From cad3ab2d19196843619f0be7962809890697e362 Mon Sep 17 00:00:00 2001 From: Lliar-liar <1169523200@qq.com> Date: Sun, 24 May 2026 17:10:35 +0000 Subject: [PATCH] Simplify main results webpage table --- index.html | 277 +++++++++----------------------------------------- skillopt.html | 277 +++++++++----------------------------------------- 2 files changed, 96 insertions(+), 458 deletions(-) diff --git a/index.html b/index.html index 336aae1..44c9949 100644 --- a/index.html +++ b/index.html @@ -306,8 +306,7 @@ } .statement h3, - .panel h3, - .result-card h3 { + .panel h3 { margin: 0 0 12px; font-family: var(--display); font-size: 1.45rem; @@ -471,144 +470,6 @@ line-height: 1.55; } - .results-grid { - display: grid; - grid-template-columns: repeat(3, minmax(0, 1fr)); - gap: 12px; - } - - .result-card { - min-height: 202px; - padding: 22px; - background: var(--panel); - border: 1px solid var(--line); - border-radius: 8px; - } - - .result-card.featured { - color: #f8faf7; - background: var(--teal); - border-color: var(--teal); - } - - .metric { - display: block; - margin: 10px 0 6px; - font-family: var(--display); - font-size: 3rem; - font-weight: 800; - line-height: 1; - } - - .result-card p { - margin: 0; - color: var(--muted); - font-size: 0.96rem; - } - - .result-card.featured p { - color: rgba(248, 250, 247, 0.84); - } - - .model-gallery { - display: grid; - grid-template-columns: repeat(7, minmax(172px, 1fr)); - gap: 10px; - margin-top: 16px; - overflow-x: auto; - padding-bottom: 4px; - } - - .model-card { - min-width: 172px; - padding: 15px; - background: var(--panel); - border: 1px solid var(--line); - border-radius: 8px; - box-shadow: 0 10px 22px rgba(18, 24, 31, 0.08); - } - - .model-card.highlight { - color: #f8faf7; - background: var(--black); - border-color: var(--black); - } - - .model-card strong { - display: block; - min-height: 38px; - font-family: var(--mono); - font-size: 0.78rem; - line-height: 1.25; - } - - .score-pair { - display: flex; - justify-content: space-between; - gap: 10px; - margin: 12px 0; - color: var(--quiet); - font-family: var(--mono); - font-size: 0.68rem; - text-transform: uppercase; - } - - .score-pair b { - display: block; - margin-top: 3px; - color: var(--ink); - font-size: 0.95rem; - } - - .model-card.highlight .score-pair { - color: rgba(248, 250, 247, 0.58); - } - - .model-card.highlight .score-pair b { - color: #f8faf7; - } - - .gain-meter { - height: 9px; - background: rgba(21, 25, 31, 0.12); - border-radius: 999px; - overflow: hidden; - } - - .model-card.highlight .gain-meter { - background: rgba(248, 250, 247, 0.16); - } - - .gain-meter i { - display: block; - height: 100%; - width: var(--w); - background: linear-gradient(90deg, var(--gold), var(--green)); - border-radius: inherit; - } - - .gain-label { - display: block; - margin-top: 8px; - color: var(--green); - font-family: var(--display); - font-size: 1.55rem; - font-weight: 800; - line-height: 1; - } - - .model-card.highlight .gain-label { - color: #f4c542; - } - - .result-note { - margin: 10px 0 0; - color: var(--muted); - font-family: var(--mono); - font-size: 0.72rem; - line-height: 1.55; - } - .table-wrap { overflow-x: auto; background: var(--panel); @@ -620,7 +481,7 @@ table { width: 100%; border-collapse: collapse; - min-width: 820px; + min-width: 1040px; font-family: var(--mono); font-size: 0.78rem; line-height: 1.35; @@ -652,6 +513,10 @@ background: rgba(235, 238, 240, 0.62); } + .harness-group td { + border-top: 2px solid var(--line-strong); + } + .num { text-align: right; white-space: nowrap; @@ -1126,9 +991,7 @@ font-size: 4.1rem; } - .results-grid, .method-grid, - .model-gallery, .transfer-grid, .evolution-footnotes { grid-template-columns: repeat(2, minmax(0, 1fr)); @@ -1166,9 +1029,7 @@ font-size: 2rem; } - .results-grid, .method-grid, - .model-gallery, .transfer-grid, .evolution-footnotes, .steps { @@ -1392,86 +1253,19 @@

SkillOpt improves GPT and Qwen students.

