📡 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 (14 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: 0.55

contextWindow: 1000000

inputPrice: 3

outputPrice: 15

benchmarkMmlu: 90

benchmarkHumanEval: 93.5

benchmarkMath: 92

benchmarkHellaSwag: 95.5

benchmarkGpqa: 71

benchmarkMmluPro: 75

reasoningScore: 81

codingScore: 92

benchmarkSweBench: 70.3

Anthropic: Claude Sonnet 4.5

anthropic🔒 Proprietary

Published Humanity’s Last Exam leaderboard evidence.

LLM Stats Scores

81.0

Reasoning

92.0

Coding

🎯

71.0%GPQA Diamond — graduate-level science accuracy

75.0%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 ↗

17.8%

Humanity's Last Exam

70.3%

SWE-bench

Quality Score

86.0

Overall (0–100)

Speed

80 c/s

characters/second

Latency (TTFT)

0.55s

to first token

Input Price

per 1M tokens

Output Price

$15

per 1M tokens

Context Window

tokens

Release Date

2025-09-29

30-Day Rank History

📊 Benchmark Scores

Reported scores · % accuracy

What do these benchmarks test?

🎯

GPQA Diamond71.0%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-Pro75.0%Top tier

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

🧠

MMLU90.0%Top tier

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

💻

HumanEval93.5%Top tier

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

∑

MATH Benchmark92.0%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%.

🌐

HellaSwag95.5%Top tier

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.