Ergebnisse aktualisiert (14 Läufe)

index.html

@@ -49,6 +49,23 @@
   <td class="num" data-value="">–</td>
   <td data-value="2026-09-18">2026-09-18</td>
 </tr>
+<tr data-reasoning="off">
+  <td data-value="qwen3.8-flash-next-abliterated (pool)">
+    <a href="runs/32.html" class="strong">qwen3.8-flash-next-abliterated (pool)</a>
+    <div class="sub">Reasoning off · direct · 2× NVIDIA DGX Spark, je 128 GB RAM</div>
+  </td>
+  <td class="num strong" data-value="72.53692007797271">72.5</td>
+  <td class="num" data-value="77.15084175084174" title="mmlu_pro: 87.0 ± 1.9 (n=300)&#10;gpqa_diamond_gen: 75.3 ± 3.1 (n=198)&#10;musr_gen: 69.2 ± 2.9 (n=250)&#10;">77.2</td>
+  <td class="num" data-value="72.0" title="omni_math_gen: 72.0 ± 2.8 (n=250)&#10;">72.0</td>
+  <td class="num" data-value="55.16290726817043" title="ifbench: 43.7 ± 2.9 (n=300)&#10;ifeval: 90.0 ± 2.5 (n=150)&#10;">55.2</td>
+  <td class="num" data-value="77.0" title="livecodebench_gen: 77.0 ± 3.0 (n=200)&#10;">77.0</td>
+  <td class="num strong" data-value="81.37085137085137" title="mmlu_prox_de: 86.7 ± 2.0 (n=300)&#10;include_de_gen: 70.8 ± 3.7 (n=154)&#10;">81.4</td>
+  <td class="num" data-value="41.18692185852276">41</td>
+  <td class="num" data-value="37.23226449422559" title="overall 113.3 t/s with 3 parallel requests, from 9 of 9 tasks">37</td>
+  <td class="num" data-value="2569.0663350056934">2569</td>
+  <td class="num" data-value="1566.3277919957181">1566</td>
+  <td data-value="2026-09-27">2026-09-27</td>
+</tr>
 <tr data-reasoning="off">
   <td data-value="qwen3.8-flash-next-ple4">
     <a href="runs/15.html" class="strong">qwen3.8-flash-next-ple4</a>
@@ -59,7 +76,7 @@
   <td class="num strong" data-value="73.2" title="omni_math_gen: 73.2 ± 2.8 (n=250)&#10;">73.2</td>
   <td class="num" data-value="49.56390977443609" title="ifbench: 36.0 ± 2.8 (n=300)&#10;ifeval: 90.7 ± 2.4 (n=150)&#10;">49.6</td>
   <td class="num" data-value="75.5" title="livecodebench_gen: 75.5 ± 3.0 (n=200)&#10;">75.5</td>
-  <td class="num strong" data-value="81.13708513708514" title="mmlu_prox_de: 85.7 ± 2.0 (n=300)&#10;include_de_gen: 72.1 ± 3.6 (n=154)&#10;">81.1</td>
+  <td class="num" data-value="81.13708513708514" title="mmlu_prox_de: 85.7 ± 2.0 (n=300)&#10;include_de_gen: 72.1 ± 3.6 (n=154)&#10;">81.1</td>
   <td class="num" data-value="26.376464212349354">26</td>
   <td class="num" data-value="21.59310838133867" title="overall 64.4 t/s with 3 parallel requests, from 5 of 9 tasks">22</td>
   <td class="num" data-value="2041.4640201348918">2041</td>
@@ -100,6 +117,23 @@
   <td class="num" data-value="2954.110997961834">2954</td>
   <td data-value="2026-09-19">2026-09-19</td>
 </tr>
+<tr data-reasoning="off">
+  <td data-value="qwen3-coder-next">
+    <a href="runs/30.html" class="strong">qwen3-coder-next</a>
+    <div class="sub">Q6 · Reasoning off · direct · NVIDIA DGX Spark, 128 GB RAM</div>
+  </td>
+  <td class="num strong" data-value="65.05957469431154">65.1</td>
+  <td class="num" data-value="71.26060606060607" title="mmlu_pro: 82.0 ± 2.2 (n=300)&#10;gpqa_diamond_gen: 68.2 ± 3.3 (n=198)&#10;musr_gen: 63.6 ± 3.0 (n=250)&#10;">71.3</td>
+  <td class="num" data-value="61.6" title="omni_math_gen: 61.6 ± 3.1 (n=250)&#10;">61.6</td>
