Qwen3.7-Plus

Qwen3.7-Plus ranks first on 5 of the 124 benchmarks with five or more models scored.

Qwen Released June 2nd, 2026 Compare with others

132

Benchmarks with a score

Ranked first, out of five or more models

In the top three

Qwen Jun 2026

Qwen3.7-Plus

Closed weights

147.9 #78 of 256

Epoch Capabilities Index

Self-Reported Index 153.7 #68 of 404

MMMU-Pro 79% #21 /90
IFBench 79.1% #13 /80
AutomationBench 3.70% #36 /42

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.

Knowledge and language

Benchmark	Score	Rank	Source
MMLU-Pro	88.5%	#4 of 167	Lab model card
SimpleVQA	81.7%	#1 of 30	Lab model card
IFEval	94.6%	#8 of 135	Lab model card
StudyArena Text	1,307	#6 of 85	Official leaderboard
MMLU-ProX	85.4%	#2 of 23	Lab model card
MMLU-Redux	94.5%	#4 of 45	Lab model card
SuperGPQA	71.4%	#4 of 35	Lab model card
Phare	74.1%	#10 of 62	Official leaderboard
IFBench	79.1%	#13 of 80	Lab model card
MRCR v2	91.7%	#5 of 30	Lab model card
LMArena (Elo)	1,455	#57 of 335	Official leaderboard
MAXIFE	88.8%	#2 of 11	Lab model card
MMMLU	89%	#14 of 71	Lab model card
INCLUDE	83%	#8 of 31	Lab model card
NOVA-63	58.8%	#3 of 11	Lab model card
Global PIQA	90.3%	#5 of 14	Lab model card
Last Translation Benchmark	10.2	#17 of 36	Official leaderboard
Humanity's Last Exam	34.7%	#74 of 154	Lab model card
Extended NYT Connections	74.8%	#53 of 103	Official leaderboard
DesignArena ASCII Art	1,134	#57 of 77	Official leaderboard
Document Arena	1,446	#31 of 39	Official leaderboard

Math and science

Benchmark	Score	Rank	Source
PolyMath	84%	#2 of 24	Lab model card
OTIS Mock AIME 2024-2025	93.3%	#60 of 212	Epoch AI run
GPQA Diamond	87.9%	#65 of 229	Epoch AI run
IMO-AnswerBench	86%	#12 of 37	Lab model card
DTBench	84%	#74 of 180	Official leaderboard
HMMT 2026	92.9%	#8 of 19	Lab model card
HiPhO	84.1%	#2 of 4	Lab model card
FrontierMath Tiers 1-3 v2	34.4%	#64 of 86	Official leaderboard
CritPt	6.00%	#11 of 13	Lab model card
MathArena (Apex, IMO, USAMO)	22.7%	#11 of 12	Lab model card

Coding

Benchmark	Score	Rank	Source
LiveCodeBench	89.6%	#3 of 54	Lab model card
SciCode	51.3%	#8 of 49	Lab model card
SWE-bench Verified	77.7%	#31 of 155	Lab model card
DesignArena Data Visualization	1,276	#27 of 118	Official leaderboard
DesignArena Website	1,262	#43 of 151	Official leaderboard
StructEval	76.8%	#9 of 28	Official leaderboard
DesignArena Code	1,260	#46 of 143	Official leaderboard
LoopArena	34.2%	#2 of 6	Official leaderboard
DesignArena Game Dev	1,250	#48 of 143	Official leaderboard
DesignArena UI Component	1,256	#48 of 139	Official leaderboard
DesignArena SVG	1,202	#36 of 103	Official leaderboard
DesignArena 3D Design	1,221	#51 of 136	Official leaderboard
QwenVision2Code	1,772	#2 of 5	Official leaderboard
SWE-bench Multilingual	75.8%	#30 of 73	Lab model card
QwenSVG	1,588	#3 of 7	Official leaderboard
SWE-Bench Pro	57.6%	#37 of 81	Lab model card
Vibe Code Bench	46.4%	#71 of 120	Official leaderboard
Monthly-SWEBench	47%	#8 of 12	Official leaderboard
DesignArena Image to HTML	1,171	#38 of 51	Official leaderboard
NL2Repo-Bench	41.1%	#23 of 30	Lab model card
AndroidBench	57.7%	#25 of 32	Official leaderboard
Code Migration	12.9%	#62 of 78	Official leaderboard
QwenBlenderBench	41.5%	#5 of 6	Official leaderboard
QwenWebDev	1,536	#5 of 6	Official leaderboard

