Qwen3.5-35B-A3B

Qwen / Qwen

85scores
75benchmarks
$0.15 / $1 per 1M tokenscost in/out

Metadata

Qwen Open source

Aliases: qwen-qwen3.5-35b-a3b, qwen-qwen3.5-35b-a3b-20260224, qwen/qwen3.5-35b-a3b, qwen/qwen3.5-35b-a3b-20260224, qwen3.5-35b-a3b, qwen3.5-35b-a3b-20260224

Benchmark Results

Benchmark Category Rank Score Sampled
AutoBench Agentic 18 2.82 2026-05-06
DeepPlanning Agentic 5 0.23 2026-05-06
Gert Labs Rankings Agentic 52 0.35 2026-05-11
ITBench-AA Agentic 22 21.5% 2026-05-28
OSWorld-Verified Agentic 11 0.55 2026-05-06
PinchBench Agentic 43 0.78 2026-05-06
RuneBench Agentic 18 0.70 2026-05-05
ScreenSpot-Pro Agentic 8 68.60 2026-05-06
t2-bench Agentic 8 0.81 2026-05-06
Tau2-Bench Telecom Agentic 61 89.2% 2026-05-11
Tau2-Bench Telecom Agentic 79 86.3% 2026-05-11
Terminal-Bench Hard Agentic 114 26.5% 2026-05-11
Terminal-Bench Hard Agentic 210 10.6% 2026-05-11
TIR-Bench Agentic 3 0.56 2026-05-06
Vending-Bench 2 Agentic 31 462.69 2026-05-28
OpenUGI Alignment 1015 23.15 2026-05-06
OpenUGI Alignment 1132 16.30 2026-05-06
ALE-Bench Coding 85 221.80 2026-05-06
Arena AI Code Coding 60 1249 2026-05-06
Codeforces Coding 5 0.822 2026-05-28
FullStackBench en Coding 3 0.58 2026-05-06
FullStackBench zh Coding 3 0.55 2026-05-06
SciCode Coding 141 37.7% 2026-05-11
SciCode Coding 259 29.3% 2026-05-11
OmniDocBench 1.5 Document Understanding 4 0.89 2026-05-06
EmbSpatialBench Embodied 6 0.83 2026-05-06
Vectara HHEM Hallucination Leaderboard Factuality 59 89.50 2026-05-06
BenchLM General Knowledge 56 56 2026-05-06
MAXIFE General Knowledge 5 0.87 2026-05-06
MMLU-ProX General Knowledge 5 0.81 2026-05-06
MMLU-Redux General Knowledge 9 0.93 2026-05-06
NOVA-63 General Knowledge 5 0.57 2026-05-06
MedXpertQA Healthcare 4 0.61 2026-05-06
PMC-VQA Healthcare 3 0.62 2026-05-06
SlakeVQA Healthcare 3 0.79 2026-05-06
IFBench Instruction Following 8 0.70 2026-05-06
Artificial Analysis Intelligence Index Intelligence 97 37.12 2026-05-11
Artificial Analysis Intelligence Index Intelligence 144 30.69 2026-05-11
Humanity's Last Exam Intelligence 72 19.7% 2026-05-11
Humanity's Last Exam Intelligence 115 12.8% 2026-05-11
MathVision Intelligence 15 83.90 2026-05-06
AA-LCR Long Context 9 0.58 2026-05-06
AIME 2026 Mathematics 6 93.33 2026-05-06
DynaMath Mathematics 5 0.85 2026-05-06
HMMT 2025 Mathematics 18 0.89 2026-05-06
HMMT February 2026 Mathematics 7 81.82 2026-05-06
PolyMATH Mathematics 5 0.64 2026-05-06
BabyVision Multimodal 4 0.38 2026-05-06
CC-OCR Multimodal 8 0.81 2026-05-06
CharXiv-R Multimodal 14 0.78 2026-05-06
LingoQA Multimodal 3 0.79 2026-05-06
LVBench Multimodal 4 0.71 2026-05-06
MLVU Multimodal 6 0.86 2026-05-06
MMVU Multimodal 4 0.72 2026-05-06
Nuscene Multimodal 3 0.15 2026-05-06
SimpleVQA Multimodal 8 0.58 2026-05-06
VideoMME w sub. Multimodal 5 0.87 2026-05-06
VideoMME w/o sub. Multimodal 3 0.82 2026-05-06
VideoMMMU Multimodal 14 0.80 2026-05-06
VLMsAreBlind Multimodal 1 0.97 2026-05-06
ZEROBench Multimodal 5 0.08 2026-05-06
ZEROBench-Sub Multimodal 4 0.34 2026-05-06
Artificial Analysis Openness Index Openness 141 38.89 2026-05-11
Artificial Analysis Openness Index Openness 142 38.89 2026-05-11
ERQA Reasoning 3 0.65 2026-05-06
Global PIQA Reasoning 7 0.87 2026-05-06
GPQA Diamond Reasoning 60 84.5% 2026-05-11
GPQA Diamond Reasoning 87 81.9% 2026-05-11
OJBench Reasoning 5 0.36 2026-05-06
InvisibleBench Safety 11 0.11 2026-05-06
CritPt Science 101 0.9% 2026-05-11
CritPt Science 118 0.6% 2026-05-11
BrowseComp-zh Search 3 0.69 2026-05-06
Seal-0 Search 6 0.41 2026-05-06
WideSearch Search 8 0.57 2026-05-06
CountBench Spatial Reasoning 1 0.98 2026-05-06
Hypersim Spatial Reasoning 1 0.13 2026-05-06
RefCOCO-avg Spatial Reasoning 7 0.89 2026-05-06
RefSpatialBench Spatial Reasoning 6 0.64 2026-05-06
SUNRGBD Spatial Reasoning 4 0.33 2026-05-06
BFCL-V4 Tool Use 4 0.67 2026-05-06
WMT24++ Translation 7 0.76 2026-05-06
ODinW Vision 10 0.43 2026-05-06
K-MetBench Weather 6 81.8% accuracy 2026-05-28
K-MetBench Weather 22 69.3% accuracy 2026-05-28