LFM2.5-8B-A1B vs North Mini Code: Benchmarks, Pricing & Capabilities Compared
TL;DR — LFM2.5-8B-A1B wins for general use · North Mini Code wins for reasoning + long-context.
LFM2.5-8B-A1B Liquid AI
- Released
- 2026-05-28
- Context window
- 32K tokens
- Input price
- $0.00 / Mtok
- Output price
- $0.00 / Mtok
North Mini Code Cohere
- Released
- 2026-06-09
- Context window
- 256K tokens
- Input price
- $0.00 / Mtok
- Output price
- $0.00 / Mtok
Benchmark comparison
| Benchmark | LFM2.5-8B-A1B | North Mini Code |
|---|---|---|
| GPQA Diamond | 51.3% | 75.7% ✓ |
| HLE | 6.9% | 9.9% ✓ |
| IF-Bench | 55.6% | 57.6% ✓ |
| LiveCodeBench Reasoning | 0.0% | 32.3% ✓ |
| SciCode | 7.8% | 38.2% ✓ |
| TAU2-bench | 16.1% | 37.4% ✓ |
| TerminalBench-Hard | 4.5% | 31.1% ✓ |
Pricing comparison
| Metric | LFM2.5-8B-A1B | North Mini Code |
|---|---|---|
| Input ($/Mtok) | $0.00 | $0.00 |
| Output ($/Mtok) | $0.00 | $0.00 |
| Cached input ($/Mtok) | — | — |
| Cost per 1M-token roundtrip (1M in + 1M out) | $0.00 | $0.00 |
Context window & modalities
| Attribute | LFM2.5-8B-A1B | North Mini Code |
|---|---|---|
| Context window | 32K tokens | 256K tokens |
| Input modalities | text | text |
| Output modalities | text | text |
| Knowledge cutoff | — | — |
Verdict by use case
Coding
Insufficient data
Basis: SWE-bench
No shared coding benchmark.
Reasoning
→ North Mini Code
Basis: GPQA Diamond
LFM2.5-8B-A1B 51.3% vs North Mini Code 75.7% on GPQA Diamond.
Math
Insufficient data
Basis: MATH / AIME
No shared math benchmark.
Long context
→ North Mini Code
Basis: Context window
LFM2.5-8B-A1B 32K tokens vs North Mini Code 256K tokens.
Cost
Tie
Basis: Input $/Mtok
LFM2.5-8B-A1B $0/Mtok vs North Mini Code $0/Mtok input.
Changelog & releases
LFM2.5-8B-A1B
Released 2026-05-28
North Mini Code
Released 2026-06-09