diff --git a/README.md b/README.md
index 4bccd89b4..f5e45874b 100644
--- a/README.md
+++ b/README.md
@@ -21,16 +21,19 @@ Unlike prior SQL-only or single-database benchmarks, DAB stresses agents under *
## 🏆 Leaderboard
-| Rank | Model | Pass@1 | Date |
-| ---- | -------------- | ------------------- | ------- |
-| 1 | PromptQL (Gemini-3.1-Pro) (5 trials/query) | 0.543 | 2026-03-018 |
-| 2 | PromptQL (Claude-Opus-4.6) (5 trials/query) | 0.508 | 2026-03-02 |
-| 3 | Claude-Opus-4.6 (5 trials/query) | 0.4376 | 2026-03-18 |
-| 4 | Gemini-3-Pro | 0.38 | 2026-03-02 |
-| 5 | GPT-5-mini | 0.30 | 2026-03-02 |
-| 6 | GPT-5.2 | 0.25 | 2026-03-02 |
-| 7 | Kimi-K2 | 0.23 | 2026-03-02 |
-| 8 | Gemini-2.5-Flash | 0.09 | 2026-03-02 |
+| Rank | Model | Pass@1 | Date | Submission |
+| ---- | -------------- | ------------------- | ------- | ---------- |
+| 1 | Pi Coding Agent (Claude-Opus-4.6) (5 trials/query) | 0.5603 | 2026-04-21 | [#31](https://github.com/ucbepic/DataAgentBench/pull/31) |
+| 2 | PromptQL (Gemini-3.1-Pro) (5 trials/query) | 0.543 | 2026-03-18 | [#24](https://github.com/ucbepic/DataAgentBench/pull/24) |
+| 3 | PromptQL (Claude-Opus-4.6) (5 trials/query) | 0.508 | 2026-03-02 | [#23](https://github.com/ucbepic/DataAgentBench/pull/23) |
+| 4 | Oracle Forge — Tenacious Intelligence (Claude-Sonnet-4.6) (5–7 trials/query) | 0.4554 | 2026-04-21 | [#32](https://github.com/ucbepic/DataAgentBench/pull/32) |
+| 5 | Claude-Opus-4.6 (5 trials/query) | 0.4376 | 2026-03-18 | [#22](https://github.com/ucbepic/DataAgentBench/pull/22) |
+| 6 | Gemini-3-Pro | 0.38 | 2026-03-02 | — |
+| 7 | GPT-5-mini | 0.30 | 2026-03-02 | — |
+| 8 | GPT-5.2 | 0.25 | 2026-03-02 | — |
+| 9 | Kimi-K2 | 0.23 | 2026-03-02 | — |
+| 10 | Oracle Forge — Team Cohere (Gemini-2.0-Flash) (5 trials/query) | 0.128 | 2026-04-21 | [#38](https://github.com/ucbepic/DataAgentBench/pull/38) |
+| 11 | Gemini-2.5-Flash | 0.09 | 2026-03-02 | — |
### How to Submit to the Leaderboard
diff --git a/docs/app.js b/docs/app.js
index 901021ec8..3fb9ca5b0 100644
--- a/docs/app.js
+++ b/docs/app.js
@@ -172,6 +172,18 @@ function renderOverallLeaderboard(rows) {
const trialsTd = createElement("td", "num", String(row.trials));
const passTd = createElement("td", "num", formatPercentFromScore(row.passAt1));
const dateTd = createElement("td", "", row.date);
+ const prTd = document.createElement("td");
+ if (row.prUrl) {
+ const prMatch = row.prUrl.match(/\/pull\/(\d+)/);
+ const prLabel = prMatch ? `PR #${prMatch[1]}` : "PR";
+ const prLink = createElement("a", "", prLabel);
+ prLink.href = row.prUrl;
+ prLink.target = "_blank";
+ prLink.rel = "noopener noreferrer";
+ prTd.appendChild(prLink);
+ } else {
+ prTd.textContent = "—";
+ }
tr.appendChild(rankTd);
tr.appendChild(agentTd);
@@ -179,6 +191,7 @@ function renderOverallLeaderboard(rows) {
tr.appendChild(trialsTd);
tr.appendChild(passTd);
tr.appendChild(dateTd);
