This commit is contained in:
Paul Gauthier 2023-11-07 10:21:36 -08:00
parent 5da64a6abc
commit ca3ef646ce
2 changed files with 56 additions and 56 deletions

View file

@ -6,7 +6,7 @@
<rdf:RDF xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:cc="http://creativecommons.org/ns#" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
<cc:Work>
<dc:type rdf:resource="http://purl.org/dc/dcmitype/StillImage"/>
<dc:date>2023-11-07T07:21:57.718957</dc:date>
<dc:date>2023-11-07T10:21:00.074181</dc:date>
<dc:format>image/svg+xml</dc:format>
<dc:creator>
<cc:Agent>
@ -41,12 +41,12 @@ z
<g id="xtick_1">
<g id="line2d_1">
<defs>
<path id="m4e3c01096c" d="M 0 0
<path id="m58592fa816" d="M 0 0
L 0 3.5
" style="stroke: #000000; stroke-width: 0.8"/>
</defs>
<g>
<use xlink:href="#m4e3c01096c" x="63.35774" y="239.24" style="stroke: #000000; stroke-width: 0.8"/>
<use xlink:href="#m58592fa816" x="63.35774" y="239.24" style="stroke: #000000; stroke-width: 0.8"/>
</g>
</g>
<g id="text_1">
@ -363,7 +363,7 @@ z
<g id="xtick_2">
<g id="line2d_2">
<g>
<use xlink:href="#m4e3c01096c" x="128.411046" y="239.24" style="stroke: #000000; stroke-width: 0.8"/>
<use xlink:href="#m58592fa816" x="128.411046" y="239.24" style="stroke: #000000; stroke-width: 0.8"/>
</g>
</g>
<g id="text_2">
@ -428,7 +428,7 @@ z
<g id="xtick_3">
<g id="line2d_3">
<g>
<use xlink:href="#m4e3c01096c" x="193.464352" y="239.24" style="stroke: #000000; stroke-width: 0.8"/>
<use xlink:href="#m58592fa816" x="193.464352" y="239.24" style="stroke: #000000; stroke-width: 0.8"/>
</g>
</g>
<g id="text_3">
@ -461,7 +461,7 @@ z
<g id="xtick_4">
<g id="line2d_4">
<g>
<use xlink:href="#m4e3c01096c" x="258.517658" y="239.24" style="stroke: #000000; stroke-width: 0.8"/>
<use xlink:href="#m58592fa816" x="258.517658" y="239.24" style="stroke: #000000; stroke-width: 0.8"/>
</g>
</g>
<g id="text_4">
@ -507,7 +507,7 @@ z
<g id="xtick_5">
<g id="line2d_5">
<g>
<use xlink:href="#m4e3c01096c" x="323.570964" y="239.24" style="stroke: #000000; stroke-width: 0.8"/>
<use xlink:href="#m58592fa816" x="323.570964" y="239.24" style="stroke: #000000; stroke-width: 0.8"/>
</g>
</g>
<g id="text_5">
@ -532,7 +532,7 @@ z
<g id="xtick_6">
<g id="line2d_6">
<g>
<use xlink:href="#m4e3c01096c" x="388.62427" y="239.24" style="stroke: #000000; stroke-width: 0.8"/>
<use xlink:href="#m58592fa816" x="388.62427" y="239.24" style="stroke: #000000; stroke-width: 0.8"/>
</g>
</g>
<g id="text_6">
@ -766,16 +766,16 @@ z
<g id="line2d_7">
<path d="M 47.81 239.24
L 404.17201 239.24
" clip-path="url(#pccd18e2cbe)" style="fill: none; stroke: #b0b0b0; stroke-width: 0.2; stroke-linecap: square"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: none; stroke: #b0b0b0; stroke-width: 0.2; stroke-linecap: square"/>
</g>
<g id="line2d_8">
<defs>
<path id="mf098c48a56" d="M 0 0
<path id="m7e2ee167c1" d="M 0 0
L -3.5 0
" style="stroke: #000000; stroke-width: 0.8"/>
</defs>
<g>
<use xlink:href="#mf098c48a56" x="47.81" y="239.24" style="stroke: #000000; stroke-width: 0.8"/>
<use xlink:href="#m7e2ee167c1" x="47.81" y="239.24" style="stroke: #000000; stroke-width: 0.8"/>
</g>
</g>
<g id="text_7">
@ -789,11 +789,11 @@ L -3.5 0
<g id="line2d_9">
<path d="M 47.81 196.530625
L 404.17201 196.530625
" clip-path="url(#pccd18e2cbe)" style="fill: none; stroke: #b0b0b0; stroke-width: 0.2; stroke-linecap: square"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: none; stroke: #b0b0b0; stroke-width: 0.2; stroke-linecap: square"/>
</g>
<g id="line2d_10">
<g>
<use xlink:href="#mf098c48a56" x="47.81" y="196.530625" style="stroke: #000000; stroke-width: 0.8"/>
<use xlink:href="#m7e2ee167c1" x="47.81" y="196.530625" style="stroke: #000000; stroke-width: 0.8"/>
</g>
</g>
<g id="text_8">
@ -835,11 +835,11 @@ z
<g id="line2d_11">
<path d="M 47.81 153.82125
L 404.17201 153.82125
" clip-path="url(#pccd18e2cbe)" style="fill: none; stroke: #b0b0b0; stroke-width: 0.2; stroke-linecap: square"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: none; stroke: #b0b0b0; stroke-width: 0.2; stroke-linecap: square"/>
</g>
<g id="line2d_12">
<g>
<use xlink:href="#mf098c48a56" x="47.81" y="153.82125" style="stroke: #000000; stroke-width: 0.8"/>
<use xlink:href="#m7e2ee167c1" x="47.81" y="153.82125" style="stroke: #000000; stroke-width: 0.8"/>
</g>
</g>
<g id="text_9">
@ -854,11 +854,11 @@ L 404.17201 153.82125
<g id="line2d_13">
<path d="M 47.81 111.111875
L 404.17201 111.111875
" clip-path="url(#pccd18e2cbe)" style="fill: none; stroke: #b0b0b0; stroke-width: 0.2; stroke-linecap: square"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: none; stroke: #b0b0b0; stroke-width: 0.2; stroke-linecap: square"/>
</g>
<g id="line2d_14">
<g>
<use xlink:href="#mf098c48a56" x="47.81" y="111.111875" style="stroke: #000000; stroke-width: 0.8"/>
<use xlink:href="#m7e2ee167c1" x="47.81" y="111.111875" style="stroke: #000000; stroke-width: 0.8"/>
</g>
</g>
<g id="text_10">
@ -873,11 +873,11 @@ L 404.17201 111.111875
<g id="line2d_15">
<path d="M 47.81 68.4025
L 404.17201 68.4025
