The Model Index
Up to four models

Qwen3-8B vs Qwen3-30B-A3B

On the index (GPT-4 = 100), Qwen3-8B scores 126 and Qwen3-30B-A3B 125. 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 Qwen3-8B
Presets
Qwen3-8B
126110–141
WeightsOpen
ReleasedApr 2025
Price in / out–
Context–
Core tests taken1 of 9
Qwen3-30B-A3B
125109–141
WeightsOpen
ReleasedApr 2025
Price in / out$0.12 / $0.50
Context41K
Core tests taken1 of 9

Qwen3-8B and Qwen3-30B-A3B are too close to call (0 points apart, within the uncertainty), ahead on 0 of 1 shared core tests.

Test by testthird-party results

Qwen3-8BQwen3-30B-A3B
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)Fiction.LiveBenchFiction.LiveBenchMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)AGENTSDTBenchDTBenchLMCALMCA
Every result as a table
TestQwen3-8BQwen3-30B-A3B
Reasoning & knowledge
GPQA Diamond (Epoch AI)56.8%61.7%
Fiction.LiveBench62.1%40.6%
Maths
AIME-style maths (OTIS mock)56.1%62.8%
Agents
DTBench59.7%60.3%
LMCA8.8%15.8%

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

This page as a chartDownload PNG