+  <td class="num" data-value="45.89974937343358" title="ifbench: 32.7 ± 2.7 (n=300)&#10;ifeval: 86.0 ± 2.8 (n=150)&#10;">45.9</td>
+  <td class="num" data-value="70.5" title="livecodebench_gen: 70.5 ± 3.2 (n=200)&#10;">70.5</td>
+  <td class="num" data-value="76.03751803751804" title="mmlu_prox_de: 78.7 ± 2.4 (n=300)&#10;include_de_gen: 70.8 ± 3.7 (n=154)&#10;">76.0</td>
+  <td class="num" data-value="43.69461761825484">44</td>
+  <td class="num" data-value="23.80832467007433" title="overall 59.7 t/s with 3 parallel requests, from 9 of 9 tasks">24</td>
+  <td class="num" data-value="987.8475690816915">988</td>
+  <td class="num" data-value="4077.5521710747853">4078</td>
+  <td data-value="2026-09-23">2026-09-23</td>
+</tr>
 <tr data-reasoning="off">
   <td data-value="qwen3.8-27b-mtp">
     <a href="runs/20.html" class="strong">qwen3.8-27b-mtp</a>
@@ -240,12 +274,12 @@
 </table>
 </div>
 <div class="chart-set">
-<script type="application/json" class="chart-data" id="charts-v3-quick">{"categories": [{"key": "overall", "label": "Overall"}, {"key": "knowledge", "label": "Knowledge \u0026 reasoning"}, {"key": "math", "label": "Math"}, {"key": "instructions", "label": "Instruction following"}, {"key": "code", "label": "Code"}, {"key": "german", "label": "German"}], "missing_tps": false, "reasoning_mark": "\ud83d\udcad", "runs": [{"label": "gpt-oss-120b \u00b7 \ud83d\udcad", "run_id": 18, "scores": {"code": 83.0, "german": 77.4, "instructions": 66.1, "knowledge": 68.5, "math": 70.4, "overall": 73.1}, "tps": 19.6, "tps_source": "run"}, {"label": "qwen3.8-flash-next-ple4", "run_id": 15, "scores": {"code": 75.5, "german": 81.1, "instructions": 49.6, "knowledge": 77.9, "math": 73.2, "overall": 71.5}, "tps": 21.6, "tps_source": "run"}, {"label": "gemma-4-12b-it", "run_id": 21, "scores": {"code": 75.0, "german": 74.5, "instructions": 51.3, "knowledge": 67.5, "math": 60.8, "overall": 65.8}, "tps": 13.8, "tps_source": "run"}, {"label": "gemma-4-12b-it-heretic", "run_id": 22, "scores": {"code": 75.0, "german": 76.5, "instructions": 50.0, "knowledge": 68.4, "math": 59.2, "overall": 65.8}, "tps": 13.8, "tps_source": "run"}, {"label": "qwen3.8-27b-mtp", "run_id": 20, "scores": {"code": 65.0, "german": 76.3, "instructions": 49.5, "knowledge": 69.9, "math": 60.4, "overall": 64.2}, "tps": 22.4, "tps_source": "run"}, {"label": "occamy-1.0", "run_id": 27, "scores": {"code": 63.0, "german": 76.9, "instructions": 44.7, "knowledge": 73.1, "math": 62.4, "overall": 64.0}, "tps": 31.6, "tps_source": "run"}, {"label": "qwen3.8-27b-abliterated", "run_id": 23, "scores": {"code": 59.5, "german": 72.1, "instructions": 46.1, "knowledge": 71.5, "math": 58.0, "overall": 61.4}, "tps": 21.9, "tps_source": "run"}, {"label": "ternary-bonsai-2-27b", "run_id": 26, "scores": {"code": 56.5, "german": 74.5, "instructions": 46.3, "knowledge": 69.5, "math": 59.6, "overall": 61.3}, "tps": 19.3, "tps_source": "run"}, {"label": "gemma-4-12b-it-heretic", "run_id": 17, "scores": {"code": 62.0, "german": 67.7, "instructions": 46.8, "knowledge": 63.7, "math": 48.4, "overall": 57.7}, "tps": 21.1, "tps_source": "run"}, {"label": "nemotron-3.5-lightning-dspark", "run_id": 16, "scores": {"code": 53.0, "german": 