The Model Index
Up to four models

DeepSeek-R1-Distill-Llama-70B vs Qwen3-30B-A3B

On the index (GPT-4 = 100), DeepSeek-R1-Distill-Llama-70B scores 125 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 DeepSeek-R1-Distill-Llama-70B
Presets
DeepSeek-R1-Distill-Llama-70B
125109–142
WeightsOpen
ReleasedJan 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

DeepSeek-R1-Distill-Llama-70B 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

DeepSeek-R1-Distill-Llama-70BQwen3-30B-A3B
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)
Every result as a table
TestDeepSeek-R1-Distill-Llama-70BQwen3-30B-A3B
Reasoning & knowledge
GPQA Diamond (Epoch AI)55.7%61.7%
Maths
AIME-style maths (OTIS mock)51.4%62.8%

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

This page as a chartDownload PNG