List your company
ResearchFormerly WizWand

Code Generation on LCB v6

57.1AccuracyQwen3-30B-A3B
7.80420.60233.446.198Aug 12, 2025Sep 30, 2025Nov 18, 2025Jan 7, 2026Feb 25, 2026Apr 15, 2026Jun 4, 2026
Updated 4mo ago

Evaluation results

MethodLinks
Qwen3-30B-A3BBase Model=Qwen3-30B-A3B2026.0557.1
ZEDABase Model=Qwen3-30B-A3B2026.0553.2
NETSFT→OPDBase Model=Qwen3-30B-A3B2026.0552.9
ZEDASFTBase Model=Qwen3-30B-A3B2026.0552.8
Dynamic SkippingBase Model=Qwen3-30B-A3B2026.0551.9
NETSFTBase Model=Qwen3-30B-A3B2026.0550.9
SDPO2026.0148.8
Qwen2.5-32B-Instruct + Bootcamp-SFT-RLModel=Qwen2.5-32B-Instruct, Training Stage=Bootcamp-SFT-RL2025.0847.4
ZEDABase Model=GLM-4.7-Flash2026.0545.6
ZEDASFTBase Model=GLM-4.7-Flash2026.0545
NETSFTBase Model=GLM-4.7-Flash2026.0544.7
DS-R1-Distilled-Qwen-32B + Bootcamp-RLModel=DS-R1-Distilled-Qwen-32B, Training Stage=Bootcamp-RL2025.0844.6
GLM-4.7-FlashBase Model=GLM-4.7-Flash2026.0544.4
Qwen2.5-32B-Instruct + Bootcamp-SFTModel=Qwen2.5-32B-Instruct, Training Stage=Bootcamp-SFT2025.0844
NETSFT→OPDBase Model=GLM-4.7-Flash2026.0543.8
Qwen3-30B A3B-Instruct-2507Orchestration Strategy=Self Refine2026.0443.25
Qwen3-Coder 30B-A3B-InstructOrchestration Strategy=Base+Tool2026.0442.8
SFT on self-teacher2026.0142.7
ParaManager-MonoOrchestration Strategy=Mono2026.0442.5
Qwen3-30B A3B-Instruct-2507Orchestration Strategy=Majority Vote2026.0442.45
Qwen3-30B A3B-Instruct-2507Orchestration Strategy=Base2026.0442.1
ParaManagerOrchestration Strategy=Unified2026.0441.51
ParaManager-SerialOrchestration Strategy=Serial2026.0441.38
Qwen3-30B A3B-Instruct-2507Orchestration Strategy=Base+Tool2026.0441.25
RouterOrchestration Strategy=Static Workflow2026.0441.25
GRPO2026.0141.2
PuppeteerOrchestration Strategy=Serial Orchestration2026.0441.06
GPT-OSS-20BOrchestration Strategy=Base+Tool2026.0440.87
GPT-OSS-20BOrchestration Strategy=Self Refine2026.0440.2
Qwen3-Coder 30B-A3B-InstructOrchestration Strategy=Majority Vote2026.0440.2
Qwen3-Coder 30B-A3B-InstructOrchestration Strategy=Self Refine2026.0440.2
Qwen3-4B Instruct-2507Orchestration Strategy=Self Refine2026.0440.12
Qwen3-4B Instruct-2507Orchestration Strategy=Base2026.0439.95
Qwen3-Coder 30B-A3B-InstructOrchestration Strategy=Base2026.0439.68
Qwen3-4B Instruct-2507Orchestration Strategy=Majority Vote2026.0439.54
Qwen3-4B Instruct-2507Orchestration Strategy=Base+Tool2026.0439.52
ToolOrchestraOrchestration Strategy=Serial Orchestration2026.0438.27
GPT-OSS-20BOrchestration Strategy=Base2026.0437.43
GPT-OSS-20BOrchestration Strategy=Majority Vote2026.0437.2
EvoFlowOrchestration Strategy=Static Workflow2026.0437.12
Meta Agent SearchOrchestration Strategy=Static Workflow2026.0435.16
AdaMoEBase Model=Qwen3-30B-A3B2026.0534.3
DS-R1-Distilled-Qwen-32BModel=DS-R1-Distilled-Qwen-32B2025.0833.7
ParaManager-SFTOrchestration Strategy=SFT2026.0433.58
Dynamic SkippingBase Model=GLM-4.7-Flash2026.0532.4
Qwen2.5-32B-Instruct + Bootcamp-RLModel=Qwen2.5-32B-Instruct, Training Stage=Bootcamp-RL2025.0829.7
AdaMoEBase Model=GLM-4.7-Flash2026.0528.6
Qwen2.5-32B-InstructModel=Qwen2.5-32B-Instruct2025.0828
Base2026.0127.9
SDAR-8BScale=8B, Tokens=55B, FLOPs=2640, Decoding Strategy=greedy static decoding, Block Size=42026.0614.5
SDAR-4BScale=4B, Tokens=55B, FLOPs=1320, Decoding Strategy=greedy static decoding, Block Size=42026.0612.6
OPDLM-4BScale=4B, Tokens=0.076B, FLOPs=2.4, Decoding Strategy=greedy static decoding, Block Size=42026.0610.4
Fast-dLLM-v2-7BScale=8B, Tokens=1B, FLOPs=42, Decoding Strategy=greedy static decoding, Block Size=42026.069.7
OPDLM-8BScale=8B, Tokens=0.066B, FLOPs=4.2, Decoding Strategy=greedy static decoding, Block Size=42026.069.7