70.5, "instructions": 46.0, "knowledge": 55.8, "math": 40.4, "overall": 53.1}, "tps": 70.4, "tps_source": "run"}, {"label": "qwen3.5-9b-heretic-v2-mtp", "run_id": 19, "scores": {"code": 46.5, "german": 67.0, "instructions": 44.1, "knowledge": 65.1, "math": 35.6, "overall": 51.7}, "tps": 35.2, "tps_source": "run"}, {"label": "zgcm-1-7b", "run_id": 29, "scores": {"code": 23.0, "german": 24.8, "instructions": 44.3, "knowledge": 34.7, "math": 40.0, "overall": 33.4}, "tps": 34.0, "tps_source": "run"}], "texts": {"overall": "Overall", "overall_title": "Overall score", "points": "points", "score_axis": "Score (0\u2013100)", "source_run": "measured during the run", "source_test": "from the speed test", "tps_axis": "Generation (tokens/s)", "vs": " vs. generation (tokens/s)"}}</script>
+<script type="application/json" class="chart-data" id="charts-v3-quick">{"categories": [{"key": "overall", "label": "Overall"}, {"key": "knowledge", "label": "Knowledge \u0026 reasoning"}, {"key": "math", "label": "Math"}, {"key": "instructions", "label": "Instruction following"}, {"key": "code", "label": "Code"}, {"key": "german", "label": "German"}], "missing_tps": false, "reasoning_mark": "\ud83d\udcad", "runs": [{"label": "gpt-oss-120b \u00b7 \ud83d\udcad", "run_id": 18, "scores": {"code": 83.0, "german": 77.4, "instructions": 66.1, "knowledge": 68.5, "math": 70.4, "overall": 73.1}, "tps": 19.6, "tps_source": "run"}, {"label": "qwen3.8-flash-next-abliterated (pool)", "run_id": 32, "scores": {"code": 77.0, "german": 81.4, "instructions": 55.2, "knowledge": 77.2, "math": 72.0, "overall": 72.5}, "tps": 37.2, "tps_source": "run"}, {"label": "qwen3.8-flash-next-ple4", "run_id": 15, "scores": {"code": 75.5, "german": 81.1, "instructions": 49.6, "knowledge": 77.9, "math": 73.2, "overall": 71.5}, "tps": 21.6, "tps_source": "run"}, {"label": "gemma-4-12b-it", "run_id": 21, "scores": {"code": 75.0, "german": 74.5, "instructions": 51.3, "knowledge": 67.5, "math": 60.8, "overall": 65.8}, "tps": 13.8, "tps_source": "run"}, {"label": "gemma-4-12b-it-heretic", "run_id": 22, "scores": {"code": 75.0, "german": 76.5, "instructions": 50.0, "knowledge": 68.4, "math": 59.2, "overall": 65.8}, "tps": 13.8, "tps_source": "run"}, {"label": "qwen3-coder-next", "run_id": 30, "scores": {"code": 70.5, "german": 76.0, "instructions": 45.9, "knowledge": 71.3, "math": 61.6, "overall": 65.1}, "tps": 23.8, "tps_source": "run"}, {"label": "qwen3.8-27b-mtp", "run_id": 20, "scores": {"code": 65.0, "german": 76.3, "instructions": 49.5, "knowledge": 69.9, "math": 60.4, "overall": 64.2}, "tps": 22.4, "tps_source": "run"}, {"label": "occamy-1.0", "run_id": 27, "scores": {"code": 63.0, "german": 76.9, "instructions": 44.7, "knowledge": 73.1, "math": 62.4, "overall": 64.0}, "tps": 31.6, "tps_source": "run"}, {"label": "qwen3.8-27b-abliterated", "run_id": 23, "scores": {"code": 59.5, "german": 72.1, "instructions": 46.1, "knowledge": 71.5, "math": 58.0, "overall": 61.4}, "tps": 21.9, "tps_source": "run"}, {"label": "ternary-bonsai-2-27b", "run_id": 26, "scores": {"code": 56.5, "german": 74.5, "instructions": 46.3, "knowledge": 69.5, "math": 59.6, "overall": 61.3}, "tps": 19.3, "tps_source": "run"}, {"label": "gemma-4-12b-it-heretic", "run_id": 