The Model Index
Up to four models

Gemini 1.5 Pro (Sept 2024) vs Qwen2.5

On the index (GPT-4 = 100), Gemini 1.5 Pro (Sept 2024) scores 117 and Qwen2.5 112. 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 Gemini 1.5 Pro (Sept 2024)
Presets
Gemini 1.5 Pro (Sept 2024)
117101–133
WeightsClosed
ReleasedSep 2024
Price in / out–
Context–
Core tests taken2 of 9
Qwen2.5
11296–128
WeightsOpen
ReleasedSep 2024
Price in / out$0.36 / $0.40
Context33K
Core tests taken2 of 9

Gemini 1.5 Pro (Sept 2024) and Qwen2.5 are too close to call (4 points apart, within the uncertainty), ahead on 1 of 1 shared core tests.

Test by testthird-party results

Gemini 1.5 Pro (Sept 2024)Qwen2.5
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)CODINGWeirdMLWeirdMLAGENTSBALROGBALROGDTBenchDTBench
Every result as a table
TestGemini 1.5 Pro (Sept 2024)Qwen2.5
Reasoning & knowledge
GPQA Diamond (Epoch AI)57.2%49.1%
MMLU (HELM runs)86.9%83.4%
Maths
AIME-style maths (OTIS mock)23.1%8.1%
MATH (level 5)70.4%63.2%
Coding
WeirdML22.2%16.0%
Agents
BALROG21.0%16.2%
DTBench59.0%62.9%
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