📡 LLM Pulse|🆕 New on leaderboard: Baidu: ERNIE-Light-DT-1.0 by Baidu — $1.13/M tokensLearn more →1/10

Measurement sources and verification status (11 fields)

Collected third-party figures are not independent tests. A source link and collection date do not establish reproducibility. Exact model version, dataset and test settings may be missing. No independent verification date is supplied.

speed: 80

latency: 0.5

contextWindow: 131072

inputPrice: 0.2

outputPrice: 1.1

benchmarkMmlu: 78

benchmarkHumanEval: 78

benchmarkMath: 74

benchmarkGpqa: 60

reasoningScore: 67

codingScore: 78

Z.ai: GLM 4.5 Air

z-ai🔒 Proprietary

GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...

LLM Stats Scores

67.0

Reasoning

78.0

Coding

🎯

60.0%GPQA Diamond — graduate-level science accuracy

Published benchmark evidence

Task scores are reported independently by each publisher; they are not combined into a hidden quality score.

View HLE source ↗

7.0%

Humanity's Last Exam

BenchLM performance measurements

Published output speed and first-token timing, kept separate from provider pricing and other benchmark sources.

View source ↗

Output speed

tokens / second

TTFT

30.55s

BenchLM measured

Collected 11/11/2026

Quality Score

73.0

Overall (0–100)

Speed

80 c/s

characters/second

Latency (TTFT)

0.50s

to first token

Input Price

$0.2

per 1M tokens

Output Price

$1.1

per 1M tokens

Context Window

131K

tokens

Release Date

2025-07-25

30-Day Rank History

📊 Benchmark Scores

Reported scores · % accuracy

What do these benchmarks test?

🎯

GPQA Diamond60.0%Below avg

Designed so that even PhD-level human experts average ~65–70%. A score above 80% signals near-expert scientific reasoning that goes far beyond memorisation.

🧠

MMLU78.0%Solid

The classic academic breadth benchmark. Top frontier models now score above 85%, so it best distinguishes mid-tier from strong generalist models.

💻

HumanEval78.0%Solid

Measures whether a model writes functionally correct code — not just plausible-looking syntax. Strong scores (>85%) indicate reliable day-to-day coding assistance.

∑

MATH Benchmark74.0%Solid

Tests multi-step mathematical reasoning under strict correctness. Even a 60% score requires strong chain-of-thought; top reasoning models now exceed 90%.