17, "scores": {"code": 62.0, "german": 67.7, "instructions": 46.8, "knowledge": 63.7, "math": 48.4, "overall": 57.7}, "tps": 21.1, "tps_source": "run"}, {"label": "nemotron-3.5-lightning-dspark", "run_id": 16, "scores": {"code": 53.0, "german": 70.5, "instructions": 46.0, "knowledge": 55.8, "math": 40.4, "overall": 53.1}, "tps": 70.4, "tps_source": "run"}, {"label": "qwen3.5-9b-heretic-v2-mtp", "run_id": 19, "scores": {"code": 46.5, "german": 67.0, "instructions": 44.1, "knowledge": 65.1, "math": 35.6, "overall": 51.7}, "tps": 35.2, "tps_source": "run"}, {"label": "zgcm-1-7b", "run_id": 29, "scores": {"code": 23.0, "german": 24.8, "instructions": 44.3, "knowledge": 34.7, "math": 40.0, "overall": 33.4}, "tps": 34.0, "tps_source": "run"}], "texts": {"overall": "Overall", "overall_title": "Overall score", "points": "points", "score_axis": "Score (0\u2013100)", "source_run": "measured during the run", "source_test": "from the speed test", "tps_axis": "Generation (tokens/s)", "vs": " vs. generation (tokens/s)"}}</script>
 <p class="segmented" role="group" aria-label="Chart category"><button type="button" data-chart-category="overall" class="active" aria-pressed="true">Overall</button><button type="button" data-chart-category="knowledge" class="" aria-pressed="false">Knowledge &amp; reasoning</button><button type="button" data-chart-category="math" class="" aria-pressed="false">Math</button><button type="button" data-chart-category="instructions" class="" aria-pressed="false">Instruction following</button><button type="button" data-chart-category="code" class="" aria-pressed="false">Code</button><button type="button" data-chart-category="german" class="" aria-pressed="false">German</button></p>
 <div class="charts">
   <figure class="chart-card">
     <figcaption><span data-chart-title="bar">Overall score</span> <span class="sub">(💭 = with reasoning)</span></figcaption>
-    <div class="chart-box" data-chart-box="bar" style="height: 430px"><canvas data-chart="bar" role="img" aria-label="Score per model variant; the values are also in the table"></canvas></div>
+    <div class="chart-box" data-chart-box="bar" style="height: 490px"><canvas data-chart="bar" role="img" aria-label="Score per model variant; the values are also in the table"></canvas></div>
   </figure>
   <figure class="chart-card">
     <figcaption><span data-chart-title="scatter">Overall score vs. generation (tokens/s)</span> <span class="sub">(💭 = with reasoning)</span></figcaption>
@@ -256,7 +290,7 @@
 </div>
 </section>
 <p class="hint">Scores run from 0 to 100; the best value per category is shown in bold. Hovering a category cell lists its tasks with standard error (±) and number of items (n). Speed: generation in tokens/s from the speed test and measured during the run (gen t/s run, per request), prompt processing at 4k context in tokens/s, time to first token at 4k context in ms. Click a column header to sort.</p>
-<footer class="page-foot">As of 2026-09-23 · scores 0–100 · built with <code>bench publish</code></footer>
+<footer class="page-foot">As of 2026-09-27 · scores 0–100 · built with <code>bench publish</code></footer>
 </main>
 <script src="chart.umd.min.js"></script>
 <script src="app.js"></script>

