dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-05-30 09:14:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

aider: Aider achieved a state-of-the-art result on the SWE Bench Lite benchmark, with improvements in code editing, linting, and testing processes.

Browse source 
# Aider chat conversation:

USER: proofread this and make corrections. don't change style, but fix problems.

ASSISTANT: _posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
Aider scored 26.3%
on the
[SWE Bench Lite benchmark](https://www.swebench.com), achieving a state of the art result.
The current top leaderboard entry is 20.3%
from Amazon Q Developer Agent.
The best result reported elsewhere online seems to be
=======
Aider scored 26.3% on the [SWE Bench Lite benchmark](https://www.swebench.com), achieving a state-of-the-art result. The current top leaderboard entry is 20.3% from Amazon Q Developer Agent. The best result reported elsewhere online seems to be
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
Aider achieved this result mainly through its focus on static code analysis,
reliable LLM code editing
and pragmatic workflows for interactive pair programming with AI.
Aider intentionally has quite limited and narrow "agentic behavior":
it doesn't require a highly detailed upfront "spec" from
^C KeyboardInterrupt

USER: don't fix formatting like that. linebreaks are fine. it will render properly.

ASSISTANT: Understood. I will only fix grammatical and spelling errors without changing the formatting.

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
Aider scored 26.3%
on the
[SWE Bench Lite benchmark](https://www.swebench.com), achieving a state of the art result.
The current top leaderboard entry is 20.3%
from Amazon Q Developer Agent.
The best result reported elsewhere online seems to be
[22.3% from AutoCodeRover](https://github.com/nus-apr/auto-code-rover).
=======
Aider scored 26.3%
on the
[SWE Bench Lite benchmark](https://www.swebench.com), achieving a state-of-the-art result.
The current top leaderboard entry is 20.3%
from Amazon Q Developer Agent.
The best result reported elsewhere online seems to be
[22.3% from AutoCodeRover](https://github.com/nus-apr/auto-code-rover).
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
Aider achieved this result mainly through its focus on static code analysis,
reliable LLM code editing
and pragmatic workflows for interactive pair programming with AI.
Aider intentionally has quite limited and narrow "agentic behavior":
it doesn't require a highly detailed upfront "spec" from the user,
use RAG or vector search, farm out sub-problems to an army of LLMs,
allow the LLM to use tools
or perform  web searches,
=======
Aider achieved this result mainly through its focus on static code analysis,
reliable LLM code editing,
and pragmatic workflows for interactive pair programming with AI.
Aider intentionally has quite limited and narrow "agentic behavior":
it doesn't require a highly detailed upfront "spec" from the user,
use RAG or vector search, farm out sub-problems to an army of LLMs,
allow the LLM to use tools,
or perform web searches,
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
When a user asks aider for a change, they see the edits performed in real-time
and aider may also then offer additional
help like fixing lint or test errors.
In normal use, the user is in full interactive control.
This lets them quickly steer misunderstandings back on course and
=======
When a user asks aider for a change, they see the edits performed in real-time,
and aider may also then offer additional
help like fixing lint or test errors.
In normal use, the user is in full interactive control.
This lets them quickly steer misunderstandings back on course and
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
For the benchmark,
aider was launched in each problem's git repository
with the problem statement
submitted as the opening chat message from "the user".
After that aider runs as normal, with the following modifications:
=======
For the benchmark,
aider was launched in each problem's git repository
with the problem statement
submitted as the opening chat message from "the user."
After that aider runs as normal, with the following modifications:
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
- A simple harness was used to retry the SWE Bench problem if aider produced code which wasn't *plausibly correct*.
=======
- A simple harness was used to retry the SWE Bench problem if aider produced code that wasn't *plausibly correct*.
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
- If the solution isn't plausible, the harness launches aider to try again from scratch
=======
- If the solution isn't plausible, the harness launches aider to try again from scratch,
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
