📡 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 (12 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: 0.36

contextWindow: 256000

inputPrice: 0.3

outputPrice: 0.9

benchmarkMmlu: 80.5

benchmarkHumanEval: 88

benchmarkMath: 75

benchmarkGpqa: 34

reasoningScore: 59

codingScore: 88

benchmarkSweBench: 40

Mistral: Codestral 2508

mistralai🔒 Proprietary

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)

LLM Stats Scores

59.0

Reasoning

88.0

Coding

🎯

34.0%GPQA Diamond — graduate-level science accuracy

Published benchmark evidence

Task scores are reported independently by each publisher; they are not combined into a hidden quality score.

40.0%

SWE-bench

Quality Score

71.0

Overall (0–100)

Speed

80 c/s

characters/second

Latency (TTFT)

0.36s

to first token

Input Price

$0.3

per 1M tokens

Output Price

$0.9

per 1M tokens

Context Window

256K

tokens

Release Date

2025-08-01

30-Day Rank History

📊 Benchmark Scores

Reported scores · % accuracy

What do these benchmarks test?

🎯

GPQA Diamond34.0%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.

🧠

MMLU80.5%Solid

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

💻

HumanEval88.0%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 Benchmark75.0%Solid

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