BIRD-SQL

BIRD-SQL evaluates database-grounded text-to-SQL systems on execution accuracy over large cross-domain databases.

102rows
test_execution_accuracyprimary metric
2026-05-06sampled

Metadata

Metrics

Dev Execution Accuracy, Test Execution Accuracy

Latest Results

Rows are ranked by Test execution accuracy from the overall BIRD-SQL leaderboard. Source system display names are preserved.

Rank Subject Test Execution Accuracy Model Match Provenance Sampled
1 Human Performance 92.96 Imported 2026-05-06
2 AskData + GPT-4o 81.95 Imported 2026-05-06
3 Agentar-Scale-SQL 81.67 Imported 2026-05-06
4 LongData-SQL 77.53 Imported 2026-05-06
5 SiriusAI-Text2SQL-Agent 77.03 Imported 2026-05-06
6 Zhiwen-Lingsi-Agent 76.63 Imported 2026-05-06
7 DeepEye-SQL 76.58 Imported 2026-05-06
8 GT-ChatBI-SQL 76.47 Imported 2026-05-06
9 Q-SQL 76.47 Imported 2026-05-06
10 MIC 2 -SQL 76.41 Imported 2026-05-06
11 CHASE-SQL + Gemini 76.02 Imported 2026-05-06
12 xiaoyi-text-to-sql 75.96 Imported 2026-05-06
13 RED-SQL 75.91 Imported 2026-05-06
14 JoyDataAgent-SQL 75.85 Imported 2026-05-06
15 Sinovatio-SQL 75.80 Imported 2026-05-06
16 TCDataAgent-SQL 75.74 Imported 2026-05-06
17 Contextual-SQL 75.63 Imported 2026-05-06
18 XiYan-SQL 75.63 Imported 2026-05-06
19 CYAN-SQL 75.35 Imported 2026-05-06
20 DB-SQL 75.35 Imported 2026-05-06
21 MCR-SQL + Qwen2.5-Coder-32B-Instruct 75.29 Imported 2026-05-06
22 DeepEye-SQL 75.07 Imported 2026-05-06
23 Spektr-SQL 74.85 Imported 2026-05-06
24 JT-SQLAgent 74.06 Imported 2026-05-06
25 CSC-SQL + XiYanSQL-QwenCoder-32B-2412 73.67 Imported 2026-05-06
26 ExSL + granite-34b-code 73.17 Imported 2026-05-06
27 Reasoning-SQL 14B 72.78 Imported 2026-05-06
28 GPT-5.5-xhigh 72.55 Imported 2026-05-06
29 GenaSQL 72.28 Imported 2026-05-06
30 OpenSearch-SQL, v2 + GPT-4o 72.28 Imported 2026-05-06
31 OmniSQL-32B 72.05 Imported 2026-05-06
32 Distillery + GPT-4o 71.83 Imported 2026-05-06
33 Share + GPT-5 71.83 Imported 2026-05-06
34 CSC-SQL + Qwen2.5-Coder-7B-Instruct 71.72 Imported 2026-05-06
35 LEAF-SQL 71.60 Imported 2026-05-06
36 Queryosity 71.16 Imported 2026-05-06
37 CHESS IR + CG + UT 71.10 Imported 2026-05-06
38 Infly-RL-SQL-32B 70.60 Imported 2026-05-06
39 SLM-SQL + Qwen2.5-Coder-1.5B-Instruct 70.49 Imported 2026-05-06
40 Alpha-SQL + Qwen2.5-Coder-32B-Instruct 70.26 Imported 2026-05-06
41 Insights AI 70.26 Imported 2026-05-06
42 PURPLE + RED + GPT-4o 70.21 Imported 2026-05-06
43 GSR 69.26 Imported 2026-05-06
44 PB-SQL, GPT-4o 69.26 Imported 2026-05-06
