📡 LLM Pulse|🆕 New on leaderboard: Baidu: ERNIE-Light-DT-1.0 by Baidu — $1.13/M tokens1/10
Measurement sources and verification status (17 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: 16384
inputPrice: 0.07
outputPrice: 0.14
benchmarkMmlu: 71
benchmarkHumanEval: 82.6
benchmarkMath: 80.3
benchmarkHellaSwag: 88.6
benchmarkGpqa: 48
benchmarkMmluPro: 70.5
reasoningScore: 67
codingScore: 78
aaIntelligenceIndex: 6
aaOutputSpeed: 41
aaLatency: 2.18
aaEndToEndTime: 14.51

Microsoft: Phi-4

Microsoft🔒 Proprietary

Microsoft's compact 14B model outperforming many 70B models on math and reasoning.

6.6
LLM Stats Scores
67.0
Reasoning
78.0
Coding
🎯
48.0%GPQA Diamond — graduate-level science accuracy
70.5%MMLU-Pro
Published benchmark evidence
Task scores are reported independently by each publisher; they are not combined into a hidden quality score.
View HLE source ↗
3.8%
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
6
AA Index
Output speed
41
tokens / second
TTFT
2.18s
AA measured
Response time
14.51s
end to end
Collected 11/11/2026
BenchLM performance measurements
Published output speed and first-token timing, kept separate from provider pricing and other benchmark sources.
View source ↗
Output speed
41
tokens / second
TTFT
2.64s
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
$0.07
per 1M tokens
Output Price
$0.14
per 1M tokens
Context Window
16K
tokens
Release Date
2025-Q1

30-Day Rank History

📊 Benchmark Scores

Reported scores · % accuracy
0%25%50%75%100%GPQA ◆MMLU-ProMMLUHumanEvalMATHHellaSwag
What do these benchmarks test?
🎯
GPQA Diamond48.0%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.
📚
MMLU-Pro70.5%Solid
The harder successor to MMLU — more options per question eliminate single-answer guessing. Tests depth of professional knowledge across 14 disciplines.
🧠
MMLU71.0%Below avg
The classic academic breadth benchmark. Top frontier models now score above 85%, so it best distinguishes mid-tier from strong generalist models.
💻
HumanEval82.6%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 Benchmark80.3%Top tier
Tests multi-step mathematical reasoning under strict correctness. Even a 60% score requires strong chain-of-thought; top reasoning models now exceed 90%.
🌐
HellaSwag88.6%Solid
Tests grounded, everyday common sense rather than memorised facts. Most frontier models now score 90%+, so it best separates small/mid models from large ones.

💰 Cost Calculator

Input cost
$0.070
Output cost
$0.070
Total / month
$0.14
Annual cost
$1.68
Input: $0.07/1M
Output: $0.14/1M
Rate: 1 USD = 1.00 USD · 2026-11-10
95.7% cheaper than average
Cheaper alternatives:
Z.ai: GLM 5.2$0.007/1M · Q73

AI Score

Powered by Groq
6.5/10

"Very cheap and efficient for short prompts, but limited context and size"

🤖 AI Analysis

⚔ Battle This Model← Back