📡 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 (16 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: 262144

inputPrice: 0.08

outputPrice: 0.1

benchmarkMmlu: 78

benchmarkHumanEval: 78

benchmarkMath: 74

benchmarkGpqa: 60

reasoningScore: 67

codingScore: 78

aaIntelligenceIndex: 17

aaCostPerTask: 0.04

aaOutputSpeed: 122

aaLatency: 1.49

aaEndToEndTime: 5.01

Google: Gemma 4 26B A4B

google🔓 Open Source

Published Humanity’s Last Exam leaderboard evidence.

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 ↗

19.3%

Humanity's Last Exam

Artificial Analysis measurements

Published operational results. Cost per task, speed, and latency are kept separate from provider API prices.

View source ↗

Intelligence

AA Index

Cost / task

$0.04

AA measured

Output speed

122

tokens / second

TTFT

1.49s

AA measured

Response time

5.01s

end to end

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

$0.08

per 1M tokens

Output Price

$0.1

per 1M tokens

Context Window

262K

tokens

Release Date

2025-Q2

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%.