- Direct-chat results are reported for seven target models, not only - GPT-5.5. The cross-model view below averages the six benchmark scores - in the main paper table, comparing no-skill execution with the final - SkillOpt skill for each student. + The table reports main-result gains across target models and + execution harnesses, comparing no-skill execution with the final + SkillOpt skill on held-out test splits.

-
-
-

Covered students

- 7 -

GPT-5.5, GPT-5.4 family, GPT-5.2, and two Qwen targets in direct chat.

-
-
-

Largest average lift

- +24.9 -

GPT-5.4-nano gains the most on average, showing strong benefit for weaker students.

-
-
-

Largest single lift

- +50.7 -

Qwen3.5-4B on ALFWorld, where the optimized skill turns procedural memory into a large gain.

-
-
- -
-
- GPT-5.5 -
No skill58.8SkillOpt82.3
-
- +23.5 -
-
- GPT-5.4 -
No skill59.7SkillOpt72.4
-
- +12.8 -
-
- GPT-5.4-mini -
No skill51.1SkillOpt63.8
-
- +12.7 -
-
- GPT-5.4-nano -
No skill32.4SkillOpt57.4
-
- +24.9 -
-
- GPT-5.2 -
No skill51.3SkillOpt67.9
-
- +16.6 -
-
- Qwen3.5-4B -
No skill38.6SkillOpt57.9
-
- +19.2 -
-
- Qwen3.6-35B-A3B -
No skill55.9SkillOpt65.0
-
- +9.1 -
-
- -

- Values are six-benchmark direct-chat averages computed from the main result matrix. Bars are scaled by average gain over no skill. -

- -
- +
+
+ @@ -1484,6 +1278,7 @@ + @@ -1494,6 +1289,7 @@ + @@ -1504,6 +1300,7 @@ + @@ -1514,6 +1311,7 @@ + @@ -1524,6 +1322,7 @@ + @@ -1534,6 +1333,7 @@ + @@ -1544,6 +1344,7 @@ + @@ -1552,6 +1353,28 @@ + + + + + + + + + + + + + + + + + + + + + +
Student modelHarness SearchQA Sheet Office
GPT-5.5Direct chat +9.6 +38.9 +39.0
GPT-5.4Direct chat +6.2 +21.1 +12.8
GPT-5.4-miniDirect chat +4.3 +11.4 +26.7
GPT-5.4-nanoDirect chat +19.0 +8.2 +33.7
GPT-5.2Direct chat +11.2 +18.9 +21.5
Qwen3.5-4BDirect chat +3.1 +14.6 +15.2
Qwen3.6-35B-A3BDirect chat +7.6 +9.3 +1.2+22.4 +9.1
GPT-5.5Codex+5.5+57.5+12.8+5.0+28.0N/A+21.8
GPT-5.5Claude Code+4.0+58.3+13.9+3.5+13.3N/A+18.6
@@ -1561,6 +1384,7 @@ Benchmark + Harness No skill Best non-SkillOpt baseline SkillOpt @@ -1571,6 +1395,7 @@ SearchQA + Direct chat 77.7 84.8 87.3 @@ -1579,6 +1404,7 @@ SpreadsheetBench + Direct chat 41.8 73.6 80.7 @@ -1587,6 +1413,7 @@ OfficeQA + Direct chat 33.1 66.9 72.1 @@ -1595,6 +1422,7 @@ DocVQA + Direct chat 78.8 90.6 91.2 @@ -1603,6 +1431,7 @@ LiveMathBench + Direct chat 37.6 52.0 66.9 @@ -1611,6 +1440,7 @@ ALFWorld + Direct chat 83.6 93.3 95.5 @@ -1620,17 +1450,6 @@ - -
-
-

Codex harness

-

With GPT-5.5 in a Codex-style execution harness, SkillOpt reaches 85.0 on SpreadsheetBench and 78.4 on LiveMathBench, outperforming no skill by +57.5 and +28.0 points respectively.

