License | EXAONE License (non-commercial) | LFM Open License |
| API price / 1M tokens | Self-host only | Self-host only |
| Hugging Face downloads (30 days) | 13.3K | 8.1K |
Benchmarks
Higher is better. Bold marks the winner where both labs report a score. ≈ marks the index model's estimate for a score that wasn't reported, ✓ an independent measurement and * a score measured by another lab.
| Benchmark | EXAONE 4.0 1.2B | LFM2.5 1.2B Thinking |
|---|---|---|
| MMLU-Pro Knowledge | 59.3 | 49.7 |
| GPQA Diamond Knowledge | 52.0 | 37.9 |
| AIME Math | 45.2 | 31.7 |
| LiveCodeBench Coding | 45.3 | ≈ 32 |
| IFBench Instruction following | — | 44.9 |
| MMLU Knowledge | 71.5 | — |
| Multilingual MMLU Multilingual | 62.4 | — |
| IFEval Instruction following | 67.8 | 88.4 |
| BFCL Agentic | 52.9 | 57.0 |
| MATH-500 Math | — | 88.0 |
| HMMT Math | 34.0 | — |
Scores are mostly reported by each lab with its own settings, so small gaps are noise. See the methodology. Open in the interactive comparison to add more models.
Questions
Which is better, EXAONE 4.0 1.2B or LFM2.5 1.2B Thinking?
EXAONE 4.0 1.2B scores higher on the Small LM Index: 36.1 vs 30.1, although their likely ranges overlap, so the lead is not certain. On the 5 benchmarks both labs report, EXAONE 4.0 1.2B wins 3 and LFM2.5 1.2B Thinking wins 2.
Which is cheaper to run?
Neither model has a hosted API on OpenRouter, so you would run both yourself. Both need about 1.8 GB of memory at 4-bit quantization.
Which has the longer context window?
EXAONE 4.0 1.2B has the longer context window: 64K tokens against 32K.
Can I use EXAONE 4.0 1.2B and LFM2.5 1.2B Thinking commercially?
EXAONE 4.0 1.2B is released under EXAONE License (non-commercial) and LFM2.5 1.2B Thinking under LFM Open License. Apache 2.0 and MIT allow commercial use; other licenses can add conditions, so read the license before shipping a product.
Related comparisons
- EXAONE 4.0 1.2B vs LFM3 1.7B
- EXAONE 4.0 1.2B vs Spark-X2.6 1.7B
- EXAONE 4.0 1.2B vs LFM2.5 1.2B Instruct
- EXAONE 4.0 1.2B vs Gemma 3 1B
- EXAONE 4.0 1.2B vs Qwen3.5 0.8B
- LFM2.5 1.2B Thinking vs Spark-X2.6 1.7B
- LFM2.5 1.2B Instruct vs LFM2.5 1.2B Thinking
- Gemma 3 1B vs LFM2.5 1.2B Thinking
- LFM2.5 1.2B Thinking vs Qwen3.5 0.8B
- LFM2.5 1.2B Thinking vs LFM2.5 350M