Agents and tools

Benchmark	Score	Rank	Source
Terminal-Bench 2.0	70.3%	#4 of 63	Lab model card
DeepPlanning	62.3%	#1 of 10	Lab model card
BFCL V4	72.9%	#4 of 30	Lab model card
AndroidWorld	81%	#5 of 23	Lab model card
VITA-Bench	45.6%	#4 of 16	Lab model card
ScreenSpot-Pro	79%	#9 of 32	Lab model card
Pencil Puzzle Bench	16.7%	#15 of 53	Official leaderboard
OSWorld-Verified	73.3%	#10 of 33	Official leaderboard
QwenClawBench	61.8%	#2 of 6	Lab model card
MCPMark	58.7%	#4 of 10	Lab model card
GameHorizon	68.7	#15 of 37	Official leaderboard
MMSearch-Plus	41.4%	#1 of 2	Lab model card
SnakeBench	23	#102 of 188	Official leaderboard
MCP Atlas	73.2%	#28 of 46	Lab model card
SkillsBench	54.9%	#9 of 14	Lab model card
Mystery Game Puzzles	17%	#62 of 84	Epoch AI run
MM-BrowseComp	46.3%	#4 of 5	Lab model card
Agent Arena	-7.99%	#47 of 56	Official leaderboard
AutomationBench	3.70%	#36 of 42	Official leaderboard
OSWorld-Science	15.2%	#10 of 11	Official leaderboard
Claw-Eval	62.7%	#12 of 13	Lab model card
RecreationBench	9.15%	#10 of 10	Official leaderboard
OSWorld 2.0	2.80%	#7 of 7	Official leaderboard
BrowseComp-VL	51.1%	#3 of 3	Lab model card

Professional work

Benchmark	Score	Rank	Source
MedXpertQA-MM	71%	#4 of 21	Lab model card
MortgageTax	66.2%	#33 of 87	Official leaderboard
RadLE 2.0	472.0	#6 of 12	Official leaderboard
SpreadsheetBench	86.3%	#3 of 6	Lab model card
MerchantBench	29.4	#5 of 8	Official leaderboard
Vals Index v2	38.6%	#47 of 65	Official leaderboard
Excel Modeling Benchmark	49.3%	#56 of 76	Official leaderboard
Legal Research Bench	16.4%	#71 of 93	Official leaderboard
Vals Finance Agent v2	38.2%	#65 of 80	Official leaderboard
Tax Agent Bench	10.5%	#69 of 84	Official leaderboard
Harvey LAB (Legal Agent Benchmark)	0%	#76 of 80	Official leaderboard
CoWorkBench	65.1%	#7 of 7	Lab model card

Vision, audio and robotics

Benchmark	Score	Rank	Source
CC-OCR-Bench-V2	76.6%	#1 of 15	Official leaderboard
MLVU	87.4%	#2 of 22	Lab model card
OCRBench v2	70.7%	#2 of 22	Lab model card
RealWorldQA	86.9%	#4 of 38	Lab model card
WorldVQA	61.1%	#1 of 9	Lab model card
Video-MME	88%	#6 of 51	Lab model card
ODinW-13	51.1%	#2 of 13	Lab model card
MATH-Vision (MathVision)	90.3%	#9 of 51	Lab model card
Video-MMMU	85.4%	#7 of 36	Lab model card
LingoQA	83.4%	#2 of 10	Lab model card
QwenWorldBench	62.1%	#1 of 5	Official leaderboard
ERQA	69.8%	#8 of 36	Lab model card
MMMU-Pro	79%	#21 of 90	Lab model card
CharXiv	85.9%	#18 of 75	Lab model card
Vision Arena	1,262	#37 of 136	Official leaderboard
BabyVision	70.4%	#9 of 27	Official leaderboard
LVBench	76.2%	#11 of 31	Lab model card
ZeroBench	13%	#32 of 76	Official leaderboard
PerceptionBench (Moonshot)	51.1%	#8 of 16	Official leaderboard
TVBench	78.2%	#4 of 7	Lab model card
QwenVisualOffice	32.4%	#4 of 6	Official leaderboard
CountQA	77%	#2 of 3	Lab model card
RoTA-Bench	0%	#6 of 8	Official leaderboard
VisFactor	42.8%	#3 of 4	Lab model card
Chartography	15.8%	#33 of 43	Official leaderboard
Claw-Eval-MM	55.7%	#6 of 6	Lab model card
SURDS	77.2%	#2 of 2	Lab model card
Ego3D-Bench	5.90	#1 of 1	Lab model card
VLADBench	77.2%	#1 of 1	Lab model card

Safety and security

Benchmark	Score	Rank	Source
nocot-bench (NCRI)	83.1	#50 of 185	Official leaderboard
SecCodeBench	70.1%	#2 of 6	Official leaderboard
Dictatorship Eval	45.6%	#14 of 20	Official leaderboard
CyberBench (Vals)	37.5%	#25 of 26	Official leaderboard
PatchEval	62.6%	#7 of 7	Official leaderboard
PatchEval-Verified	62.6%	#7 of 7	Official leaderboard

