LIVE INTELLIGENCE · part of the Xentir AI Index

Grok 4.20 (4.20 0309 Reasoning) vs Qwen3.7-Max

Grok 4.20 (4.20 0309 Reasoning) · xAI, released 2026-02-17
Qwen3.7-Max · Alibaba, released 2026-05-19

“Epoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource].” · epoch.ai/benchmarks · Licensed CC BY 4.0 · data last verified 2026-07-26 · Methodology · Data Sources

Head-to-head

Measured on 5 of 9 tracked benchmarks for both models — Grok 4.20 (4.20 0309 Reasoning) leads on 1, Qwen3.7-Max leads on 4.

Benchmark	Grok 4.20 (4.20 0309 Reasoning)	Qwen3.7-Max	Leads
Epoch Capabilities Index (ECI)	152.6	153.1	Qwen3.7-Max
SWE-bench Verified	Not measured	0.773	Not measured on both
GPQA Diamond	0.893	0.916	Qwen3.7-Max
MATH Level 5	Not measured	Not measured	Not measured on both
OTIS Mock AIME 2024-2025	0.922	0.950	Qwen3.7-Max
FrontierMath	Not measured	Not measured	Not measured on both
FrontierMath Tier 4	Not measured	Not measured	Not measured on both
SimpleQA Verified	0.351	0.585	Qwen3.7-Max
Chess Puzzles	0.240	0.220	Grok 4.20 (4.20 0309 Reasoning)

Benchmark results measure specific tasks and should not be treated as a universal measure of model quality. A model with no row here for a benchmark has not been measured on it — that is left blank, never estimated.

Full profiles

Grok 4.20 (4.20 0309 Reasoning) → · Qwen3.7-Max → · the full AI Model Rankings table