Spider

Spider evaluates complex cross-domain semantic parsing and text-to-SQL generalization over unseen database schemas.

34rows
execution_accuracy_with_valuesprimary metric
2026-05-06sampled

Metadata

Metrics

Execution Accuracy with Values

Latest Results

Rows are ranked by execution accuracy with values from the first official Spider leaderboard table. Source display names are preserved without canonical model mapping.

Rank Subject Execution Accuracy with Values Model Match Provenance Sampled
1 MiniSeek 91.20 Imported 2026-05-06
2 DAIL-SQL + GPT-4 + Self-Consistency 86.60 GPT-4
openai-gpt-4
Imported 2026-05-06
3 DAIL-SQL + GPT-4 86.20 GPT-4
openai-gpt-4
Imported 2026-05-06
4 DPG-SQL + GPT-4 + Self-Correction 85.60 GPT-4
openai-gpt-4
Imported 2026-05-06
5 DIN-SQL + GPT-4 85.30 GPT-4.5
openai-gpt-4.5-preview
Imported 2026-05-06
6 Hindsight Chain of Thought with GPT-4 83.90 GPT-4
openai-gpt-4
Imported 2026-05-06
7 C3 + ChatGPT + Zero-Shot 82.30 Imported 2026-05-06
8 Hindsight Chain of Thought with GPT-4 and Instructions 80.80 GPT-4
openai-gpt-4
Imported 2026-05-06
9 RESDSQL-3B + NatSQL (DB content used) 79.90 Imported 2026-05-06
10 SeaD + PQL (DB content used) 78.50 Imported 2026-05-06
11 DIN-SQL + CodeX 78.20 Imported 2026-05-06
12 CatSQL + GraPPa (DB content used) 78 Imported 2026-05-06
13 T5-3B+NatSQL+Token Preprocessing (DB content used) 78 Imported 2026-05-06
14 Graphix-3B+PICARD (DB content used) 77.60 Imported 2026-05-06
15 SHiP+PICARD (DB content used) 76.60 Imported 2026-05-06
16 RASAT + NatSQL + Reranker (DB content used) 76.50 Imported 2026-05-06
17 N-best List Rerankers + PICARD (DB content used) 75.90 Imported 2026-05-06
18 RASAT+PICARD (DB content used) 75.50 Imported 2026-05-06
19 T5-SR (DB content used) 75.20 Imported 2026-05-06
20 RESDSQL+T5-1.1-lm100k-xl (DB content used) 75.10 Imported 2026-05-06
21 T5-3B+PICARD (DB content used) 75.10 Imported 2026-05-06
22 RESDSQL+T5-1.1-lm100k-large (DB content used) 74.80 Imported 2026-05-06
23 SeaD + SP (DB content used) 74.10 Imported 2026-05-06
24 RATSQL+GAP+NatSQL (DB content used) 73.30 Imported 2026-05-06
25 SmBoP + GraPPa (DB content used) 71.10 Imported 2026-05-06
26 T5-Base+NatSQL+Token Preprocessing (DB content used) 71.10 Imported 2026-05-06
27 RaSaP + ELECTRA (DB content used) 70 Imported 2026-05-06
28 BRIDGE v2 + BERT(ensemble) (DB content used) 68.30 Imported 2026-05-06
29 COMBINE (DB content used) 68.20 Imported 2026-05-06
30 T5QL-Base (DB content used) 66.80 Imported 2026-05-06
31 BRIDGE v2 + BERT (DB content used) 64.30 Imported 2026-05-06
32 AuxNet + BART (DB content used) 62.60 Imported 2026-05-06
33 BRIDGE + BERT (DB content used) 59.90 Imported 2026-05-06
34 GAZP + BERT (DB content used) 53.50 Imported 2026-05-06