Model
Model explorer

openPangu-2.0-Flash (Thinking)

OPEN
Huawei · openPangu family · released Jun 12, 2026

Announced at HDC 2026 (June 12, 2026); Huawei's first frontier-scale open-weight release, trained entirely on Ascend 910B NPUs with zero NVIDIA involvement. A larger 505B-total/18B-active 'Pro' sibling in the same openPangu 2.0 family was also announced but its benchmark card could not be independently confirmed via a fetchable source this pass (see uncertain). Scores here are the model's 'Thinking' inference-mode numbers; a 'Non-Thinking' mode is reported separately as a sibling entry per the effort-tier convention.

ReasoningCodingVisionFunction callingTool useAgentic
2087.7
Elo · rank #53
Parameters
92B
Active params
6B (MoE)
Context
512K tokens
Architecture
MoE with MLA + DSA/SWA hybrid attention (1:2 ratio), 4-stream mHC residual, multi-token prediction heads; trained on Huawei Ascend NPUs (no NVIDIA hardware)
License
OpenPangu Model License Agreement v2.0
Languages
API price (in/out)
No hosted API
Modalities
text
Benchmark results
Bar shows position within the tracked field; marker = field best
AIMEMath93.3%#27
best: GPT-5.2 · 100.0%
BrowseCompAgents57.0%#28
best: Kimi K3 · 91.2%
GPQA DiamondReasoning83.7%#63
best: GPT-5.6 · 94.6%
IFBenchReasoning79.6%#7
best: MiniMax M3 · 83.0%
IFEvalReasoning95.9%#3
best: Gemma 4 26B A4B · 98.5%
LiveCodeBenchCoding85.1%#22
best: DeepSeek-V4-Pro (Think Max) · 93.5%
PinchBenchAgents85.6%#5
best: Trinity-Large-Thinking · 91.9%
SWE-bench VerifiedCoding63.1%#73
best: Claude Fable 5 · 95.0%
Run it locally
VRAM @ Q4
VRAM @ FP16
Fits on (Q4)
Multi-node cluster required
Throughput data unavailable.
Quantizations
API price weights · each benchmark row carries its own source badge (see methodology)