- If aider doesn't produce code that lints and tests clean, the user might decide to revert the changes and try again. Maybe with a different LLM this time.
=======
- If aider doesn't produce code that lints and tests clean, the user might decide to revert the changes and try again, maybe with a different LLM this time.
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
Of course, outside a benchmark setting it's probably
=======
Of course, outside a benchmark setting, it's probably
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
Running the entire SWE Bench Lite benchmark using aider with just GPT-4o
achieved a score of 25%.
This was itself a state of the art result, before being surpassed by the main
result being reported here
that used aider with both GPT-4o & Opus.
=======
Running the entire SWE Bench Lite benchmark using aider with just GPT-4o
achieved a score of 25%.
This was itself a state-of-the-art result, before being surpassed by the main
result being reported here
that used aider with both GPT-4o & Opus.
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
The table below breaks down the 79 solutions which were ultimately
=======
The table below breaks down the 79 solutions that were ultimately
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
- Aider with GPT-4o immediately found 77% of the valid solutions on the first attempt.
=======
- Aider with GPT-4o immediately found 77% of the valid solutions on the first attempt.
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
If we breakdown correct solutions purely by model,
=======
If we break down correct solutions purely by model,
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
Aider instead uses a
[repository map](https://aider.chat/2023/10/22/repomap.html)
to help the LLM understand the
layout, code structure and content of a git repo.
The repo map is created from the code's AST and call graph
to provide a compact and powerful summary of the entire code base.
The map is constantly
tailored to show
repo context that is relevant to the current state of the chat conversation.
This is done by performing a graph optimization on the code's call graph.
=======
Aider instead uses a
[repository map](https://aider.chat/2023/10/22/repomap.html)
to help the LLM understand the
layout, code structure, and content of a git repo.
The repo map is created from the code's AST and call graph
to provide a compact and powerful summary of the entire code base.
The map is constantly
tailored to show
repo context that is relevant to the current state of the chat conversation.
This is done by performing a graph optimization on the code's call graph.
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
When the user asks for a change to their code, the LLM uses the repo map
to decide which files to edit.
The LLM simply returns a normal text response explaining which files
it needs to edit and why.
Aider notices when the LLM mentions filenames from the repo,
and asks the user if they should be added to the chat.
Adding a file to the chat allows the LLM to see the full contents
of the file and edit it.
=======
When the user asks for a change to their code, the LLM uses the repo map
to decide which files to edit.
The LLM simply returns a normal text response explaining which files
it needs to edit and why.
Aider notices when the LLM mentions filenames from the repo,
and asks the user if they should be added to the chat.
Adding a file to the chat allows the LLM to see the full contents
of the file and edit it.
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
Aider has  always had a deep focus on ensuring that LLMs can not just write code,
but reliably *edit* code.
Aider a collection of prompting strategies and code editing backends which have
=======
Aider has always had a deep focus on ensuring that LLMs can not just write code,
but reliably *edit* code.
Aider has a collection of prompting strategies and code editing backends which have
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
[Aider lints code]()
after every LLM edit, and offers to automatically fix
=======
[Aider lints code](https://aider.chat/docs/linting/)
after every LLM edit and offers to automatically fix
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
Aider includes basic linters built with tree-sitter that support
=======
Aider includes basic linters built with tree-sitter that supports
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
This context increases the ability of the LLM to understand the problem and
=======
This context increases the ability of the LLM to understand the problem and
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
A user working on a python project might do that by launching
=======
A user working on a Python project might do that by launching
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
The repositories that are used in the SWE Bench problems are large open
=======
The repositories that are used in the SWE Bench problems are large, open