45 TC-SQL 69.20 Imported 2026-05-06
46 RECAP + Gemini 69.03 Imported 2026-05-06
47 XiYanSQL-QwenCoder-32B 69.03 Imported 2026-05-06
48 ByteBrain 68.87 Imported 2026-05-06
49 RSL-SQL + GPT-4o 68.70 Imported 2026-05-06
50 OmniSQL-7B 67.97 Imported 2026-05-06
51 ExSL + granite-20b-code 67.86 Imported 2026-05-06
52 AskData + GPT-4o 67.41 Imported 2026-05-06
53 CHESS IR + SS + CG 66.69 Imported 2026-05-06
54 E-SQL + GPT-4o 66.29 Imported 2026-05-06
55 Arcwise + GPT-4o 66.21 Imported 2026-05-06
56 NucliOS 65.90 Imported 2026-05-06
57 Command A 65.68 Imported 2026-05-06
58 RSL-SQL + DeepSeek-v2 65.51 Imported 2026-05-06
59 MCS-SQL + GPT-4 65.45 Imported 2026-05-06
60 SCL-SQL 65.23 Imported 2026-05-06
61 OpenSearch-SQL,v1 + GPT-4 64.95 Imported 2026-05-06
62 SFT CodeS-15B + SQLFixAgent 64.62 Imported 2026-05-06
63 PURPLE + GPT-4o 64.51 Imported 2026-05-06
64 MSL-SQL + DeepSeek-V2.5 64 Imported 2026-05-06
65 EBA-SQL + GPT-4 63.50 Imported 2026-05-06
66 Sense 63.39 Imported 2026-05-06
67 OneSQL-v0.1-Qwen-32B 63.33 Imported 2026-05-06
68 GRA-SQL 63.22 Imported 2026-05-06
69 SuperSQL 62.66 Imported 2026-05-06
70 SLM-SQL + Qwen2.5-Coder-0.5B-Instruct 61.82 Imported 2026-05-06
71 {Chat2Query} (GPT-4 + data entity modeling) (PingCAP) 60.98 Imported 2026-05-06
72 Dubo-SQL, v1 60.71 Imported 2026-05-06
73 Struct-SQL 60.42 Imported 2026-05-06
74 SFT CodeS-15B 60.37 Imported 2026-05-06
75 DTS-SQL + DeepSeek 7B 60.31 Imported 2026-05-06
76 E-SQL + GPT-4o mini 59.81 Imported 2026-05-06
77 MAC-SQL + GPT-4 59.59 Imported 2026-05-06
78 SFT CodeS-7B 59.25 Imported 2026-05-06
79 TA-SQL + GPT-4 59.14 Imported 2026-05-06
80 DAIL-SQL + GPT-4 57.41 Imported 2026-05-06
81 ExSL + granite-20b-code 57.13 Imported 2026-05-06
82 DeepSeek 56.68 Imported 2026-05-06
83 DIN-SQL + GPT-4 55.90 Imported 2026-05-06
84 Mistral 55.84 Imported 2026-05-06
85 GPT-4 54.89 Imported 2026-05-06
86 Interactive-T2S 54.11 Imported 2026-05-06
87 Prem-1B-SQL 51.54 Imported 2026-05-06
88 Claude-2 49.02 Imported 2026-05-06
89 Open-SQL 47.74 Imported 2026-05-06
90 ChatGPT + CoT 40.08 Imported 2026-05-06
91 ChatGPT 39.30 Imported 2026-05-06
92 Codex 36.47 Imported 2026-05-06
93 Palm-2 33.04 Imported 2026-05-06
94 ChatGPT + CoT 28.95 Imported 2026-05-06
95 ChatGPT 26.77 Imported 2026-05-06
96 Codex 24.86 Imported 2026-05-06
97 T5-3B 24.05 Imported 2026-05-06
98 T5-Large 20.94 Imported 2026-05-06
99 T5-Base 12.89 Imported 2026-05-06
100 T5-3B 11.17 Imported 2026-05-06
101 T5-Large 10.38 Imported 2026-05-06
102 T5-Base 7.06 Imported 2026-05-06