" clip-path="url(#pccd18e2cbe)" style="fill: none; stroke: #b0b0b0; stroke-width: 0.2; stroke-linecap: square"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: none; stroke: #b0b0b0; stroke-width: 0.2; stroke-linecap: square"/>
</g>
<g id="line2d_16">
<g>
<use xlink:href="#mf098c48a56" x="47.81" y="68.4025" style="stroke: #000000; stroke-width: 0.8"/>
<use xlink:href="#m7e2ee167c1" x="47.81" y="68.4025" style="stroke: #000000; stroke-width: 0.8"/>
</g>
</g>
<g id="text_11">
@ -933,11 +933,11 @@ z
<g id="line2d_17">
<path d="M 47.81 25.693125
L 404.17201 25.693125
" clip-path="url(#pccd18e2cbe)" style="fill: none; stroke: #b0b0b0; stroke-width: 0.2; stroke-linecap: square"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: none; stroke: #b0b0b0; stroke-width: 0.2; stroke-linecap: square"/>
</g>
<g id="line2d_18">
<g>
<use xlink:href="#mf098c48a56" x="47.81" y="25.693125" style="stroke: #000000; stroke-width: 0.8"/>
<use xlink:href="#m7e2ee167c1" x="47.81" y="25.693125" style="stroke: #000000; stroke-width: 0.8"/>
</g>
</g>
<g id="text_12">
@ -1199,17 +1199,17 @@ z
<g id="patch_3">
<path d="M 0 0
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_4">
<path d="M 0 0
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_5">
<path d="M 0 0
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_6">
<path d="M 233.146869 239.24
@ -1217,7 +1217,7 @@ L 257.867125 239.24
L 257.867125 104.368289
L 233.146869 104.368289
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_7">
<path d="M 298.200175 239.24
@ -1225,15 +1225,15 @@ L 322.920431 239.24
L 322.920431 102.762674
L 298.200175 102.762674
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_8">
<path d="M 363.25348 239.24
L 387.973737 239.24
L 387.973737 101.06261
L 363.25348 101.06261
L 387.973737 98.389934
L 363.25348 98.389934
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_9">
<path d="M 64.008273 239.24
@ -1241,7 +1241,7 @@ L 88.728529 239.24
L 88.728529 115.607599
L 64.008273 115.607599
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_10">
<path d="M 129.061579 239.24
@ -1249,7 +1249,7 @@ L 153.781835 239.24
L 153.781835 131.663755
L 129.061579 131.663755
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_11">
<path d="M 194.114885 239.24
@ -1257,22 +1257,22 @@ L 218.835141 239.24
L 218.835141 120.424445
L 194.114885 120.424445
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_12">
<path d="M 0 0
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_13">
<path d="M 0 0
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_14">
<path d="M 0 0
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_15">
<path d="M 47.81 239.24
@ -1360,10 +1360,10 @@ z
</g>
</g>
<g id="text_16">
<!-- 65% -->
<g transform="translate(369.60939 95.811985) scale(0.06 -0.06)">
<!-- 66% -->
<g transform="translate(369.60939 93.139309) scale(0.06 -0.06)">
<use xlink:href="#Helvetica-36"/>
<use xlink:href="#Helvetica-35" x="55.615234"/>
<use xlink:href="#Helvetica-36" x="55.615234"/>
<use xlink:href="#Helvetica-25" x="111.230469"/>
</g>
</g>
@ -1394,17 +1394,17 @@ z
<g id="patch_19">
<path d="M 0 0
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_20">
<path d="M 0 0
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_21">
<path d="M 0 0
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_22">
<path d="M 233.146869 239.24
@ -1412,7 +1412,7 @@ L 257.867125 239.24
L 257.867125 138.086217
L 233.146869 138.086217
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_23">
<path d="M 298.200175 239.24
@ -1420,15 +1420,15 @@ L 322.920431 239.24
L 322.920431 139.691833
L 298.200175 139.691833
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_24">
<path d="M 363.25348 239.24
L 387.973737 239.24
L 387.973737 121.16114
L 363.25348 121.16114
L 387.973737 118.835911
L 363.25348 118.835911
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3e6a8; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_25">
<path d="M 64.008273 239.24
@ -1436,7 +1436,7 @@ L 88.728529 239.24
L 88.728529 131.663755
L 64.008273 131.663755
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_26">
<path d="M 129.061579 239.24
@ -1444,7 +1444,7 @@ L 153.781835 239.24
L 153.781835 157.353604
L 129.061579 157.353604
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_27">
<path d="M 194.114885 239.24
@ -1452,22 +1452,22 @@ L 218.835141 239.24
L 218.835141 150.931142
L 194.114885 150.931142
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_28">
<path d="M 0 0
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_29">
<path d="M 0 0
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_30">
<path d="M 0 0
z
" clip-path="url(#pccd18e2cbe)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
" clip-path="url(#pbeff7bd0a1)" style="fill: #b3d1e6; stroke: #ffffff; stroke-width: 1.5; stroke-linejoin: miter"/>
</g>
<g id="patch_31">
<path d="M 173.129544 81.808517
@ -1868,7 +1868,7 @@ z
</g>
</g>
<defs>
<clipPath id="pccd18e2cbe">
<clipPath id="pbeff7bd0a1">
<rect x="47.81" y="25.693125" width="356.36201" height="213.546875"/>
</clipPath>
</defs>

