Model comparison

GLM-5 vs LFM2.5-230M

Data verified July 14, 2026

Head-to-head evidence from 4 shared benchmark results across 2 categories. Overall scores shown here use BenchLM's provisional ranking lane.

GLM-5

Z.AI

63/100

Margin

32.0pts

← winning

LFM2.5-230M

LiquidAI

31/100

2 category wins0 category wins

Verified leaderboard positions: GLM-5 #16; LFM2.5-230M unranked

Evidence parity. GLM-5 and LFM2.5-230M share 4 comparable benchmark results. 2 of 8 categories are comparable. 46 results are unique to GLM-5; 2 to LFM2.5-230M.

Updated July 14, 2026

Shared results: 4
GLM-5 only: 46
LFM2.5-230M only: 2
Comparable categories: 2 / 8

Pick GLM-5 if you want the stronger benchmark profile. LFM2.5-230M only becomes the better choice if you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 4 shared benchmark results across 2 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

GLM-5 is clearly ahead on the provisional aggregate, 63 to 31. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GLM-5's sharpest advantage is in knowledge, where it averages 66.6 against 21.2. The single biggest benchmark swing on the page is MMLU-Pro, 85.7% to 20.3%.

GLM-5 is also the more expensive model on tokens at $1.00 input / $3.20 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for LFM2.5-230M. That is roughly Infinityx on output cost alone. GLM-5 gives you the larger context window at 200K, compared with 32K for LFM2.5-230M.

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 scores and score margins for GLM-5 and LFM2.5-230M
Category	GLM-5	Δ	LFM2.5-230M
Knowledge	GLM-566.6	Margin← 45.4	LFM2.5-230M21.2
Inst. Following	GLM-592.6	Margin← 42.5	LFM2.5-230M50.1
Agentic	GLM-556.2	MarginNo overlap	LFM2.5-230MNot measured
Coding	GLM-563.3	MarginNo overlap	LFM2.5-230MNot measured
Reasoning	GLM-560.8	MarginNo overlap	LFM2.5-230MNot measured
Math	GLM-556.3	MarginNo overlap	LFM2.5-230MNot measured
Multilingual	GLM-583.1	MarginNo overlap	LFM2.5-230MNot measured

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

A · GLM-5B · LFM2.5-230M

MMLU-Pro
Knowledge
Source ↗
A 85.7%B 20.3%
Winner: GLM-5Δ 65.5
MMLU-Pro: GLM-5 scored 85.7%; LFM2.5-230M scored 20.3%. GLM-5 wins this benchmark.
GPQA
Knowledge
Source ↗
A 86%B 25.4%
Winner: GLM-5Δ 60.6
GPQA: GLM-5 scored 86%; LFM2.5-230M scored 25.4%. GLM-5 wins this benchmark.
IFEval
Inst. Following
Source ↗
A 92.6%B 71.7%
Winner: GLM-5Δ 20.9
IFEval: GLM-5 scored 92.6%; LFM2.5-230M scored 71.7%. GLM-5 wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

Metric	GLM-5	LFM2.5-230M	Comparison
Input / output priceUSD per 1M tokens	GLM-5$1 input / $3.2 output	LFM2.5-230M$0 input / $0 output	LFM2.5-230M has the lower combined listed price.
Generation speedtokens per second	GLM-574 tok/s	LFM2.5-230MNot available	A complete speed comparison is not available.
First-answer latencyseconds to first token	GLM-51.64 s	LFM2.5-230MNot available	A complete latency comparison is not available.
Context windowmaximum listed tokens	GLM-5200K	LFM2.5-230M32K	GLM-5 lists the larger context window.