methodology.html

@@ -117,7 +117,7 @@ on hardware and inference software.</p>
 </tbody>
 </table>
 </div>
-<footer class="page-foot">As of 2026-09-23 · scores 0–100 · built with <code>bench publish</code></footer>
+<footer class="page-foot">As of 2026-09-27 · scores 0–100 · built with <code>bench publish</code></footer>
 </main>
 <script src="chart.umd.min.js"></script>
 <script src="app.js"></script>

runs/15.html

@@ -188,7 +188,7 @@
 </table>
 </div>
 <p class="hint">Measured directly at the inference server.</p>
-<footer class="page-foot">As of 2026-09-23 · scores 0–100 · built with <code>bench publish</code></footer>
+<footer class="page-foot">As of 2026-09-27 · scores 0–100 · built with <code>bench publish</code></footer>
 </main>
 <script src="../chart.umd.min.js"></script>
 <script src="../app.js"></script>

runs/16.html

@@ -188,7 +188,7 @@
 </table>
 </div>
 <p class="hint">Measured directly at the inference server.</p>
-<footer class="page-foot">As of 2026-09-23 · scores 0–100 · built with <code>bench publish</code></footer>
+<footer class="page-foot">As of 2026-09-27 · scores 0–100 · built with <code>bench publish</code></footer>
 </main>
 <script src="../chart.umd.min.js"></script>
 <script src="../app.js"></script>

runs/17.html

@@ -188,7 +188,7 @@
 </table>
 </div>
 <p class="hint">Measured directly at the inference server.</p>
-<footer class="page-foot">As of 2026-09-23 · scores 0–100 · built with <code>bench publish</code></footer>
+<footer class="page-foot">As of 2026-09-27 · scores 0–100 · built with <code>bench publish</code></footer>
 </main>
 <script src="../chart.umd.min.js"></script>
 <script src="../app.js"></script>

