Model results

EvalPlus

Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.

Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.

Official source

← All evaluation groups

EvalPlus

Source: EvalPlus (reviewed publisher results)
Version: mbpp+-v0.2.0-399
Measurement date: Not reported
Metric: % · Higher is better
Evaluation scope: EvalPlus harness; mbpp+; MBPP+ v0.2.0 extended tests; 399 hand-verified tasks from MBPP-sanitized 427; greedy decoding; pass@1; prompted=True; result date not supplied

Exact score ties share a position. Positions do not establish statistical significance. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.

#1Qwen2.5 Coder 32B Instruct
qwen/qwen-2.5-coder-32b-instruct
77%
View modelEvidence independent
#2DeepSeek V3
deepseek/deepseek-chat-v3
73%
View modelEvidence independent
#3Claude 3 Haiku
anthropic/claude-3-haiku
68.8%
View modelEvidence independent
#4Mixtral 8x22B Instruct
mistralai/mixtral-8x22b-instruct
64.3%
View modelEvidence independent
#5Llama 3.1 8B Instruct
meta/llama-3.1-8b-instruct
55.6%
View modelEvidence independent