Compare/LFM2.5-8B-A1B vs GLM-4.5V (Non-reasoning)

LFM2.5-8B-A1BvsGLM-4.5V (Non-reasoning)

Side-by-side comparison of pricing, 12 benchmarks, and generation speed.

Liquid AI

LFM2.5-8B-A1B

Input
$0/M
Output
$0/M
Speed
339 tok/s
TTFT
1.95s
Z AI

GLM-4.5V (Non-reasoning)

Input
$0.6/M
Output
$1.8/M
Speed
92 tok/s
TTFT
1.85s

Winner by Category

Cheaper
LFM2.5-8B-A1B
Faster (tok/s)
LFM2.5-8B-A1B
Lower Latency
GLM-4.5V (Non-reasoning)
Benchmarks (1-0)
LFM2.5-8B-A1B

Pricing Comparison

MetricLFM2.5-8B-A1BGLM-4.5V (Non-reasoning)
Input ($/M tokens)$0$0.6
Output ($/M tokens)$0$1.8
Cost for 1M input + 100K output tokens:
LFM2.5-8B-A1B$0.00
GLM-4.5V (Non-reasoning)$0.78

Speed Comparison

Output Speed (tokens/s) — higher is better
LFM2.5-8B-A1B
339 tok/s
GLM-4.5V (Non-reasoning)
92 tok/s
Time to First Token (seconds) — lower is better
LFM2.5-8B-A1B
1.95s
GLM-4.5V (Non-reasoning)
1.85s

Editorial Analysis

Verdict. LFM2.5-8B-A1B wins the overall benchmark matchup 1–0 across 1 overlapping categories, but raw benchmark score is only one input to the decision.

Pricing. Pricing varies significantly between these models — check the table above for the exact per-token rates. Many production workloads actually surface input-token cost (retrieval-augmented prompts, code-context windows), so factor both directions.

Strengths. LFM2.5-8B-A1B is strongest on Intelligence Index (8.1). GLM-4.5V (Non-reasoning) leads on Intelligence Index (6.8).

Speed. On throughput, LFM2.5-8B-A1B generates tokens at 339 tok/s versus 92 tok/s — about 73% faster. On time-to-first-token, GLM-4.5V (Non-reasoning) responds in 1850ms vs 1950ms, which matters most for chat-style UIs.

Provider. Liquid AI and Z AI sell to overlapping but distinct developer audiences: Liquid AI tends to ship frontier reasoning models with premium positioning, while Z AI often prices more aggressively. Your existing vendor relationships, billing, and SLA preferences may matter as much as the raw numbers above.

Workload cost. Workload scenarios (per million requests at 30M input + 15M output tokens): LFM2.5-8B-A1B costs $0.00 ($0/year); GLM-4.5V (Non-reasoning) costs $45.00 ($540/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): LFM2.5-8B-A1B ≈ $0.00/run, GLM-4.5V (Non-reasoning) ≈ $6.60/run. At agent/realtime scale (200M input / 100M output per million requests): LFM2.5-8B-A1B ≈ $0/run, GLM-4.5V (Non-reasoning) ≈ $300/run. LFM2.5-8B-A1B becomes more attractive at higher volume — the absolute per-token pricing difference compounds when you ship at scale.

Recommendation. Both models have legitimate use cases — the right answer depends on whether you are optimizing for benchmark ceiling, latency, or unit cost. Start with the cheaper / faster model, evaluate against your specific task, and only switch if the upgrade shows a meaningful lift.

Head-to-head deltas

  • On throughput, LFM2.5-8B-A1B is 3.67× faster (339 tok/s vs 92 tok/s). For streaming chat or real-time agents this alone often flips the recommendation.

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
8.16.8
Coding Index
Math Index
GPQA Diamond
MMLU-Pro
LiveCodeBench
AIME 2025
MATH-500
Humanity's Last Exam
SciCode
IFBench
TerminalBench
LFM2.5-8B-A1B1 wins
0 winsGLM-4.5V (Non-reasoning)

Frequently Asked Questions

Which is cheaper, LFM2.5-8B-A1B or GLM-4.5V (Non-reasoning)?

LFM2.5-8B-A1B is cheaper overall. Its blended price (3:1 input/output ratio) is $0.00/M tokens vs $0.90/M for GLM-4.5V (Non-reasoning).

Which model performs better on benchmarks?

LFM2.5-8B-A1B wins 1 out of 12 benchmarks compared to 0 for GLM-4.5V (Non-reasoning). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

LFM2.5-8B-A1B generates tokens faster at 339 tok/s vs 92 tok/s. However, GLM-4.5V (Non-reasoning) has lower time-to-first-token (1.85s vs 1.95s).

When should I use LFM2.5-8B-A1B vs GLM-4.5V (Non-reasoning)?

Choose based on your priorities: LFM2.5-8B-A1B for lower cost, LFM2.5-8B-A1B for stronger benchmark performance, and LFM2.5-8B-A1B for faster generation. For latency-sensitive apps, check the TTFT comparison above.