📡 LLM Pulse|🆕 New on leaderboard: Google: Gemini 4 Hydrogen by Google — $1.5/M tokens1/10
Measurement sources and verification status (15 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: 160
latency: 0.28
contextWindow: 1048576
inputPrice: 1.5
outputPrice: 7.5
benchmarkMmlu: 68
benchmarkHumanEval: 68
benchmarkMath: 64
benchmarkGpqa: 50
reasoningScore: 57
codingScore: 68
aaIntelligenceIndex: 54
aaCostPerTask: 0.29
aaOutputSpeed: 13.7
aaLatency: 5.73

Google: Gemini 4 Hydrogen

google🔓 Open Source
7.3
LLM Stats Scores
57.0
Reasoning
68.0
Coding
🎯
50.0%GPQA Diamond — graduate-level science accuracy
Artificial Analysis measurements
Published operational results. Cost per task, speed, and latency are kept separate from provider API prices.
View source ↗
Intelligence
54
AA Index
Cost / task
$0.29
AA measured
Output speed
14
tokens / second
TTFT
5.73s
AA measured
Collected 11/13/2026
Quality Score
63.0
Overall (0–100)
Speed
160 c/s
characters/second
Latency (TTFT)
0.28s
to first token
Input Price
$1.5
per 1M tokens
Output Price
$7.5
per 1M tokens
Context Window
1M
tokens
Release Date
2026-11-12

📊 Benchmark Scores

Reported scores · % accuracy
0%25%50%75%100%GPQA ◆MMLUHumanEvalMATH50.0%68.0%68.0%64.0%
What do these benchmarks test?
🎯
GPQA Diamond50.0%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.
🧠
MMLU68.0%Below avg
The classic academic breadth benchmark. Top frontier models now score above 85%, so it best distinguishes mid-tier from strong generalist models.
💻
HumanEval68.0%Below avg
Measures whether a model writes functionally correct code — not just plausible-looking syntax. Strong scores (>85%) indicate reliable day-to-day coding assistance.
∑
MATH Benchmark64.0%Solid
Tests multi-step mathematical reasoning under strict correctness. Even a 60% score requires strong chain-of-thought; top reasoning models now exceed 90%.

💰 Cost Calculator

Input cost
$1.50
Output cost
$3.75
Total / month
$5.25
Annual cost
$63.00
Input: $1.5/1M
Output: $7.5/1M
Rate: 1 USD = 1.00 USD · 2026-11-12

AI Score

Ask the AI to assess this model's real-world capability and give it an evidence-based score out of 10.

🤖 AI Analysis