runs/18.html

@@ -126,7 +126,7 @@
 </table>
 </div>
 <p class="hint">Measured directly at the inference server.</p>
-<footer class="page-foot">As of 2026-09-23 · scores 0–100 · built with <code>bench publish</code></footer>
+<footer class="page-foot">As of 2026-09-27 · scores 0–100 · built with <code>bench publish</code></footer>
 </main>
 <script src="../chart.umd.min.js"></script>
 <script src="../app.js"></script>

runs/19.html

@@ -188,7 +188,7 @@
 </table>
 </div>
 <p class="hint">Measured directly at the inference server.</p>
-<footer class="page-foot">As of 2026-09-23 · scores 0–100 · built with <code>bench publish</code></footer>
+<footer class="page-foot">As of 2026-09-27 · scores 0–100 · built with <code>bench publish</code></footer>
 </main>
 <script src="../chart.umd.min.js"></script>
 <script src="../app.js"></script>

runs/20.html

@@ -188,7 +188,7 @@
 </table>
 </div>
 <p class="hint">Measured directly at the inference server.</p>
-<footer class="page-foot">As of 2026-09-23 · scores 0–100 · built with <code>bench publish</code></footer>
+<footer class="page-foot">As of 2026-09-27 · scores 0–100 · built with <code>bench publish</code></footer>
 </main>
 <script src="../chart.umd.min.js"></script>
 <script src="../app.js"></script>

runs/21.html

@@ -188,7 +188,7 @@
 </table>
 </div>
 <p class="hint">Measured directly at the inference server.</p>
-<footer class="page-foot">As of 2026-09-23 · scores 0–100 · built with <code>bench publish</code></footer>
+<footer class="page-foot">As of 2026-09-27 · scores 0–100 · built with <code>bench publish</code></footer>
 </main>
 <script src="../chart.umd.min.js"></script>
 <script src="../app.js"></script>

runs/22.html

@@ -188,7 +188,7 @@
 </table>
 </div>
 <p class="hint">Measured directly at the inference server.</p>
-<footer class="page-foot">As of 2026-09-23 · scores 0–100 · built with <code>bench publish</code></footer>
+<footer class="page-foot">As of 2026-09-27 · scores 0–100 · built with <code>bench publish</code></footer>
 </main>
 <script src="../chart.umd.min.js"></script>
 <script src="../app.js"></script>

runs/23.html

@@ -188,7 +188,7 @@
 </table>
 </div>
 <p class="hint">Measured directly at the inference server.</p>
-<footer class="page-foot">As of 2026-09-23 · scores 0–100 · built with <code>bench publish</code></footer>
+<footer class="page-foot">As of 2026-09-27 · scores 0–100 · built with <code>bench publish</code></footer>
 </main>
 <script src="../chart.umd.min.js"></script>
 <script src="../app.js"></script>

runs/26.html

@@ -188,7 +188,7 @@
 </table>
 </div>
 <p class="hint">Measured directly at the inference server.</p>
-<footer class="page-foot">As of 2026-09-23 · scores 0–100 · built with <code>bench publish</code></footer>
+<footer class="page-foot">As of 2026-09-27 · scores 0–100 · built with <code>bench publish</code></footer>
 </main>
 <script src="../chart.umd.min.js"></script>
 <script src="../app.js"></script>

runs/27.html

@@ -188,7 +188,7 @@
 </table>
 </div>
 <p class="hint">Measured directly at the inference server.</p>
-<footer class="page-foot">As of 2026-09-23 · scores 0–100 · built with <code>bench publish</code></footer>
+<footer class="page-foot">As of 2026-09-27 · scores 0–100 · built with <code>bench publish</code></footer>
 </main>
 <script src="../chart.umd.min.js"></script>
 <script src="../app.js"></script>

runs/29.html

@@ -188,7 +188,7 @@
 </table>
 </div>
 <p class="hint">Measured directly at the inference server.</p>
-<footer class="page-foot">As of 2026-09-23 · scores 0–100 · built with <code>bench publish</code></footer>
+<footer class="page-foot">As of 2026-09-27 · scores 0–100 · built with <code>bench publish</code></footer>
 </main>
 <script src="../chart.umd.min.js"></script>
 <script src="../app.js"></script>

