📡 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: 48

latency: 0.85

contextWindow: 163840

inputPrice: 0.5

outputPrice: 2.15

benchmarkMmlu: 90.8

benchmarkHumanEval: 92.6

benchmarkMath: 97.3

benchmarkHellaSwag: 90

benchmarkGpqa: 71.5

benchmarkMmluPro: 73

reasoningScore: 84

codingScore: 92.8

benchmarkSweBench: 49.2

DeepSeek: R1 0528

deepseek🔒 Proprietary

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...

LLM Stats Scores

84.0

Reasoning

92.8

Coding

🎯

71.5%GPQA Diamond — graduate-level science accuracy

73.0%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 ↗

15.8%

Humanity's Last Exam

49.2%

SWE-bench

Quality Score

88.0

Overall (0–100)

Speed

48 c/s

characters/second

Latency (TTFT)

0.85s

to first token

Input Price

$0.5

per 1M tokens

Output Price

$2.15

per 1M tokens

Context Window

164K

tokens

Release Date

2025-05-28

30-Day Rank History

📊 Benchmark Scores

Reported scores · % accuracy

What do these benchmarks test?

🎯

GPQA Diamond71.5%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-Pro73.0%Solid

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

🧠

MMLU90.8%Top tier

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

💻

HumanEval92.6%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 Benchmark97.3%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%.

🌐

HellaSwag90.0%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.