Claude Haiku 5.5 vs LFM2.5 2.6B
LFM2.5 2.6B is cheaper on output tokens, while Claude Haiku 5.5 offers a larger context window. Choose Claude Haiku 5.5 or LFM2.5 2.6B based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Claude Haiku 5.5 | LFM2.5 2.6B |
|---|---|---|
| Provider | Anthropic | NanoGPT |
| Input / 1M tokens | $0.10 | $0.10 |
| Output / 1M tokens | $0.50 | $0.20 |
| Context window | 1M | 128K |
| Parameters | — | — |
| Open weights | — | Yes |
| Released | — | Aug 2026 |
| GPQA Diamond score | 89.7 | — |
| LMArena WebDev Elo score | 1586 | — |
| Epoch Capabilities Index score | 159 | — |
FAQ
Is Claude Haiku 5.5 or LFM2.5 2.6B cheaper?
LFM2.5 2.6B is cheaper on output tokens ($0.20 vs $0.50 per 1M).
Which has the larger context window, Claude Haiku 5.5 or LFM2.5 2.6B?
Claude Haiku 5.5 has the larger context window (1M tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.