The Model Index
Up to four models

Qwen2 vs Gemini 1.5 Flash

On the index (GPT-4 = 100), Qwen2 scores 106 and Gemini 1.5 Flash 101. 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
Presets
Qwen2
10690–122
WeightsOpen
ReleasedJun 2024
Price in / out–
Context–
Core tests taken2 of 9
Gemini 1.5 Flash
10185–118
WeightsClosed
ReleasedMay 2024
Price in / out–
Context–
Core tests taken1 of 9

Qwen2 and Gemini 1.5 Flash are too close to call (5 points apart, within the uncertainty), ahead on 1 of 1 shared core tests.

Test by testthird-party results

Qwen2Gemini 1.5 Flash
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MMLU (HELM runs)MMLU (HELM runs)MATHSMATH (level 5)MATH (level 5)
Every result as a table
TestQwen2Gemini 1.5 Flash
Reasoning & knowledge
GPQA Diamond (Epoch AI)40.8%40.4%
MMLU (HELM runs)82.4%77.9%
Maths
MATH (level 5)39.1%25.1%
Task length · METR18 sec

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

This page as a chartDownload PNG