List your company

Grammatical Error Correction on UNLP 2023 (test)

78.52PrecisionmBART50-large
22.068836.724451.3866.0356Jun 8, 2026

Evaluation results

MethodLinks
mBART50-largeProtocol=fine-tuned, Lang.=-2026.0678.5250.670.71
mT5-largePrompting Strategy=fine-tuned SOTA2026.0676.8161.3973.14
mT5-largeProtocol=fine-tuned, Lang.=-2026.0676.8161.3973.14
Gemini 3.1-ProPrompting Strategy=minimal-edits + few-shot + optimized-v2 (A.5.2), Lang.=UA2026.0670.7763.6369.22
Gemini 3-FlashPrompting Strategy=minimal-edits + few-shot + optimized-v2 (A.5.2), Lang.=UA2026.0669.9862.8768.43
Claude Opus 4.6Prompting Strategy=minimal-edits + few-shot (A.4.1), Lang.=UA2026.0668.5449.7563.73
Claude Sonnet 4.6Prompting Strategy=minimal-edits + few-shot + optimized-v1 (A.5.1), Lang.=UA2026.0666.7336.5857.29
Claude Opus 4.6Prompting Strategy=minimal-edits + few-shot + optimized-v1 (A.5.1), Lang.=UA2026.0666.5438.2757.98
GPT-5.4Prompting Strategy=minimal-edits + few-shot + optimized-v1 (A.5.1), Lang.=UA2026.0663.9451.7561.07
Gemini 3.1-ProPrompting Strategy=minimal-edits + few-shot (A.4.1), Lang.=UA2026.0663.7663.3563.68
Claude Sonnet 4.6Prompting Strategy=minimal-edits + zero-shot8 (A.3.1), Lang.=UA2026.0662.4448.5559.06
Gemini 3-FlashPrompting Strategy=minimal-edits + few-shot (A.4.1), Lang.=UA2026.0660.2866.1861.38
GPT-5.4Prompting Strategy=minimal-edits + few-shot (A.4.1), Lang.=UA2026.0660.0258.459.69
GPT-4.1-miniPrompting Strategy=minimal-edits + few-shot + optimized-v1 (A.5.1), Lang.=UA2026.0655.7551.4954.84
Claude Opus 4.6Protocol=zero-shot, Lang.=UA, UA?=+2026.0649.251.649.7
Claude Opus 4.6Protocol=zero-shot, Lang.=EN2026.0647.646.247.3
GPT-4.1-miniPrompting Strategy=minimal-edits + few-shot (A.4.1), Lang.=UA2026.0647.1651.4847.97
Claude Sonnet 4.6Protocol=zero-shot, Lang.=UA, UA?=+2026.0642.747.7643.63
Claude Sonnet 4.6Protocol=zero-shot, Lang.=EN2026.0641.7945.8342.54
Gemini 3.1-ProProtocol=zero-shot, Lang.=EN2026.0641.558.0344.01
Gemini 3.1-ProProtocol=zero-shot, Lang.=UA2026.0639.1662.0142.28
Gemini 3-FlashProtocol=zero-shot, Lang.=EN2026.0639.0964.8542.46
GPT-4.1-miniProtocol=zero-shot, Lang.=EN2026.0639.0651.9241.09
Gemini 3-ProProtocol=zero-shot, Lang.=EN2026.0637.8960.5440.96
GPT-4.1Protocol=zero-shot, Lang.=EN2026.0637.1755.5439.8
GPT-5.4 (medium)Protocol=zero-shot, Lang.=EN2026.0636.8762.9640.2
GPT-4.1-miniProtocol=zero-shot, Lang.=UA2026.0636.7353.0339.13
Gemini 3-ProProtocol=zero-shot, Lang.=UA2026.0636.363.5839.71
GPT-5.1 (medium)Protocol=zero-shot, Lang.=EN2026.0636.0660.1539.2
Gemini 3-FlashProtocol=zero-shot, Lang.=UA2026.0635.9167.3839.61
Kimi-K2Protocol=zero-shot, Lang.=EN2026.0634.2452.7436.82
GPT-5.2 (medium)Protocol=zero-shot, Lang.=EN2026.0634.0466.3137.71
GPT-5.4 (medium)Protocol=zero-shot, Lang.=UA2026.0632.7365.3536.36
GPT-5.1 (medium)Protocol=zero-shot, Lang.=UA2026.0632.3562.6135.82
GPT-4.1Protocol=zero-shot, Lang.=UA2026.0630.2458.4133.47
GPT-5.2 (medium)Protocol=zero-shot, Lang.=UA2026.0629.8966.933.6
Kimi-K2Protocol=zero-shot, Lang.=UA2026.0629.0360.1132.38
Lapa v0.1.2Protocol=zero-shot, Lang.=UA, UA?=+2026.0628.5732.3829.26
GPT-3.5Protocol=zero-shot, Lang.=EN2026.0625.836.227.4
Lapa v0.1.2Protocol=zero-shot, Lang.=EN2026.0624.2423.5224.09