Qwen3.7-Max

Qwen3.7-Max ranks first on 7 of the 94 benchmarks it has scores on.

Qwen Released 19 May 2026 Family Qwen3.7 The lab's model card

Benchmarks with a score

Ranked first, out of five or more models

In the top three

Qwen May 2026

Closed weights Flagship

154.2 #45 of 271

Epoch Capabilities Index

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Benchmark	Score	Rank	Source
MMLU-Pro	89.6%	#2 of 151	Model card
MMLU-Redux	95%	#1 of 38	Model card
MMLU-ProX	87%	#1 of 17	Model card
IFEval	94.3%	#8 of 126	Model card
SuperGPQA	73.6%	#2 of 26	Model card
LMArena (Elo)	1,474	#35 of 333	Official leaderboard
Phare	75.6%	#8 of 62	Official leaderboard
MMMLU	90.3%	#9 of 62	Model card
BullshitBench V2	72%	#18 of 122	Official leaderboard
IFBench	79.1%	#12 of 70	Model card
Humanity's Last Exam	53.5%	#28 of 147	Model card
INCLUDE	86.2%	#5 of 25	Model card
MAXIFE	89.2%	#1 of 5	Model card
MRCR v2	90.4%	#6 of 27	Model card
BullshitBench	52.7%	#26 of 107	Official leaderboard
SimpleQA Verified	55.8%	#22 of 84	Epoch AI
Wer wird Millionär? LLM Benchmark	87044.0	#21 of 76	Official leaderboard
Extended NYT Connections	85.1%	#31 of 97	Official leaderboard
NOVA-63	59%	#2 of 5	Model card
WMT24++	85.8%	#5 of 12	Model card
Global PIQA	91.4%	#4 of 8	Model card
EQ-Bench 4	1,100	#27 of 32	Official leaderboard

Benchmark	Score	Rank	Source
HMMT 2026	97.1%	#1 of 18	Model card
PolyMath	86.5%	#1 of 18	Model card
IMO-AnswerBench	90%	#3 of 37	Model card
GPQA Diamond	90.9%	#34 of 219	Epoch AI
SimpleBench	70.4%	#19 of 100	Official leaderboard
DTBench	87.1%	#35 of 178	Official leaderboard
OTIS Mock AIME 2024-2025	95.6%	#42 of 202	Epoch AI
CritPt	13.4%	#49 of 160	Epoch AI
FrontierMath Tier 4 v2	34.1%	#29 of 71	Epoch AI
FrontierMath Tiers 1-3 v2	64.6%	#38 of 89	Epoch AI
ProofBench	26%	#26 of 59	Official leaderboard
ResearchClawBench	18.7	#11 of 23	Official leaderboard
MathArena (Apex, IMO, USAMO)	44.5%	#7 of 13	Model card
xbench-ScienceQA	70.8%	#18 of 29	Official leaderboard
NatureBench	7.78%	#13 of 18	Official leaderboard

Benchmark	Score	Rank	Source
LiveCodeBench	91.6%	#2 of 73	Model card
SciCode	53.5%	#6 of 47	Model card
IOI (Vals)	46.8%	#11 of 55	Official leaderboard
SWE-bench Verified	77.3%	#7 of 32	Epoch AI
SWE-bench Multilingual	78.3%	#16 of 70	Model card
SWE-Bench Pro	60.6%	#25 of 77	Model card
ALE-Bench	1,189	#42 of 121	Epoch AI
FrontierCS	61.9	#5 of 14	Official leaderboard
WebDev Arena	1,517	#39 of 105	Epoch AI
Code Arena	1,515	#52 of 124	Official leaderboard
NL2Repo-Bench	47.2%	#14 of 28	Model card
QwenSVG	1,608	#1 of 2	Model card
QwenWebDev	1,568	#1 of 2	Model card
Vibe Code Bench	47.7%	#63 of 115	Official leaderboard
Monthly-SWEBench	51%	#7 of 12	Official leaderboard
EvoCode-Bench v2	11.9%	#8 of 13	Official leaderboard
Code Migration	13.1%	#60 of 78	Official leaderboard
MLS-Bench	31.7%	#12 of 15	Official leaderboard
AndroidBench	54.2%	#27 of 32	Official leaderboard
GBAEval	0.41%	#20 of 21	Official leaderboard
Kernel Bench L3	1.98	#2 of 2	Model card

Benchmark	Score	Rank	Source
PinchBench 2.0	92.5%	#2 of 57	Official leaderboard
BFCL V4	75%	#1 of 24	Model card
SnakeBench	34	#12 of 183	Official leaderboard
Terminal-Bench 2.0	69.7%	#5 of 61	Model card
Pencil Puzzle Bench	40%	#7 of 53	Official leaderboard
VITA-Bench	47.9%	#2 of 12	Model card
QwenClawBench	64.3%	#1 of 6	Model card
CEO-Bench	$365,346	#5 of 19	Official leaderboard
MCPMark	60.8%	#3 of 10	Model card
Mystery Game Puzzles	32%	#29 of 80	Epoch AI
SkillsBench	59.2%	#5 of 13	Model card
MCP Atlas	76.4%	#17 of 40	Model card
PACT	1,511	#14 of 26	Official leaderboard
Claw-Eval	65.2%	#8 of 14	Model card
Chess Puzzles	26%	#51 of 83	Epoch AI
Long-Horizon-Terminal-Bench (LHTB)	29.6%	#18 of 25	Official leaderboard
Agent Arena	-0.07	#41 of 53	Official leaderboard
EBR-bench	9.52%	#23 of 28	Epoch AI
Harbor-Index	4.90%	#8 of 9	Official leaderboard

Benchmark	Score	Rank	Source
TaxEval v2	75.3%	#19 of 129	Official leaderboard
LegalBench	84.9%	#28 of 138	Official leaderboard
SpreadsheetBench	87%	#2 of 6	Model card
CorpFin v2	63.7%	#42 of 119	Official leaderboard
Excel Modeling Benchmark	57%	#42 of 76	Official leaderboard
MedScribe	79.4%	#58 of 98	Official leaderboard
Harvey LAB (Legal Agent Benchmark)	1.67%	#52 of 80	Official leaderboard
Vals Finance Agent v2	47.8%	#52 of 80	Official leaderboard
MedCode	38.8%	#65 of 96	Official leaderboard
Legal Research Bench	25.5%	#60 of 88	Official leaderboard
Tax Agent Bench	15.8%	#56 of 79	Official leaderboard
E-Commerce Bench	1.65	#15 of 19	Official leaderboard
PolicyBench	76.9%	#41 of 50	Official leaderboard
CoWorkBench	67.2%	#5 of 6	Model card

Benchmark	Score		Rank	Source
VoxelBench	1,612		#34 of 56	Official leaderboard
QwenWorldBench	57.3%		#2 of 2	Model card

Benchmark	Score		Rank	Source
BrowseSafe++	89%		#5 of 15	Official leaderboard
DrugDiscoveryBench	29.3%		#17 of 19	Official leaderboard

Benchmark	Score	Rank	Source
LMCA	44%	#42 of 139	Epoch AI
Conceptual Reasoning Index	56.9	#46 of 149	Official leaderboard
ACCoRD	65.3	#70 of 150	Official leaderboard

Qwen's models in color, against every other model on the Epoch Capabilities Index, by release date.

The benchmarks the lab chose to headline, with the scores it gave.