Model comparison

GLM-5 vs LFM2.5-8B-A1B

Data verified July 16, 2026

Head-to-head evidence from 14 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

GLM-5

Z.AI

65.98/100

Margin

24.7pts

← winning

LFM2.5-8B-A1B

LiquidAI

41.25/100

2 category wins0 category wins

Verified leaderboard positions: GLM-5 #15; LFM2.5-8B-A1B unranked

BenchAlign evidence: GLM-5 supported; LFM2.5-8B-A1B estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. GLM-5 and LFM2.5-8B-A1B share 14 comparable benchmark results. 2 of 8 categories are comparable. 36 results are unique to GLM-5; 4 to LFM2.5-8B-A1B.

Updated July 16, 2026

Shared results: 14
GLM-5 only: 36
LFM2.5-8B-A1B only: 4
Comparable categories: 2 / 8

Pick GLM-5 if you want the stronger benchmark profile. LFM2.5-8B-A1B only becomes the better choice if you want the cheaper token bill or you want the stronger reasoning-first profile.

Confidence note. This is a partial-evidence comparison with 14 shared benchmark results across 6 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 37. 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 instruction following, where it averages 92.6 against 68.8. The single biggest benchmark swing on the page is AIME26, 95.8% to 50.0%.

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 LFM2.5-8B-A1B. That is roughly Infinityx on output cost alone. LFM2.5-8B-A1B is the reasoning model in the pair, while GLM-5 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. GLM-5 gives you the larger context window at 200K, compared with 128K for LFM2.5-8B-A1B.

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 LFM2.5-8B-A1B
Category	GLM-5	Δ	LFM2.5-8B-A1B
Inst. Following	GLM-592.6	Margin← 23.8	LFM2.5-8B-A1B68.8
Math	GLM-556.3	Margin← 6.3	LFM2.5-8B-A1B50.0
Agentic	GLM-556.2	MarginNo overlap	LFM2.5-8B-A1BNot measured
Coding	GLM-566.3	MarginNo overlap	LFM2.5-8B-A1BNot measured
Reasoning	GLM-560.8	MarginNo overlap	LFM2.5-8B-A1BNot measured
Knowledge	GLM-566.6	MarginNo overlap	LFM2.5-8B-A1BNot measured
Multilingual	GLM-583.1	MarginNo overlap	LFM2.5-8B-A1BNot measured

Decisive benchmark drivers

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

A · GLM-5B · LFM2.5-8B-A1B

AIME26
Math
Source ↗
A 95.8%B 50.0%
Winner: GLM-5Δ 45.8
AIME26: GLM-5 scored 95.8%; LFM2.5-8B-A1B scored 50.0%. GLM-5 wins this benchmark.
IFEval
Inst. Following
Source ↗
A 92.6%B 91.8%
Winner: GLM-5Δ 0.8
IFEval: GLM-5 scored 92.6%; LFM2.5-8B-A1B scored 91.8%. 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	LFM2.5-8B-A1B	Comparison
Input / output priceUSD per 1M tokens	GLM-5$1 input / $3.2 output	LFM2.5-8B-A1B$0 input / $0 output	LFM2.5-8B-A1B has the lower combined listed price.
Generation speedtokens per second	GLM-574 tok/s	LFM2.5-8B-A1BNot available	A complete speed comparison is not available.
First-answer latencyseconds to first token	GLM-51.64 s	LFM2.5-8B-A1BNot available	A complete latency comparison is not available.
Context windowmaximum listed tokens	GLM-5200K	LFM2.5-8B-A1B128K	GLM-5 lists the larger context window.

Benchmark Deep Dive

Agentic

14 benchmarks

Benchmark	GLM-5	LFM2.5-8B-A1B	Result
Terminal-Bench 2.0Source	56.2%	—	Not comparable
Claw-EvalSource	57.7%	—	Not comparable
QwenClawBenchSource	54.1%	—	Not comparable
τ³-bench resultsSource	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
τ²-bench resultsSource	98.2%	16.1%	GLM-5 leads
CyberGymSource	43.2%	—	Not comparable
APEX-Agents-AASource	14.5%	—	Not comparable
Gert LabsSource	50.99%	—	Not comparable
BFCL v4Source	—	49.7%	Not comparable

Coding

8 benchmarks

Benchmark	GLM-5	LFM2.5-8B-A1B	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%	4.5%	GLM-5 leads
AA-SciCodeSource	46.2%	7.8%	GLM-5 leads

Reasoning

4 benchmarks

Benchmark	GLM-5	LFM2.5-8B-A1B	Result
LongBench v2Source	60.8%	—	Not comparable
AI-NeedleSource	63.3%	—	Not comparable
AA-LCRSource	63.3%	0.0%	GLM-5 leads
CritPtSource	2.0%	0.0%	GLM-5 leads

Knowledge

12 benchmarks

Benchmark	GLM-5	LFM2.5-8B-A1B	Result
GPQASource	86%	—	Not comparable
GPQA-DSource	86.0%	—	Not comparable
SuperGPQASource	66.8%	—	Not comparable
MMLU-ProSource	85.7%	—	Not comparable
MMLU-Pro (Arcee)Source	85.8%	—	Not comparable
HLESource	50.4%	—	Not comparable
Artificial Analysis Intelligence IndexSource	39.5%	8.3%	GLM-5 leads
AA-GPQA DiamondSource	82.0%	51.3%	GLM-5 leads
AA-HLESource	27.2%	6.9%	GLM-5 leads
AA-Omniscience IndexSource	2.0%	-33.3%	GLM-5 leads
AA-Omniscience AccuracySource	26.9%	9.4%	GLM-5 leads
AA-Omniscience Hallucination RateSource	34.0%	47.0%	GLM-5 leads

MathGLM-5 wins

10 benchmarks

Benchmark	GLM-5	LFM2.5-8B-A1B	Result
AIME26Source	95.8%	50.0%	GLM-5 leads
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
MATH-500Source	—	88.8%	Not comparable
AIME 2025Source	—	42.5%	Not comparable

Multilingual

2 benchmarks

Benchmark	GLM-5	LFM2.5-8B-A1B	Result
MMLU-ProXSource	83.1%	—	Not comparable
NOVA-63Source	55.1%	—	Not comparable

Multimodal

1 benchmarks

Benchmark	GLM-5	LFM2.5-8B-A1B	Result
Design Arena WebsiteSource	1282	—	Not comparable

Inst. FollowingGLM-5 wins

3 benchmarks

Benchmark	GLM-5	LFM2.5-8B-A1B	Result
IFEvalSource	92.6%	91.8%	GLM-5 leads
AA-IFBenchSource	72.3%	55.6%	GLM-5 leads
IFBenchSource	—	56.5%	Not comparable

Frequently Asked Questions (3)

Which is better, GLM-5 or LFM2.5-8B-A1B?

GLM-5 is ahead on BenchLM's provisional leaderboard, 63 to 37. The biggest single separator in this matchup is AIME26, where the scores are 95.8% and 50.0%.

Which is better for math, GLM-5 or LFM2.5-8B-A1B?

GLM-5 has the edge for math in this comparison, averaging 56.3 versus 50. Inside this category, AIME26 is the benchmark that creates the most daylight between them.

Which is better for instruction following, GLM-5 or LFM2.5-8B-A1B?

GLM-5 has the edge for instruction following in this comparison, averaging 92.6 versus 68.8. Inside this category, AA-IFBench 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 16, 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.