Share your thoughts, 1 month free Claude Pro on usSee more

Coding on MBPP+

97.88Pass@1

K-EXAONE-236B-A23B

Updated 5d ago

Evaluation Results

Method	Links
K-EXAONE-236B-A23B 2026.03		97.88
Qwen-3-30B-A3B 2026.03		90.48
HyperCLOVAX-SEED-Think-32B 2026.03		89.9
Mi:dm K 2.5 Pro (March ‘26) 2026.03		89.68
Gemini 3-Pro 2026.02		86.21
GPT-5 (High) 2026.02		83.1
HyperCLOVAX-SEED-Think-32B 2026.03		83.07
ERNIE 5.0 2026.02		82.54
Llama-3.1-8B-inst 2026.01		81.8
Youtu-LLM 2025.12		81.8
DS V3.2-Thinking 2026.02		81.48
Qwen3 2025.12		80.8
RDPO 2026.05		79.63
Exaone-3.5-7.8B-inst 2026.01		79.4
RL initialization model 2026.05		78.84
GRPO 2026.05		78.57
Qwen-3-30B-A3B 2026.03		77.7
Mi:dm 2.0 Base-inst 2026.01		77.5
Mi:dm K 2.5 Pro (March ‘26) 2026.03		76.7
P-GRPO (Code+RM) 2026.05		76.2
Solar-Open-100B 2026.03		75.13
GRPO (Code) 2026.05		75.1
HASP-Evolve + RS 2026.05		74
Gemini 2.5-Pro 2026.02		73.8
Qwen3-14B 2026.01		73.4
HASP-Intervention (w. Teacher) 2026.05		73
KodCode-RL Step 256 2026.05		72.8
AceCoderRM 2026.05		71.2
Qwen3 2025.12		71
GPT-4o 2026.05		71
KodCode-RL Step 128 2026.05		70.9
Qwen 3 VL 32B Instruct 2025.12		69
AceCoderRule 2026.05		68.3
Qwen 3 32B 2025.12		67.9
Qwen2.5-7B-Instruct 2026.05		67.7
GPT-4o-mini 2026.05		67
K-EXAONE-236B-A23B 2026.03		66.9
Qwen 2.5 32B 2025.12		66.6
SmolLM3 2025.12		66.1
Prompt-Only Skills 2026.05		66
Gemma 3 27B 2025.12		65.7
Self-SFT 2026.05		65.6
Olmo 3.1 32B Instruct 2025.12		65.1
HASP-Intervention (PF-only) 2026.05		65
Iter-SFT 2026.05		63.8
Olmo 3.1 32B Instruct 2025.12		63.6
DFT 2026.05		63
SFT (vanilla) 2026.05		63
Llama3.1 2025.12		62.7
Qwen3-4B 2026.01		62.4
Qwen3-8B 2026.01		62.2
Base 2026.05		62.2
Base 2026.05		62.2
Base 2026.05		62.2
Base 2026.05		62.2
RA-Agent (multi-loop) 2026.05		62
Gemma3 2025.12		61.9
Olmo 3.1 32B Instruct 2025.12		61.5
Gemma 2 27B 2025.12		61.2
Low-SFT 2026.05		61.1
Anchored Learning 2026.05		61.1
Iter-SFT 2026.05		61.1
Mi:dm 2.0 Mini-inst 2026.01		60.9
Anchored Learning 2026.05		60.3
OLMo3-7B-Instruct 2026.01		60.2
Exaone-3.5-2.4B-inst 2026.01		59.8
STM 2026.05		59.8
Anchored Learning 2026.05		59.8
STM 2026.05		59.8
Qwen3-4B 2026.01		59.5
KL-SFT 2026.05		59.5
Self-SFT 2026.05		59.5
Iter-SFT 2026.05		59.5
Anchored Learning 2026.05		59.3
Anchored Learning 2026.05		59.3
Low-SFT 2026.05		59
Low-SFT 2026.05		59
SFT 2026.05		58.2
Low-SFT 2026.05		57.7
Molmo2-8B 2026.01		57.5
STM 2026.05		56.9
Molmo2-4B 2026.01		56.2
Molmo2-O-7B 2026.01		55.7
Low-SFT 2026.05		55.6
Self-sft 2026.05		55.6
Low-SFT 2026.05		55.3
DFT 2026.05		55
Anchored Learning 2026.05		54.5
Iter-SFT 2026.05		53.5
UnSafeChain 2026.03		53.2
Base 2026.05		51.6
SafeChain 2026.03		50.8
Low-SFT 2026.05		50
Self-SFT 2026.05		50
OLMo 2 32B 2025.12		49
PreSafe 2026.03		48.4
STM 2026.05		48.4
DFT 2026.05		48.1
Apertus 70B 2025.12		45.8
Anchored Learning 2026.05		45.5

Showing 100 of 117 rows