GLM-4.5-Air vs LFM2.5-350M

Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.

Agentic
Coding
Multimodal & Grounded
Reasoning
Knowledge
Instruction Following
Multilingual
Mathematics

GLM-4.5-Air· LFM2.5-350M

Quick Verdict

Pick LFM2.5-350M if you want the stronger benchmark profile. GLM-4.5-Air only becomes the better choice if knowledge is the priority or you need the larger 128K context window.

LFM2.5-350M is clearly ahead on the aggregate, 39 to 35. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GLM-4.5-Air gives you the larger context window at 128K, compared with 32K for LFM2.5-350M.

Operational tradeoffs

PricePricing unavailableFree*
Speed106 t/sN/A
TTFT1.18sN/A
Context128K32K

Decision framing

BenchLM keeps the benchmark table and the operator tradeoffs on the same page so a better score does not hide a materially slower, pricier, or smaller-context model.

Runtime metrics show N/A when BenchLM does not have a sourced snapshot for that exact model. The scoring rules and freshness policy are documented on the methodology page.

BenchmarkGLM-4.5-AirLFM2.5-350M
Agentic
Terminal-Bench 2.028%
OSWorld-Verified28%
Coding
HumanEval27%
SWE-bench Verified15%
LiveCodeBench15%
SWE-bench Pro14%
SWE-Rebench38.3%
Multimodal & Grounded
MMMU-Pro36%
OfficeQA Pro44%
Reasoning
MuSR31%
BBH63%
LongBench v247%
MRCRv251%
KnowledgeGLM-4.5-Air wins
MMLU35%
GPQA34%30.6%
SuperGPQA32%
MMLU-Pro51%20.0%
HLE4%
FrontierScience37%
SimpleQA33%
Instruction Following
IFEval77.0%
Multilingual
Coming soon
Mathematics
AIME 202335%
AIME 202437%
AIME 202536%
HMMT Feb 202331%
HMMT Feb 202433%
HMMT Feb 202532%
BRUMO 202534%
Frequently Asked Questions (2)

Which is better, GLM-4.5-Air or LFM2.5-350M?

LFM2.5-350M is ahead overall, 39 to 35. The biggest single separator in this matchup is MMLU-Pro, where the scores are 51% and 20.0%.

Which is better for knowledge tasks, GLM-4.5-Air or LFM2.5-350M?

GLM-4.5-Air has the edge for knowledge tasks in this comparison, averaging 31 versus 23.8. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.

Last updated: March 31, 2026

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.