runs/30.html

@@ -0,0 +1,196 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="utf-8">
+<meta name="viewport" content="width=device-width, initial-scale=1">
+<title>qwen3-coder-next – Local LLM Benchmarks</title>
+<link rel="stylesheet" href="../style.css">
+</head>
+<body>
+<header class="top">
+  <a class="brand" href="../index.html">Local LLM Benchmarks</a>
+  <nav>
+    <a href="../index.html">Overview</a>
+    <a href="../methodology.html">Methodology</a>
+  </nav>
+</header>
+<main>
+<p class="sub"><a href="../index.html#v3-quick">← Overview</a></p>
+<h1>qwen3-coder-next</h1>
+<dl class="meta">
+  <dt>Quantization</dt><dd>Q6</dd>
+  <dt>Reasoning</dt><dd>off</dd>
+  <dt>Profile</dt><dd>quick</dd>
+  <dt>Suite</dt><dd>v2b</dd>
+  <dt>Date</dt><dd>2026-09-23 – 2026-09-24</dd>
+  <dt>Hardware</dt><dd>NVIDIA DGX Spark, 128 GB RAM</dd>
+  <dt>Inference software</dt><dd>vLLM 0.26.0</dd>
+  <dt>Measured</dt><dd>directly at the inference server</dd>
+  <dt>Overall</dt><dd class="strong">65.1</dd>
+</dl>
+
+<h2>Categories</h2>
+<div class="table-wrap">
+<table>
+<thead><tr><th>Category</th><th class="num">Score</th></tr></thead>
+<tbody>
+<tr><td>Knowledge &amp; reasoning</td><td class="num">71.3</td></tr>
+<tr><td>Math</td><td class="num">61.6</td></tr>
+<tr><td>Instruction following</td><td class="num">45.9</td></tr>
+<tr><td>Code</td><td class="num">70.5</td></tr>
+<tr><td>German</td><td class="num">76.0</td></tr>
+</tbody>
+</table>
+</div>
+
+<h2>Tasks</h2>
+<div class="table-wrap">
+<table>
+<thead><tr><th>Category</th><th>Task</th><th class="num">Score</th><th class="num">±</th><th class="num">n</th></tr></thead>
+<tbody>
+<tr>
+  <td>Knowledge &amp; reasoning</td>
+  <td>mmlu_pro</td>
+  <td class="num">82.0</td>
+  <td class="num">± 2.2</td>
+  <td class="num">300</td>
+</tr>
+<tr>
+  <td>Knowledge &amp; reasoning</td>
+  <td>gpqa_diamond_gen</td>
+  <td class="num">68.2</td>
+  <td class="num">± 3.3</td>
+  <td class="num">198</td>
+</tr>
+<tr>
+  <td>Knowledge &amp; reasoning</td>
+  <td>musr_gen</td>
+  <td class="num">63.6</td>
+  <td class="num">± 3.0</td>
+  <td class="num">250</td>
+</tr>
+<tr>
+  <td>Math</td>
+  <td>omni_math_gen</td>
+  <td class="num">61.6</td>
+  <td class="num">± 3.1</td>
+  <td class="num">250</td>
+</tr>
+<tr>
+  <td>Instruction following</td>
+  <td>ifbench</td>
+  <td class="num">32.7</td>
+  <td class="num">± 2.7</td>
+  <td class="num">300</td>
+</tr>
+<tr>
+  <td>Instruction following</td>
+  <td>ifeval</td>
+  <td class="num">86.0</td>
+  <td class="num">± 2.8</td>
+  <td class="num">150</td>
+</tr>
+<tr>
+  <td>Code</td>
+  <td>livecodebench_gen</td>
+  <td class="num">70.5</td>
+  <td class="num">± 3.2</td>
+  <td class="num">200</td>
+</tr>
+<tr>
+  <td>German</td>
+  <td>mmlu_prox_de</td>
+  <td class="num">78.7</td>
+  <td class="num">± 2.4</td>
+  <td class="num">300</td>
+</tr>
+<tr>
+  <td>German</td>
+  <td>include_de_gen</td>
+  <td class="num">70.8</td>
+  <td class="num">± 3.7</td>
+  <td class="num">154</td>
+</tr>
+</tbody>
+</table>
+</div>
+<p class="hint">± is the standard error; the 95% interval spans roughly 1.96 standard errors around the score.</p>
+
+<h2>Speed</h2>
+<div class="table-wrap">
+<table>
+<thead><tr><th>Measure</th><th class="num">Context (target)</th><th class="num">Context (actual)</th><th class="num">Median</th><th class="num">p10</th><th class="num">p90</th><th class="num">n</th></tr></thead>
+<tbody>
+<tr>
+  <td>Generation [t/s]</td>
+  <td class="num">–</td>
+  <td class="num">–</td>
+  <td class="num">43.7</td>
+  <td class="num">43.5</td>
+  <td class="num">43.8</td>
+  <td class="num">5</td>
+</tr>
+<tr>
+  <td>Prompt processing [t/s]</td>
+  <td class="num">512</td>
+  <td class="num">525</td>
+  <td class="num">744.0</td>
+  <td class="num">716.4</td>
+  <td class="num">768.1</td>
+  <td class="num">5</td>
+</tr>
+<tr>
+  <td>Prompt processing [t/s]</td>
+  <td class="num">4096</td>
+  <td class="num">4028</td>
+  <td class="num">987.8</td>
+  <td class="num">986.6</td>
+  <td class="num">998.2</td>
+  <td class="num">5</td>
+</tr>
+<tr>
+  <td>Prompt processing [t/s]</td>
+  <td class="num">16384</td>
+  <td class="num">16045</td>
+  <td class="num">1030.1</td>
+  <td class="num">1028.9</td>
+  <td class="num">1033.0</td>
+  <td class="num">5</td>
+</tr>
+<tr>
+  <td>Time to first token [ms]</td>
+  <td class="num">512</td>
+  <td class="num">525</td>
+  <td class="num">705.6</td>
+  <td class="num">683.5</td>
+  <td class="num">732.0</td>
+  <td class="num">5</td>
+</tr>
+<tr>
+  <td>Time to first token [ms]</td>
+  <td class="num">4096</td>
+  <td class="num">4028</td>
+  <td class="num">4077.6</td>
+  <td class="num">4035.2</td>
+  <td class="num">4082.8</td>
+  <td class="num">5</td>
+</tr>
+<tr>
+  <td>Time to first token [ms]</td>
+  <td class="num">16384</td>
+  <td class="num">16045</td>
+  <td class="num">15576.0</td>
+  <td class="num">15532.7</td>
+  <td class="num">15593.8</td>
+  <td class="num">5</td>
+</tr>
+</tbody>
+</table>
+</div>
+<p class="hint">Measured directly at the inference server.</p>
+<footer class="page-foot">As of 2026-09-27 · scores 0–100 · built with <code>bench publish</code></footer>
+</main>
+<script src="../chart.umd.min.js"></script>
+<script src="../app.js"></script>
+</body>
+</html>