-
-
-

Claude Code harness

-

In the Claude Code-style harness, SkillOpt reaches 80.4 on SpreadsheetBench and 71.5 on OfficeQA, remaining stronger than EvoSkill in the reported harness block.

-
-
diff --git a/skillopt.html b/skillopt.html index 336aae1..44c9949 100644 --- a/skillopt.html +++ b/skillopt.html @@ -306,8 +306,7 @@ } .statement h3, - .panel h3, - .result-card h3 { + .panel h3 { margin: 0 0 12px; font-family: var(--display); font-size: 1.45rem; @@ -471,144 +470,6 @@ line-height: 1.55; } - .results-grid { - display: grid; - grid-template-columns: repeat(3, minmax(0, 1fr)); - gap: 12px; - } - - .result-card { - min-height: 202px; - padding: 22px; - background: var(--panel); - border: 1px solid var(--line); - border-radius: 8px; - } - - .result-card.featured { - color: #f8faf7; - background: var(--teal); - border-color: var(--teal); - } - - .metric { - display: block; - margin: 10px 0 6px; - font-family: var(--display); - font-size: 3rem; - font-weight: 800; - line-height: 1; - } - - .result-card p { - margin: 0; - color: var(--muted); - font-size: 0.96rem; - } - - .result-card.featured p { - color: rgba(248, 250, 247, 0.84); - } - - .model-gallery { - display: grid; - grid-template-columns: repeat(7, minmax(172px, 1fr)); - gap: 10px; - margin-top: 16px; - overflow-x: auto; - padding-bottom: 4px; - } - - .model-card { - min-width: 172px; - padding: 15px; - background: var(--panel); - border: 1px solid var(--line); - border-radius: 8px; - box-shadow: 0 10px 22px rgba(18, 24, 31, 0.08); - } - - .model-card.highlight { - color: #f8faf7; - background: var(--black); - border-color: var(--black); - } - - .model-card strong { - display: block; - min-height: 38px; - font-family: var(--mono); - font-size: 0.78rem; - line-height: 1.25; - } - - .score-pair { - display: flex; - justify-content: space-between; - gap: 10px; - margin: 12px 0; - color: var(--quiet); - font-family: var(--mono); - font-size: 0.68rem; - text-transform: uppercase; - } - - .score-pair b { - display: block; - margin-top: 3px; - color: var(--ink); - font-size: 0.95rem; - } - - .model-card.highlight .score-pair { - color: rgba(248, 250, 247, 0.58); - } - - .model-card.highlight .score-pair b { - color: #f8faf7; - } - - .gain-meter { - height: 9px; - background: rgba(21, 25, 31, 0.12); - border-radius: 999px; - overflow: hidden; - } - - .model-card.highlight .gain-meter { - background: rgba(248, 250, 247, 0.16); - } - - .gain-meter i { - display: block; - height: 100%; - width: var(--w); - background: linear-gradient(90deg, var(--gold), var(--green)); - border-radius: inherit; - } - - .gain-label { - display: block; - margin-top: 8px; - color: var(--green); - font-family: var(--display); - font-size: 1.55rem; - font-weight: 800; - line-height: 1; - } - - .model-card.highlight .gain-label { - color: #f4c542; - } - - .result-note { - margin: 10px 0 0; - color: var(--muted); - font-family: var(--mono); - font-size: 0.72rem; - line-height: 1.55; - } - .table-wrap { overflow-x: auto; background: var(--panel); @@ -620,7 +481,7 @@ table { width: 100%; border-collapse: collapse; - min-width: 820px; + min-width: 1040px; font-family: var(--mono); font-size: 0.78rem; line-height: 1.35; @@ -652,6 +513,10 @@ background: rgba(235, 238, 240, 0.62); } + .harness-group td { + border-top: 2px solid var(--line-strong); + } + .num { text-align: right; white-space: nowrap; @@ -1126,9 +991,7 @@ font-size: 4.1rem; } - .results-grid, .method-grid, - .model-gallery, .transfer-grid, .evolution-footnotes { grid-template-columns: repeat(2, minmax(0, 1fr)); @@ -1166,9 +1029,7 @@ font-size: 2rem; } - .results-grid, .method-grid, - .model-gallery, .transfer-grid, .evolution-footnotes, .steps { @@ -1392,86 +1253,19 @@

SkillOpt improves GPT and Qwen students.

