📡 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 (18 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: 0.45

contextWindow: 131072

inputPrice: 0.71

outputPrice: 0.71

benchmarkMmlu: 86

benchmarkHumanEval: 88.4

benchmarkMath: 77

benchmarkHellaSwag: 88

benchmarkGpqa: 50.5

benchmarkMmluPro: 66.4

reasoningScore: 68

codingScore: 89

benchmarkSweBench: 45

aaIntelligenceIndex: 8

aaOutputSpeed: 88

aaLatency: 1.79

aaEndToEndTime: 7.49

Meta: Llama 3.3 70B Instruct

meta-llama🔒 Proprietary

Meta's best-in-class 70B model with top OSS instruction following.

LLM Stats Scores

68.0

Reasoning

89.0

Coding

🎯

50.5%GPQA Diamond — graduate-level science accuracy

66.4%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 ↗

3.6%

Humanity's Last Exam

45.0%

SWE-bench

Artificial Analysis measurements

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

View source ↗

Intelligence

AA Index

Output speed

tokens / second

TTFT

1.79s

AA measured

Response time

7.49s

end to end

Collected 11/11/2026

Quality Score

78.0

Overall (0–100)

Speed

80 c/s

characters/second

Latency (TTFT)

0.45s

to first token

Input Price

$0.71

per 1M tokens

Output Price

$0.71

per 1M tokens

Context Window

131K

tokens

Release Date

2024-12-06

30-Day Rank History

📊 Benchmark Scores

Reported scores · % accuracy

What do these benchmarks test?

🎯

GPQA Diamond50.5%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-Pro66.4%Solid

The harder successor to MMLU — more options per question eliminate single-answer guessing. Tests depth of professional knowledge across 14 disciplines.

🧠

MMLU86.0%Solid

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

💻

HumanEval88.4%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 Benchmark77.0%Solid

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

🌐

HellaSwag88.0%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.