Benchmark Deep Dive

Agentic

14 benchmarks

Benchmark	GLM-5	LFM2.5-230M	Result
Terminal-Bench 2.0Source	56.2%	—	Not comparable
Claw-EvalSource	57.7%	—	Not comparable
QwenClawBenchSource	54.1%	—	Not comparable
TAU3-BenchSource	65.6%	—	Not comparable
DeepPlanningSource	14.6%	—	Not comparable
ToolathlonSource	38%	—	Not comparable
MCP AtlasSource	31.1%	—	Not comparable
MCP-TasksSource	60.8%	—	Not comparable
WideResearchSource	69.8%	—	Not comparable
Tau2-TelecomSource	98.2%	—	Not comparable
CyberGymSource	43.2%	—	Not comparable
APEX-Agents-AASource	14.5%	—	Not comparable
Gert LabsSource	50.99%	—	Not comparable
BFCL v4Source	—	21.0%	Not comparable

Coding

8 benchmarks

Benchmark	GLM-5	LFM2.5-230M	Result
SWE-bench VerifiedSource	77.8%	—	Not comparable
SWE-bench Verified*Source	72.8%	—	Not comparable
SWE-bench ProSource	55.1%	—	Not comparable
SWE MultilingualSource	73.3%	—	Not comparable
SWE-RebenchSource	62.8%	—	Not comparable
React Native EvalsSource	74.8%	—	Not comparable
Terminal-Bench HardSource	43.2%	—	Not comparable
AA-SciCodeSource	46.2%	—	Not comparable

Reasoning

4 benchmarks

Benchmark	GLM-5	LFM2.5-230M	Result
LongBench v2Source	60.8%	—	Not comparable
AI-NeedleSource	63.3%	—	Not comparable
AA-LCRSource	63.3%	—	Not comparable
CritPtSource	2.0%	—	Not comparable

KnowledgeGLM-5 wins

12 benchmarks

Benchmark	GLM-5	LFM2.5-230M	Result
GPQASource	86%	25.4%	GLM-5 leads
GPQA-DSource	86.0%	25.4%	GLM-5 leads
SuperGPQASource	66.8%	—	Not comparable
MMLU-ProSource	85.7%	20.3%	GLM-5 leads
MMLU-Pro (Arcee)Source	85.8%	—	Not comparable
HLESource	50.4%	—	Not comparable
Artificial Analysis Intelligence IndexSource	39.5%	—	Not comparable
AA-GPQA DiamondSource	82.0%	—	Not comparable
AA-HLESource	27.2%	—	Not comparable
AA-Omniscience IndexSource	2.0%	—	Not comparable
AA-Omniscience AccuracySource	26.9%	—	Not comparable
AA-Omniscience Hallucination RateSource	34.0%	—	Not comparable

Math

8 benchmarks

Benchmark	GLM-5	LFM2.5-230M	Result
AIME26Source	95.8%	—	Not comparable
AIME25 (Arcee)Source	93.3%	—	Not comparable
HMMT Feb 2025Source	97.5%	—	Not comparable
HMMT Nov 2025Source	96.9%	—	Not comparable
HMMT Feb 2026Source	86.4%	—	Not comparable
MMAnswerBenchSource	82.5%	—	Not comparable
FrontierMath v2 (Tiers 1-3)Source	16.434%	—	Not comparable
FrontierMath v2 (Tier 4)Source	2.100%	—	Not comparable

Multilingual

2 benchmarks

Benchmark	GLM-5	LFM2.5-230M	Result
MMLU-ProXSource	83.1%	—	Not comparable
NOVA-63Source	55.1%	—	Not comparable

Multimodal

1 benchmarks

Benchmark	GLM-5	LFM2.5-230M	Result
Design Arena WebsiteSource	1282	—	Not comparable

Inst. FollowingGLM-5 wins

3 benchmarks

Benchmark	GLM-5	LFM2.5-230M	Result
IFEvalSource	92.6%	71.7%	GLM-5 leads
AA-IFBenchSource	72.3%	—	Not comparable
IFBenchSource	—	38.4%	Not comparable

Frequently Asked Questions (3)

Which is better, GLM-5 or LFM2.5-230M?

GLM-5 is ahead on BenchLM's provisional leaderboard, 63 to 31. The biggest single separator in this matchup is MMLU-Pro, where the scores are 85.7% and 20.3%.

Which is better for knowledge tasks, GLM-5 or LFM2.5-230M?

GLM-5 has the edge for knowledge tasks in this comparison, averaging 66.6 versus 21.2. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, GLM-5 or LFM2.5-230M?

GLM-5 has the edge for instruction following in this comparison, averaging 92.6 versus 50.1. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Related Comparisons

Explore More

Z.AI Compare Pricing Methodology Find Your Best LLM Overall Rankings

Last updated: July 14, 2026

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.