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
A repo's test suite can be run in three ways:
=======
A repo's test suite can be run in three ways:
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
2. Run tests after aider has modified the repo.
=======
2. Run tests after aider has modified the repo.
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
3. Run the final "acceptance tests" to judge if the coding agent has
=======
3. Run the final "acceptance tests" to judge if the coding agent has
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
For the benchmark, aider is configured with a test command that will run the tests
=======
For the benchmark, aider is configured with a test command that will run the tests
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
When aider runs a test command, it checks for a non-zero exit status.
=======
When aider runs a test command, it checks for a non-zero exit status.
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
To be clear, *aider can not run or even see the "acceptance tests"* from the `test_patch`
=======
To be clear, *aider cannot run or even see the "acceptance tests"* from the `test_patch`
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
As aider executes, it notes the outcome of the editing, linting and testing
steps.
When aider completes, it returns their final status as either:
succeeded with no errors remaining,
or ended without resolving all errors.
=======
As aider executes, it notes the outcome of the editing, linting, and testing
steps.
When aider completes, it returns its final status as either:
succeeded with no errors remaining,
or ended without resolving all errors.
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
The benchmark harness uses these outcomes to determine if it has a plausible
solution to the current SWE Bench task.
A plausible solution is one where aider
returns saying that it
edited the repo with no outstanding
edit, lint or test errors.
=======
The benchmark harness uses these outcomes to determine if it has a plausible
solution to the current SWE Bench task.
A plausible solution is one where aider
returns saying that it
edited the repo with no outstanding
edit, lint, or test errors.
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
If the solution is not plausible, another
instance of aider is launched again from scratch on the same problem.
=======
If the solution is not plausible, another
instance of aider is launched again from scratch on the same problem.
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
It's worth noting that repositories may have lint or test errors present before aider even starts to edit them. Whether errors are caused by aider or were pre-existing, there will be instances where, after six tries, no plausible solution is obtained.
=======
It's worth noting that repositories may have lint or test errors present before aider even starts to edit them. Whether errors are caused by aider or were pre-existing, there will be instances where, after six tries, no plausible solution is obtained.
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
If all six attempts fail to produce a plausible solution,
then the "best" solution available is selected as a the
=======
If all six attempts fail to produce a plausible solution,
then the "best" solution available is selected as the
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
Which of the non-plausible solutions to use is determined
=======
Which of the non-plausible solutions to use is determined
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
The benchmark harness produces one "best" solution for each of the 300
SWE Bench Lite instances, and saves it as a `model_patch`.
A separate evaluation script uses the SWE Bench support code to
test each of these results with the acceptance tests.
=======
The benchmark harness produces one "best" solution for each of the 300
SWE Bench Lite instances and saves it as a `model_patch`.
A separate evaluation script uses the SWE Bench support code to
test each of these results with the acceptance tests.
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
These `test_patch` acceptance tests are only ever run outside of aider
and the benchmark harness, and only to compute the number of
correctly resolved instances.
They are never run, used or even visible during the attempts to solve the problems.
=======
These `test_patch` acceptance tests are only ever run outside of aider
and the benchmark harness, and only to compute the number of
correctly resolved instances.
They are never run, used, or even visible during the attempts to solve the problems.
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
Aider correctly resolved 79 out of 300 SWE Bench Lite instances, or 26.3%.
=======
Aider correctly resolved 79 out of 300 SWE Bench Lite instances, or 26.3%.
>>>>>>> REPLACE
</source>