Other

Benchmark	Score	Rank	Source
SAGE v1.1 (Vals)	89.2%	#6 of 29	Official leaderboard
LMCA	37.6%	#67 of 147	Official leaderboard
Conceptual Reasoning Index	49.4	#72 of 151	Official leaderboard
ACCoRD	60.7	#89 of 152	Official leaderboard
Vals Multimodal Index	53.9%	#22 of 33	Official leaderboard
SAGE (Vals)	39.3%	#59 of 81	Official leaderboard

Its lab's numbers put it at 153.7, 5.8 points above its ECI

The Self-Reported Index fits one score to the 51 capability results Qwen reported for this model, on the scale of the Epoch Capabilities Index. Labs choose which benchmarks to show and how to run them, so read it as the lab's claim, not an independent measurement. The 90% interval runs from 152.1 to 155.2. How we compute it.

Its lab's numbers next to 7 leaderboards

Where the benchmark's own leaderboard, or Epoch AI's run, also has this model. Gaps mostly come from different harnesses, effort levels and task subsets. Every pair.

Benchmark	Lab says	Board says	Gap
GPQA Diamond	90.3% GPQA Diamond	87.9% Epoch AI run	+2.4 pts
BabyVision	70.4% BabyVision 70.4 / 64.7 (with CI / without CI)	70.4% Leaderboard, tools	Same
OSWorld-Verified	73.3% OSWorld-Verified (enable_thinking=False)	73.3% Leaderboard, 100 steps	Same
QwenSVG	1,588 QwenSVG	1,588 Leaderboard	Same
QwenVision2Code	1,772 QwenVision2Code	1,772 Leaderboard	Same
QwenWebDev	1,536 QwenWebDev	1,536 Leaderboard	Same
QwenWorldBench	62.1% QwenWorldBench	62.1% Leaderboard	Same

Qwen's models over time

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

Source: Epoch Capabilities Index, Epoch AI (CC BY 4.0)

Its launch post

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

Qwen3.7-Plus: Multimodal Agent Intelligence (blog) Jun 1, 2026

Terminal Bench 2.0-Terminus (avg of 5 runs) 70.3
SWE-Verified (internal scaffold) 77.7
SWE-Pro (Qwen-corrected tasks) 57.6
SWE-Multilingual 75.8
NL2repo 41.1
SciCode 51.3
QwenWebDev 1536
QwenSVG 1588
Qwenclaw 61.8
CoWorkBench 65.1
ClawEval 62.7
Skillsbench (OpenCode, 78 tasks, avg of 5) 54.9
BFCL-V4 72.9
MCP-Mark 58.7
MCP-Atlas (public set) 73.2
Vitabench (claude-4.5-sonnet judge) 45.6
Deep-Planning 62.3
SpreadSheetBench-v1 86.3
Kernel Bench L3 2.06/98% (median speedup / share faster than torch.compile) 2.06
QwenWorldBench 62.1
GPQA Diamond 90.3
HLE 34.7
LiveCodeBench 89.6
HMMT 2026 Feb 92.9
IMOAnswerBench 86
CritPT 6
Apex 22.7
MMLU-Pro 88.5
MMLU-Redux 94.5
SuperGPQA 71.4
IFEval 94.6
IFBench 79.1
MRCR-v2 128k 91.7
WMT24++ (XCOMET-XXL, 55 languages) 84.6
MAXIFE 88.8
MMMLU 89
MMLU-ProX (29 languages) 85.4
NOVA-63 58.8
INCLUDE 83
Global PIQA 90.3
PolyMATH 84
MMMU-Pro 79
MathVision 90.3
BabyVision 70.4 / 64.7 (with CI / without CI) 70.4
CharXiv(RQ) 85.9 / 84.4 (with CI / without CI) 85.9
HiPhO 84.1
ERQA 69.8
VisFactor 42.8
MedXpertQA-MM 71
ScreenSpot Pro (enable_thinking=False) 79
OSWorld-Verified (enable_thinking=False) 73.3
AndroidWorld 81
QwenVision2Code 1772
ClawEval-MM 55.7
SimpleVQA (with search) 81.7
WorldVQA (with search) 61.1
MMSearchPlus (with search) 41.4
BC-VL (with search) 51.1
MMBC (with search) 46.3
RealWorldQA 86.9
CountQA 77
OmniDocBench1.5 91.4
OCR-Bench-V2(EN) 70.7, OCR-Bench-V2(ZH) 67.1 70.7
ODinW13 51.1
LingoQA 83.4
Ego3D-Bench (lower is better) 5.9
SURDS 77.2
VLADBench 77.2
VideoMME (w/ sub.) 88
VideoMMMU 85.4
MLVU (M-Avg) 87.4
TVBench 78.2
LVBench 76.2