+ tr.appendChild(prTd);
tbody.appendChild(tr);
});
}
diff --git a/docs/data/leaderboards.json b/docs/data/leaderboards.json
index 3de92cda7..e34e1620e 100644
--- a/docs/data/leaderboards.json
+++ b/docs/data/leaderboards.json
@@ -1,5 +1,5 @@
{
- "updatedAt": "2026-03-21",
+ "updatedAt": "2026-04-21",
"sources": [
"README leaderboard table",
"PromptQL stratified table shared by maintainers",
@@ -8,33 +8,56 @@
"overallLeaderboard": [
{
"rank": 1,
+ "agent": "Pi Coding Agent + Claude Opus 4.6",
+ "trials": 5,
+ "passAt1": 0.5603,
+ "team": "Pi Coding Agent",
+ "teamUrl": "https://github.com/mariozechner/pi-coding-agent",
+ "prUrl": "https://github.com/ucbepic/DataAgentBench/pull/31",
+ "date": "2026-04-21"
+ },
+ {
+ "rank": 2,
"agent": "PromptQL + Gemini 3.1 Pro",
"trials": 5,
"passAt1": 0.543,
"team": "Hasura PromptQL",
"teamUrl": "https://promptql.io/",
+ "prUrl": "https://github.com/ucbepic/DataAgentBench/pull/24",
"date": "2026-03-18"
},
{
- "rank": 2,
+ "rank": 3,
"agent": "PromptQL + Claude Opus 4.6",
"trials": 5,
"passAt1": 0.508,
"team": "Hasura PromptQL",
"teamUrl": "https://promptql.io/",
+ "prUrl": "https://github.com/ucbepic/DataAgentBench/pull/23",
"date": "2026-03-02"
},
{
- "rank": 3,
+ "rank": 4,
+ "agent": "Oracle Forge (Tenacious Intelligence) + Claude Sonnet 4.6",
+ "trials": 5,
+ "passAt1": 0.4554,
+ "team": "Tenacious Intelligence Corp",
+ "teamUrl": "https://github.com/ucbepic/DataAgentBench/pull/32",
+ "prUrl": "https://github.com/ucbepic/DataAgentBench/pull/32",
+ "date": "2026-04-21"
+ },
+ {
+ "rank": 5,
"agent": "Claude Opus 4.6 ReAct",
"trials": 5,
"passAt1": 0.4376,
"team": "EPIC Data Lab",
"teamUrl": "https://epic.berkeley.edu/",
+ "prUrl": "https://github.com/ucbepic/DataAgentBench/pull/22",
"date": "2026-03-18"
},
{
- "rank": 4,
+ "rank": 6,
"agent": "Gemini-3-Pro ReAct",
"trials": 50,
"passAt1": 0.38,
@@ -43,7 +66,7 @@
"date": "2026-03-02"
},
{
- "rank": 5,
+ "rank": 7,
"agent": "GPT-5-mini ReAct",
"trials": 50,
"passAt1": 0.3,
@@ -52,7 +75,7 @@
"date": "2026-03-02"
},
{
- "rank": 6,
+ "rank": 8,
"agent": "GPT-5.2 ReAct",
"trials": 50,
"passAt1": 0.25,
@@ -61,7 +84,7 @@
"date": "2026-03-02"
},
{
- "rank": 7,
+ "rank": 9,
"agent": "Kimi-K2 ReAct",
"trials": 50,
"passAt1": 0.23,
@@ -70,7 +93,17 @@
"date": "2026-03-02"
},
{
- "rank": 8,
+ "rank": 10,
+ "agent": "Oracle Forge (Team Cohere) + Gemini 2.0 Flash",
+ "trials": 5,
+ "passAt1": 0.128,
+ "team": "Team Cohere",
+ "teamUrl": "https://github.com/trp1-cohere-team/data-analytics-agent",
+ "prUrl": "https://github.com/ucbepic/DataAgentBench/pull/38",
+ "date": "2026-04-21"
+ },
+ {
+ "rank": 11,
"agent": "Gemini-2.5-Flash ReAct",
"trials": 50,
"passAt1": 0.09,
diff --git a/docs/index.html b/docs/index.html
index d5b991c8f..8437331f5 100644
--- a/docs/index.html
+++ b/docs/index.html
@@ -128,6 +128,7 @@ Leaderboard
n |
Pass@1 |
Date |
+ Submission |