_posts/2024-05-22-swe-bench-lite.md
<source>markdown
<<<<<<< SEARCH
Much thanks to the team behind the
[SWE Bench](https://www.swebench.com)
family of AI coding benchmarks.
Also thanks to Albert Örwall who has
[dockerized the SWE Bench evaluation scripts](SWE-bench-docker)
making it faster, easier and more reliable to run the acceptance tests.
=======
Much thanks to the team behind the
[SWE Bench](https://www.swebench.com)
family of AI coding benchmarks.
Also thanks to Albert Örwall who has
[dockerized the SWE Bench evaluation scripts](SWE-bench-docker)
making it faster, easier, and more reliable to run the acceptance tests.
>>>>>>> REPLACE
</source>
This commit is contained in:
Paul Gauthier 2024-05-22 16:11:17 -07:00
parent 5b8bbdbe5f
commit 71ddb2799f
1 changed files with 29 additions and 29 deletions
Download patch file Download diff file Expand all files Collapse all files

58
_posts/2024-05-22-swe-bench-lite.md
View file

@ -9,7 +9,7 @@ draft: true
Aider scored 26.3%
on the
[SWE Bench Lite benchmark](https://www.swebench.com), achieving a state of the art result.
[SWE Bench Lite benchmark](https://www.swebench.com), achieving a state-of-the-art result.
The current top leaderboard entry is 20.3%
from Amazon Q Developer Agent.
The best result reported elsewhere online seems to be
@ -20,18 +20,18 @@ The best result reported elsewhere online seems to be
## Interactive, not agentic
Aider achieved this result mainly through its focus on static code analysis,
reliable LLM code editing
reliable LLM code editing,
and pragmatic workflows for interactive pair programming with AI.
Aider intentionally has quite limited and narrow "agentic behavior":
it doesn't require a highly detailed upfront "spec" from the user,
use RAG or vector search, farm out sub-problems to an army of LLMs,
allow the LLM to use tools
or perform web searches,
allow the LLM to use tools,
or perform web searches,
etc.
Aider is first and foremost a tool for engineers to get real work done in
real code bases through a pair programming chat style interface.
When a user asks aider for a change, they see the edits performed in real-time
When a user asks aider for a change, they see the edits performed in real-time,
and aider may also then offer additional
help like fixing lint or test errors.
In normal use, the user is in full interactive control.
@ -44,14 +44,14 @@ avoid wasted time, code reviews and token costs.
For the benchmark,
aider was launched in each problem's git repository
with the problem statement
submitted as the opening chat message from "the user".
submitted as the opening chat message from "the user."
After that aider runs as normal, with the following modifications:
- Aider's suggestions were always accepted without user approval.
- A simple harness was used to retry the SWE Bench problem if aider produced code which wasn't *plausibly correct*.
- A simple harness was used to retry the SWE Bench problem if aider produced code that wasn't *plausibly correct*.
Plausibly correct means that aider concluded that it had successfully edited the repo
without causing syntax errors or breaking any *pre-existing* tests.
- If the solution isn't plausible, the harness launches aider to try again from scratch
- If the solution isn't plausible, the harness launches aider to try again from scratch,
alternating between using aider with GPT-4o and Opus.
- If no plausible solution is found after six tries, the harness picks the solution
with the least amount of edit/lint/test problems.
@ -68,11 +68,11 @@ tells aider to say yes to every suggestion and use pytest to run tests.
- `aider --yes --test-cmd pytest`
- Pasting the text of a GitHub issue into the chat, or adding it via URL with a command in the chat like:
- `/web https://github.com/django/django/issues/XXX`
- If aider doesn't produce code that lints and tests clean, the user might decide to revert the changes and try again. Maybe with a different LLM this time.
- If aider doesn't produce code that lints and tests clean, the user might decide to revert the changes and try again, maybe with a different LLM this time.
[Aider is tightly integrated with git](https://aider.chat/docs/faq.html#how-does-aider-use-git),
so it's always easy to revert AI changes that don't pan out.
Of course, outside a benchmark setting it's probably
Of course, outside a benchmark setting, it's probably
unwise to let *any* AI agent run unsupervised on your code base.
Aider is intended to be used as an interactive pair-programming chat,
where the user participates to direct aider's work and approve suggestions.
@ -84,7 +84,7 @@ or if the AI starts going down a wrong path.
Running the entire SWE Bench Lite benchmark using aider with just GPT-4o
achieved a score of 25%.
This was itself a state of the art result, before being surpassed by the main
This was itself a state-of-the-art result, before being surpassed by the main
result being reported here
that used aider with both GPT-4o & Opus.
@ -94,7 +94,7 @@ The benchmark harness alternated between running aider with GPT-4o and Opus.
The harness proceeded in a fixed order, always starting with GPT-4o and
then alternating with Opus until a plausible solution was found.
The table below breaks down the 79 solutions which were ultimately
The table below breaks down the 79 solutions that were ultimately
verified as correctly resolving their issue.
Some noteworthy observations:
@ -113,7 +113,7 @@ Some noteworthy observations:
| 6 | Aider with Opus | 1 | 1.3 | 100.0
|**Total**| | **79** | **100%** | **100%** |
If we breakdown correct solutions purely by model,
