The Model Index
Up to four models

Qwen2.5-7B vs Claude 3 Haiku

On the index (GPT-4 = 100), Qwen2.5-7B scores 96 and Claude 3 Haiku 95. 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 Qwen2.5-7B
Presets
Qwen2.5-7B
9677–115
WeightsOpen
ReleasedSep 2024
Price in / out–
Context–
Core tests taken1 of 9
Claude 3 Haiku
9578–113
WeightsClosed
ReleasedMar 2024
Price in / out–
Context–
Core tests taken1 of 9

Qwen2.5-7B and Claude 3 Haiku are too close to call (0 points apart, within the uncertainty), ahead on 0 of 1 shared core tests.

Test by testthird-party results

Qwen2.5-7BClaude 3 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)AGENTSDTBenchDTBenchLMCALMCA
Every result as a table
TestQwen2.5-7BClaude 3 Haiku
Reasoning & knowledge
GPQA Diamond (Epoch AI)35.5%36.3%
MMLU (HELM runs)72.9%73.8%
Maths
AIME-style maths (OTIS mock)2.5%1.8%
Agents
DTBench47.7%50.1%
LMCA6.4%8.8%

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

This page as a chartDownload PNG