- Direct-chat results are reported for seven target models, not only - GPT-5.5. The cross-model view below averages the six benchmark scores - in the main paper table, comparing no-skill execution with the final - SkillOpt skill for each student. + The table reports main-result gains across target models and + execution harnesses, comparing no-skill execution with the final + SkillOpt skill on held-out test splits.

-
-
-

Covered students

- 7 -

GPT-5.5, GPT-5.4 family, GPT-5.2, and two Qwen targets in direct chat.

-
-
-

Largest average lift

- +24.9 -

GPT-5.4-nano gains the most on average, showing strong benefit for weaker students.

-
-
-

Largest single lift

- +50.7 -

Qwen3.5-4B on ALFWorld, where the optimized skill turns procedural memory into a large gain.

-
-
- -
-
- GPT-5.5 -
No skill58.8SkillOpt82.3
-
- +23.5 -
-
- GPT-5.4 -
No skill59.7SkillOpt72.4
-
- +12.8 -
-
- GPT-5.4-mini -
No skill51.1SkillOpt63.8
-
- +12.7 -
-
- GPT-5.4-nano -
No skill32.4SkillOpt57.4
-
- +24.9 -
-
- GPT-5.2 -
No skill51.3SkillOpt67.9
-
- +16.6 -
-
- Qwen3.5-4B -
No skill38.6SkillOpt57.9
-
- +19.2 -
-
- Qwen3.6-35B-A3B -
No skill55.9SkillOpt65.0
-
- +9.1 -
-
- -

- Values are six-benchmark direct-chat averages computed from the main result matrix. Bars are scaled by average gain over no skill. -

- -
- +
+
+ @@ -1484,6 +1278,7 @@ + @@ -1494,6 +1289,7 @@ + @@ -1504,6 +1300,7 @@ + @@ -1514,6 +1311,7 @@ + @@ -1524,6 +1322,7 @@ + @@ -1534,6 +1333,7 @@ + @@ -1544,6 +1344,7 @@ + @@ -1552,6 +1353,28 @@ + + + + + + + + + + + + + + + + + + + + + +
Student modelHarness SearchQA Sheet Office
GPT-5.5Direct chat +9.6 +38.9 +39.0
GPT-5.4Direct chat +6.2 +21.1 +12.8
GPT-5.4-miniDirect chat +4.3 +11.4 +26.7
GPT-5.4-nanoDirect chat +19.0 +8.2 +33.7
GPT-5.2Direct chat +11.2 +18.9 +21.5
Qwen3.5-4BDirect chat +3.1 +14.6 +15.2
Qwen3.6-35B-A3BDirect chat +7.6 +9.3 +1.2+22.4 +9.1
GPT-5.5Codex+5.5+57.5+12.8+5.0+28.0N/A+21.8
GPT-5.5Claude Code+4.0+58.3+13.9+3.5+13.3N/A+18.6
@@ -1561,6 +1384,7 @@ Benchmark + Harness No skill Best non-SkillOpt baseline SkillOpt @@ -1571,6 +1395,7 @@ SearchQA + Direct chat 77.7 84.8 87.3 @@ -1579,6 +1404,7 @@ SpreadsheetBench + Direct chat 41.8 73.6 80.7 @@ -1587,6 +1413,7 @@ OfficeQA + Direct chat 33.1 66.9 72.1 @@ -1595,6 +1422,7 @@ DocVQA + Direct chat 78.8 90.6 91.2 @@ -1603,6 +1431,7 @@ LiveMathBench + Direct chat 37.6 52.0 66.9 @@ -1611,6 +1440,7 @@ ALFWorld + Direct chat 83.6 93.3 95.5 @@ -1620,17 +1450,6 @@ - -
-
-

Codex harness

-

With GPT-5.5 in a Codex-style execution harness, SkillOpt reaches 85.0 on SpreadsheetBench and 78.4 on LiveMathBench, outperforming no skill by +57.5 and +28.0 points respectively.

-
-
-

Claude Code harness

-

In the Claude Code-style harness, SkillOpt reaches 80.4 on SpreadsheetBench and 71.5 on OfficeQA, remaining stronger than EvoSkill in the reported harness block.

-
-