Model	SWE-bench Verified % resolved	GPQA Diamond accuracy	LiveCodeBench Pro Codeforces Elo	Berkeley Function Calling Leaderboard accuracy	LiveBench score	Terminal-Bench 2.1 task success	SWE-bench Pro % resolved	DeepSWE % resolved	Humanity's Last Exam accuracy	MMMU-Pro accuracy	LMArena source-defined rating	ARC-AGI-3 accuracy	ARC-AGI-2 accuracy	FrontierMath accuracy	AIME (OTIS Mock) accuracy	SimpleQA Verified accuracy
Qwen 3 Coder 480B Qwen	—	—	—	—	—	—	38.70%	—	—	—	—	—	—	—	—	—
Qwen3 235B A22B Instruct 2507 Qwen	—	—	1673	52.15%	—	—	21.41%	—	—	—	—	—	—	—	—	50.1%
Qwen3 Max Qwen	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	67.5%
Qwen3.5 Max Preview Qwen	—	—	—	—	—	—	—	—	—	—	1470	—	—	—	—	—
Qwen 3.6 Plus Qwen	—	87.4%	—	—	—	—	—	—	—	—	—	—	—	—	90.6%	49.1%
Qwen 3.6 Max Preview Qwen	—	89.1%	—	—	—	—	—	—	—	—	—	—	—	—	91.1%	56.9%
Qwen3.7 Max Preview Qwen	—	—	—	—	74.29%	—	—	—	—	—	1474	—	—	—	—	—

Scores are not normalised across benchmarks. Each column uses its own metric. Compare columns independently.