The Model Index
Up to four models

Qwen2.5 vs Claude 3.5 Haiku

On the index (GPT-4 = 100), Qwen2.5 scores 112 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 Qwen2.5
Presets
Qwen2.5
11296–128
WeightsOpen
ReleasedSep 2024
Price in / out$0.36 / $0.40
Context33K
Core tests taken2 of 9
Claude 3.5 Haiku
10993–125
WeightsClosed
ReleasedNov 2024
Price in / out–
Context–
Core tests taken1 of 9

Qwen2.5 and Claude 3.5 Haiku are too close to call (3 points apart, within the uncertainty), ahead on 1 of 1 shared core tests.

Test by testthird-party results

Qwen2.5Claude 3.5 Haiku
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MMLU (HELM runs)MMLU (HELM runs)GeoBenchGeoBenchMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)MATH (level 5)MATH (level 5)CODINGWeirdMLWeirdMLAGENTSBALROGBALROGDTBenchDTBench
Every result as a table
TestQwen2.5Claude 3.5 Haiku
Reasoning & knowledge
GPQA Diamond (Epoch AI)49.1%38.1%
MMLU (HELM runs)83.4%74.3%
GeoBench62.0%34.0%
Maths
AIME-style maths (OTIS mock)8.1%4.3%
MATH (level 5)63.2%46.4%
Coding
WeirdML16.0%30.7%
Agents
BALROG16.2%19.3%
DTBench62.9%56.7%
Task length · METR21 sec

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

This page as a chartDownload PNG