Compare AI models

Specifications
Parameters
8B/70B/405B>1T
Context window
128k256k
API pricing
Cheapest input
$0.02DeepInfra—
Cheapest output
$0.04DeepInfra—
$6.00DeepInfra · fp8—
Benchmarks
GPQA Diamond
49%87.4%
MMLU-Pro
73.3%85.7%
Overview
CompanyMetaQwen
Release dateJul 23 2024Jan 26 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen3-Max-Thinking leads LLaMA 3.1 on 2 of the 2 benchmarks they both report (GPQA Diamond, MMLU-Pro). LLaMA 3.1 shipped 552 days before Qwen3-Max-Thinking, so benchmark comparisons should account for the intervening progress.

LLaMA 3.1 has 8B/70B/405B parameters, while Qwen3-Max-Thinking has >1T. Context windows are 128k (LLaMA 3.1) vs 256k (Qwen3-Max-Thinking). LLaMA 3.1 is open weight, while Qwen3-Max-Thinking is closed.

On GPQA Diamond, Qwen3-Max-Thinking leads at 87.4% vs LLaMA 3.1 at 49%. On MMLU-Pro, Qwen3-Max-Thinking leads at 85.7% vs LLaMA 3.1 at 73.3%.