The Model Index
Up to four models

Llama 3.1 vs Claude 3.5 Haiku

On the index (GPT-4 = 100), Llama 3.1 scores 110 and Claude 3.5 Haiku 109. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to Llama 3.1
Presets
Llama 3.1
11094–127
WeightsOpen
ReleasedJul 2024
Price in / out–
Context–
Core tests taken1 of 9
Claude 3.5 Haiku
10993–125
WeightsClosed
ReleasedNov 2024
Price in / out–
Context–
Core tests taken1 of 9

Llama 3.1 and Claude 3.5 Haiku are too close to call (2 points apart, within the uncertainty), ahead on 1 of 1 shared core tests.

Test by testthird-party results

Llama 3.1Claude 3.5 Haiku
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MMLU (HELM runs)MMLU (HELM runs)MATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)MATH (level 5)MATH (level 5)CODINGWeirdMLWeirdMLAGENTSDTBenchDTBench
Every result as a table
TestLlama 3.1Claude 3.5 Haiku
Reasoning & knowledge
GPQA Diamond (Epoch AI)50.9%38.1%
MMLU (HELM runs)84.5%74.3%
Maths
AIME-style maths (OTIS mock)9.7%4.3%
MATH (level 5)49.8%46.4%
Coding
WeirdML21.4%30.7%
Agents
DTBench61.4%56.7%

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG