Skip to content

Qwen3.7 Plus

AlibabaProprietaryReasoningVerifiedReleased Jun 3, 2026Input: text, image
Compare with Qwen3.6 PlusSource scores ↗OpenRouter ↗
Overall score
53.8
Rank 81 of 222 · 42.7–64.8
Context window
1M
1,000,000 tokens
Price per 1M tokens
$0.32 in · $1.28 out
Source: OpenRouter
Blended price
$0.56
3:1 input:output tokens
Output speed
—
Not measured yet

Category scores

Scores per capability area with the model's rank among ranked models in that category.

  1. 1Multilingual#395.7
  2. 2Instruction following#1792.8
  3. 3Multimodal#1682.0
  4. 4Reasoning80.0
  5. 5Knowledge#6764.9
  6. 6Agentic & tool use#8364.8
  7. 7Math64.3
  8. 8Coding#6655.1
Higher is better. #N is the model's rank in that category, where it is eligible to be ranked.

Benchmark results (51)

As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.

Multimodal

Design Arena Website1270#27 of 91
MMMU-Pro79.0#15 of 48
CharXiv85.9#14 of 42
MathVision90.3#6 of 20
SimpleVQA81.7#1 of 17
ERQA69.8#6 of 16
RealWorldQA86.9#4 of 16
ScreenSpot Pro79.0#8 of 15
VideoMMMU85.4#6 of 12
OmniDocBench 1.591.4#3 of 11
Video-MME (with subtitle)88.0#3 of 11
MLVU (M-Avg)87.4#2 of 9
MedXpertQA (MM)71.0#5 of 8
OCRBench V270.7#2 of 5
ODINW1351.1#1 of 4
MMSearch-Plus41.4#1 of 1

Agentic & tool use

MCP Atlas73.2#22 of 42
Terminal-Bench 2.070.3#4 of 39
Claw-Eval62.7#18 of 36
OSWorld-Verified73.3#18 of 35
OSWorld 2.02.8#24 of 24
BFCL v472.9#5 of 19
VITA-Bench45.6#2 of 11
QwenClawBench61.8#2 of 10
AndroidWorld81.0#5 of 8
DeepPlanning62.3#1 of 7
QwenWebBench1536#2 of 5

Multilingual

SWE Multilingual75.8#24 of 46
MMLU-ProX85.4#3 of 16
INCLUDE83.0#7 of 10
NOVA-6358.8#3 of 7
PolyMath84.0#2 of 6
MAXIFE88.8#2 of 5

Knowledge

GPQA90.3#24 of 117
HLE34.7#38 of 69
MMLU-Pro88.5#3 of 67
SuperGPQA71.4#6 of 20
MMLU-Redux94.5#4 of 15
MMMLU89.0#3 of 11

Coding

SWE-bench Verified77.7#28 of 98
SWE-bench Pro57.6#35 of 69
LiveCodeBench v689.6#8 of 46
NL2Repo41.1#23 of 31
SciCode51.3#5 of 23

Math

FrontierMath v2 (Tiers 1-3)34.386#50 of 64
HMMT Feb 202692.9#5 of 24
IMOAnswerBench86.0#5 of 9
Apex22.7#8 of 8

Instruction following

IFEval94.6#4 of 53
IFBench79.1#14 of 42

Reasoning

MRCRv291.7#2 of 12

Pricing by source

USD per 1M tokens.

SourceInputOutputCached in
List price (OpenRouter)$0.32$1.28—
OpenRouter qwen/qwen3.7-plus$0.32$1.28$0.064

Arena ratings

Human-preference ratings from LMArena. Best-rated variant shown.

Text1455#46 · 42.1K votes
Vision1278#37 · 14.2K votes
Documents1444#30 · 4.6K votes

Speed

Measured by us through OpenRouter (median of trials).

Not measured yet.

Related models

Same family

Similar score