Update README.md
Browse files
README.md
CHANGED
|
@@ -5,12 +5,9 @@ colorFrom: gray
|
|
| 5 |
colorTo: yellow
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
| 8 |
-
thumbnail: >-
|
| 9 |
-
https://cdn-uploads.huggingface.co/production/uploads/65b9463ac9aa94b1ca85414b/1lQ_nGrGT4hurdTRk_Yv_.jpeg
|
| 10 |
---
|
| 11 |
|
| 12 |
<div style="max-width:980px;margin:0 auto;padding:24px 16px;font:16px/1.55 system-ui,-apple-system,Segoe UI,Roboto;">
|
| 13 |
-
|
| 14 |
<header style="display:flex;gap:16px;align-items:center;margin-bottom:12px;">
|
| 15 |
<img src="./assets/logo.png" alt="Foaster.ai" width="42" height="42" style="border-radius:8px">
|
| 16 |
<div>
|
|
@@ -19,12 +16,14 @@ thumbnail: >-
|
|
| 19 |
</div>
|
| 20 |
</header>
|
| 21 |
|
| 22 |
-
<p><strong>Foaster.ai</strong> is a French start-up
|
| 23 |
|
| 24 |
-
<
|
|
|
|
|
|
|
| 25 |
|
| 26 |
-
<
|
| 27 |
-
<p style="margin:0 0
|
| 28 |
|
| 29 |
<div style="border:1px solid #e5e7eb;border-radius:12px;overflow:hidden">
|
| 30 |
<table style="width:100%;border-collapse:collapse;font-size:14px">
|
|
@@ -40,15 +39,10 @@ thumbnail: >-
|
|
| 40 |
</tr>
|
| 41 |
</thead>
|
| 42 |
<tbody>
|
| 43 |
-
<tr><td style="padding:10px"
|
| 44 |
-
<tr><td style="padding:10px"
|
| 45 |
-
<tr><td style="padding:10px"
|
| 46 |
-
<tr><td style="padding:10px">#4</td><td style="padding:10px">Qwen3-235B-Instruct (Alibaba)</td><td style="padding:10px;text-align:center">1176</td><td style="padding:10px;text-align:center">1077</td><td style="padding:10px;text-align:center">1274</td><td style="padding:10px;text-align:center">45.0%</td><td style="padding:10px;text-align:center">60</td></tr>
|
| 47 |
-
<tr><td style="padding:10px">#5</td><td style="padding:10px">GPT-5-mini (OpenAI)</td><td style="padding:10px;text-align:center">1173</td><td style="padding:10px;text-align:center">1107</td><td style="padding:10px;text-align:center">1239</td><td style="padding:10px;text-align:center">41.7%</td><td style="padding:10px;text-align:center">60</td></tr>
|
| 48 |
-
<tr><td style="padding:10px">#6</td><td style="padding:10px">Kimi-K2-Instruct (Moonshot AI)</td><td style="padding:10px;text-align:center">1130</td><td style="padding:10px;text-align:center">1168</td><td style="padding:10px;text-align:center">1091</td><td style="padding:10px;text-align:center">36.7%</td><td style="padding:10px;text-align:center">60</td></tr>
|
| 49 |
-
<tr><td style="padding:10px">#7</td><td style="padding:10px">GPT-OSS-120B (OpenAI)</td><td style="padding:10px;text-align:center">980</td><td style="padding:10px;text-align:center">931</td><td style="padding:10px;text-align:center">1030</td><td style="padding:10px;text-align:center">15.0%</td><td style="padding:10px;text-align:center">60</td></tr>
|
| 50 |
</tbody>
|
| 51 |
</table>
|
| 52 |
</div>
|
| 53 |
-
|
| 54 |
-
</div>
|
|
|
|
| 5 |
colorTo: yellow
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
<div style="max-width:980px;margin:0 auto;padding:24px 16px;font:16px/1.55 system-ui,-apple-system,Segoe UI,Roboto;">
|
|
|
|
| 11 |
<header style="display:flex;gap:16px;align-items:center;margin-bottom:12px;">
|
| 12 |
<img src="./assets/logo.png" alt="Foaster.ai" width="42" height="42" style="border-radius:8px">
|
| 13 |
<div>
|
|
|
|
| 16 |
</div>
|
| 17 |
</header>
|
| 18 |
|
| 19 |
+
<p><strong>Foaster.ai</strong> is a French start-up focused on the agentic era. At <em>Foaster Labs</em>, our Werewolf Benchmark studies how LLMs behave under social pressure—leadership, bluffing, and resistance to manipulation.</p>
|
| 20 |
|
| 21 |
+
<div style="display:flex;align-items:center;gap:10px;margin:14px 0 22px;">
|
| 22 |
+
<a href="https://huggingface.co/spaces/Foaster-ai/werewolf-leaderboard" style="padding:10px 14px;border:1px solid #e5e7eb;border-radius:10px;text-decoration:none;">🔗 Full leaderboard →</a>
|
| 23 |
+
</div>
|
| 24 |
|
| 25 |
+
<h3 style="margin:0 0 8px;">Results — Podium (role-conditioned Elo)</h3>
|
| 26 |
+
<p style="margin:0 0 10px;color:#64748b">ELO-W = wolf (manipulation power) · ELO-V = villager (manipulation resistance)</p>
|
| 27 |
|
| 28 |
<div style="border:1px solid #e5e7eb;border-radius:12px;overflow:hidden">
|
| 29 |
<table style="width:100%;border-collapse:collapse;font-size:14px">
|
|
|
|
| 39 |
</tr>
|
| 40 |
</thead>
|
| 41 |
<tbody>
|
| 42 |
+
<tr><td style="padding:10px">🥇 #1</td><td style="padding:10px">GPT-5 (OpenAI)</td><td style="padding:10px;text-align:center">1492</td><td style="padding:10px;text-align:center">1508</td><td style="padding:10px;text-align:center">1476</td><td style="padding:10px;text-align:center">96.7%</td><td style="padding:10px;text-align:center">60</td></tr>
|
| 43 |
+
<tr><td style="padding:10px">🥈 #2</td><td style="padding:10px">Gemini 2.5 Pro (Google)</td><td style="padding:10px;text-align:center">1261</td><td style="padding:10px;text-align:center">1163</td><td style="padding:10px;text-align:center">1360</td><td style="padding:10px;text-align:center">63.3%</td><td style="padding:10px;text-align:center">60</td></tr>
|
| 44 |
+
<tr><td style="padding:10px">🥉 #3</td><td style="padding:10px">Gemini 2.5 Flash (Google)</td><td style="padding:10px;text-align:center">1188</td><td style="padding:10px;text-align:center">1103</td><td style="padding:10px;text-align:center">1273</td><td style="padding:10px;text-align:center">51.7%</td><td style="padding:10px;text-align:center">60</td></tr>
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
</tbody>
|
| 46 |
</table>
|
| 47 |
</div>
|
| 48 |
+
</div>
|
|
|