runs/32.html

@@ -0,0 +1,196 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="utf-8">
+<meta name="viewport" content="width=device-width, initial-scale=1">
+<title>qwen3.8-flash-next-abliterated (pool) – Local LLM Benchmarks</title>
+<link rel="stylesheet" href="../style.css">
+</head>
+<body>
+<header class="top">
+  <a class="brand" href="../index.html">Local LLM Benchmarks</a>
+  <nav>
+    <a href="../index.html">Overview</a>
+    <a href="../methodology.html">Methodology</a>
+  </nav>
+</header>
+<main>
+<p class="sub"><a href="../index.html#v3-quick">← Overview</a></p>
+<h1>qwen3.8-flash-next-abliterated (pool)</h1>
+<dl class="meta">
+  <dt>Quantization</dt><dd>–</dd>
+  <dt>Reasoning</dt><dd>off</dd>
+  <dt>Profile</dt><dd>quick</dd>
+  <dt>Suite</dt><dd>v2b</dd>
+  <dt>Date</dt><dd>2026-09-27</dd>
+  <dt>Hardware</dt><dd>2× NVIDIA DGX Spark, je 128 GB RAM</dd>
+  <dt>Inference software</dt><dd>vLLM 0.26.0</dd>
+  <dt>Measured</dt><dd>directly at the inference server</dd>
+  <dt>Overall</dt><dd class="strong">72.5</dd>
+</dl>
+
+<h2>Categories</h2>
+<div class="table-wrap">
+<table>
+<thead><tr><th>Category</th><th class="num">Score</th></tr></thead>
+<tbody>
+<tr><td>Knowledge &amp; reasoning</td><td class="num">77.2</td></tr>
+<tr><td>Math</td><td class="num">72.0</td></tr>
+<tr><td>Instruction following</td><td class="num">55.2</td></tr>
+<tr><td>Code</td><td class="num">77.0</td></tr>
+<tr><td>German</td><td class="num">81.4</td></tr>
+</tbody>
+</table>
+</div>
+
+<h2>Tasks</h2>
+<div class="table-wrap">
+<table>
+<thead><tr><th>Category</th><th>Task</th><th class="num">Score</th><th class="num">±</th><th class="num">n</th></tr></thead>
+<tbody>
+<tr>
+  <td>Knowledge &amp; reasoning</td>
+  <td>mmlu_pro</td>
+  <td class="num">87.0</td>
+  <td class="num">± 1.9</td>
+  <td class="num">300</td>
+</tr>
+<tr>
+  <td>Knowledge &amp; reasoning</td>
+  <td>gpqa_diamond_gen</td>
+  <td class="num">75.3</td>
+  <td class="num">± 3.1</td>
+  <td class="num">198</td>
+</tr>
+<tr>
+  <td>Knowledge &amp; reasoning</td>
+  <td>musr_gen</td>
+  <td class="num">69.2</td>
+  <td class="num">± 2.9</td>
+  <td class="num">250</td>
+</tr>
+<tr>
+  <td>Math</td>
+  <td>omni_math_gen</td>
+  <td class="num">72.0</td>
+  <td class="num">± 2.8</td>
+  <td class="num">250</td>
+</tr>
+<tr>
+  <td>Instruction following</td>
+  <td>ifbench</td>
+  <td class="num">43.7</td>
+  <td class="num">± 2.9</td>
+  <td class="num">300</td>
+</tr>
+<tr>
+  <td>Instruction following</td>
+  <td>ifeval</td>
+  <td class="num">90.0</td>
+  <td class="num">± 2.5</td>
+  <td class="num">150</td>
+</tr>
+<tr>
+  <td>Code</td>
+  <td>livecodebench_gen</td>
+  <td class="num">77.0</td>
+  <td class="num">± 3.0</td>
+  <td class="num">200</td>
+</tr>
+<tr>
+  <td>German</td>
+  <td>mmlu_prox_de</td>
+  <td class="num">86.7</td>
+  <td class="num">± 2.0</td>
+  <td class="num">300</td>
+</tr>
+<tr>
+  <td>German</td>
+  <td>include_de_gen</td>
+  <td class="num">70.8</td>
+  <td class="num">± 3.7</td>
+  <td class="num">154</td>
+</tr>
+</tbody>
+</table>
+</div>
+<p class="hint">± is the standard error; the 95% interval spans roughly 1.96 standard errors around the score.</p>
+
+<h2>Speed</h2>
+<div class="table-wrap">
+<table>
+<thead><tr><th>Measure</th><th class="num">Context (target)</th><th class="num">Context (actual)</th><th class="num">Median</th><th class="num">p10</th><th class="num">p90</th><th class="num">n</th></tr></thead>
+<tbody>
+<tr>
+  <td>Generation [t/s]</td>
+  <td class="num">–</td>
+  <td class="num">–</td>
+  <td class="num">41.2</td>
+  <td class="num">38.2</td>
+  <td class="num">41.6</td>
+  <td class="num">5</td>
+</tr>
+<tr>
+  <td>Prompt processing [t/s]</td>
+  <td class="num">512</td>
+  <td class="num">529</td>
+  <td class="num">1429.4</td>
+  <td class="num">878.3</td>
+  <td class="num">1446.7</td>
+  <td class="num">5</td>
+</tr>
+<tr>
+  <td>Prompt processing [t/s]</td>
+  <td class="num">4096</td>
+  <td class="num">4024</td>
+  <td class="num">2569.1</td>
+  <td class="num">2017.1</td>
+  <td class="num">2570.7</td>
+  <td class="num">5</td>
+</tr>
+<tr>
+  <td>Prompt processing [t/s]</td>
+  <td class="num">16384</td>
+  <td class="num">16001</td>
+  <td class="num">2721.6</td>
+  <td class="num">2264.6</td>
+  <td class="num">2727.5</td>
+  <td class="num">5</td>
+</tr>
+<tr>
+  <td>Time to first token [ms]</td>
+  <td class="num">512</td>
+  <td class="num">529</td>
+  <td class="num">370.1</td>
+  <td class="num">365.7</td>
+  <td class="num">764.0</td>
+  <td class="num">5</td>
+</tr>
+<tr>
+  <td>Time to first token [ms]</td>
+  <td class="num">4096</td>
+  <td class="num">4024</td>
+  <td class="num">1566.3</td>
+  <td class="num">1565.3</td>
+  <td class="num">2090.1</td>
+  <td class="num">5</td>
+</tr>
+<tr>
+  <td>Time to first token [ms]</td>
+  <td class="num">16384</td>
+  <td class="num">16001</td>
+  <td class="num">5879.2</td>
+  <td class="num">5866.5</td>
+  <td class="num">7247.8</td>
+  <td class="num">5</td>
+</tr>
+</tbody>
+</table>
+</div>
+<p class="hint">Measured directly at the inference server.</p>
+<footer class="page-foot">As of 2026-09-27 · scores 0–100 · built with <code>bench publish</code></footer>
+</main>
+<script src="../chart.umd.min.js"></script>
+<script src="../app.js"></script>
+</body>
+</html>