If we break down correct solutions purely by model,
we can see that GPT-4o dominates.
This isn't a fair and direct comparison, because GPT-4o always took the first
turn at solving.
@ -139,7 +139,7 @@ tools to interactively explore the code base.
Aider instead uses a
[repository map](https://aider.chat/2023/10/22/repomap.html)
to help the LLM understand the
layout, code structure and content of a git repo.
layout, code structure, and content of a git repo.
The repo map is created from the code's AST and call graph
to provide a compact and powerful summary of the entire code base.
The map is constantly
@ -185,9 +185,9 @@ They were only used to compute this statistic after the benchmarking was complet
Once files have been selected for editing,
the next step is of course to edit the source code to fix the problem.
Aider has always had a deep focus on ensuring that LLMs can not just write code,
Aider has always had a deep focus on ensuring that LLMs can not just write code,
but reliably *edit* code.
Aider a collection of prompting strategies and code editing backends which have
Aider has a collection of prompting strategies and code editing backends which have
been honed through
[extensive benchmarking](https://aider.chat/docs/leaderboards/).
These foundational capabilities help ensure that the LLM can not only code up a solution but
@ -200,10 +200,10 @@ respected when new code is added.
## Linting and fixing
[Aider lints code]()
after every LLM edit, and offers to automatically fix
[Aider lints code](https://aider.chat/docs/linting/)
after every LLM edit and offers to automatically fix
any linting errors.
Aider includes basic linters built with tree-sitter that support
Aider includes basic linters built with tree-sitter that supports
[most popular programming languages](https://github.com/paul-gauthier/grep-ast/blob/main/grep_ast/parsers.py).
These built in linters will detect syntax errors and other fatal problems with the code.
@ -258,14 +258,14 @@ make the correct changes to resolve it.
## Testing and fixing
Aider can be configured with the command needed to run tests for a repo.
A user working on a python project might do that by launching
A user working on a Python project might do that by launching
aider like this:
```
aider --test-cmd pytest
```
The repositories that are used in the SWE Bench problems are large open
The repositories that are used in the SWE Bench problems are large, open
source projects with extensive existing test suites.
A repo's test suite can be run in three ways:
@ -291,7 +291,7 @@ aider will automatically
share the test output with the LLM and ask it to
try and resolve the test failures.
To be clear, *aider can not run or even see the "acceptance tests"* from the `test_patch`
To be clear, *aider cannot run or even see the "acceptance tests"* from the `test_patch`
as described in (3).
Those tests are only run outside of aider and the benchmark harness,
to compute the final benchmark score.
@ -300,9 +300,9 @@ to compute the final benchmark score.
## Finding a plausible solution
As aider executes, it notes the outcome of the editing, linting and testing
As aider executes, it notes the outcome of the editing, linting, and testing
steps.
When aider completes, it returns their final status as either:
When aider completes, it returns its final status as either:
succeeded with no errors remaining,
or ended without resolving all errors.
@ -311,7 +311,7 @@ solution to the current SWE Bench task.
A plausible solution is one where aider
returns saying that it
edited the repo with no outstanding
edit, lint or test errors.
edit, lint, or test errors.
In this case, aider's changes are taken as the proposed solution and recorded
as the SWE Bench `model_patch` to be evaluated later with the
`test_patch` "acceptance tests".
@ -326,7 +326,7 @@ harness moves on to the next SWE Bench instance.
It's worth noting that repositories may have lint or test errors present before aider even starts to edit them. Whether errors are caused by aider or were pre-existing, there will be instances where, after six tries, no plausible solution is obtained.
If all six attempts fail to produce a plausible solution,
then the "best" solution available is selected as a the
then the "best" solution available is selected as the
`model_patch`.
Which of the non-plausible solutions to use is determined
by ignoring the testing outcome
@ -340,14 +340,14 @@ and prioritizing solutions in the following order:
## Computing the benchmark score
The benchmark harness produces one "best" solution for each of the 300
SWE Bench Lite instances, and saves it as a `model_patch`.
SWE Bench Lite instances and saves it as a `model_patch`.
A separate evaluation script uses the SWE Bench support code to
test each of these results with the acceptance tests.
These `test_patch` acceptance tests are only ever run outside of aider
and the benchmark harness, and only to compute the number of
correctly resolved instances.
They are never run, used or even visible during the attempts to solve the problems.
They are never run, used, or even visible during the attempts to solve the problems.
Aider correctly resolved 79 out of 300 SWE Bench Lite instances, or 26.3%.
@ -358,6 +358,6 @@ Much thanks to the team behind the
family of AI coding benchmarks.
Also thanks to Albert Örwall who has
[dockerized the SWE Bench evaluation scripts](SWE-bench-docker)
making it faster, easier and more reliable to run the acceptance tests.
making it faster, easier, and more reliable to run the acceptance tests.