Before

Width:  |  Height:  |  Size: 51 KiB

After

Width:  |  Height:  |  Size: 51 KiB

Before After
Before After

View file

@ -41,14 +41,14 @@ The benchmark gives aider two tries to complete the task:
### gpt-4-1106-preview
- The new `gpt-4-1106-preview` model seems **much faster** than the earlier GPT-4 models. I won't be able to properly quantify this until the rate limits loosen up.
- **It seems better at producing correct code on the first try**. It gets ~55% of the coding exercises correct, without needing to see errors from the test suite. Previous models only get 46-47% of the exercises correct on the first try.
- The new model seems to perform similar (65%) to the old models (63-64%) after being given a second chance to correct bugs by reviewing test suite error output.
- **It seems better at producing correct code on the first try**. It gets ~56% of the coding exercises correct, without needing to see errors from the test suite. Previous models only get 46-47% of the exercises correct on the first try.
- The new model seems to perform similar (66%) to the old models (63-64%) after being given a second chance to correct bugs by reviewing test suite error output.
**These results are preliminiary.**
OpenAI is enforcing very low
rate limits on the new GPT-4 model. The limits are so low, that
I have only been able to attempt
85
94
out of 133 exercism problems.
The problems are selected in random order, so results should be *roughly*
indicative of the full benchmark.