[HN Gopher] Qodo CLI agent scores 71.2% on SWE-bench Verified
       ___________________________________________________________________
        
       Qodo CLI agent scores 71.2% on SWE-bench Verified
        
       Author : bobismyuncle
       Score  : 130 points
       Date   : 2025-08-12 11:05 UTC (11 hours ago)
        
 (HTM) web link (www.qodo.ai)
 (TXT) w3m dump (www.qodo.ai)
        
       | gronky_ wrote:
       | I've been running a bunch of coding agents on benchmarks recently
       | as part of consulting, and this is actually much more impressive
       | than it seems at first glance.
       | 
       | 71.2% puts it at 5th, which is 4 points below the leader (four
       | points is a lot) and just over 1% lower than Anthropic's own
       | submission for Claude Sonnet 4 - the same model these guys are
       | running.
       | 
       | But the top rated submissions aren't running production products.
       | They generally have extensive scaffolding or harnesses that were
       | built *specifically for SWE bench*, which kind of defeats the
       | whole purpose of the benchmark.
       | 
       | Take for example Refact which is at #2 with 74.4%, they built a
       | 2k lines of code framework around their agent specifically for
       | SWE bench (https://github.com/smallcloudai/refact-bench/). It's
       | pretty elaborate, orchestrating multiple agents, with a debug
       | agent that kicks in if the main agent fails. The debug agent
       | analyzes the failure and gives insights to the main agent which
       | tries again, so it's effectively multiple attempts per problem.
       | 
       | If the results can be reproduced "out-of-the-box" with their
       | coding agent like they claim, it puts it up there as one of the
       | top 2-3 CLI agents available right now.
        
         | szundi wrote:
         | According to your experience with this model, is it just
         | trained for the benchmark or these points are actually
         | representing the performance?
        
         | energy123 wrote:
         | What are the typical context lengths in SWE-bench problems?
         | Does it partly measure performance in the 64-128k context
         | range?
        
           | dimitri-vs wrote:
           | IIRC the SWE bench dataset gives you the full repo snapshot +
           | the issue text, the evaluation pipelines typically run some
           | kind of retriever (eg. grep, BM25) to pick a subset of files
           | to place in the model's context. They provided context is
           | usually limited up to ~50k tokens.
        
           | whymauri wrote:
           | This is what the rows look like:
           | 
           | https://huggingface.co/datasets/princeton-nlp/SWE-
           | bench_Veri...
           | 
           | Its up to your retrieval system/model to selectively hunt for
           | relevant context. Here's a few critiques of the benchy:
           | 
           | https://x.com/brhydon/status/1953648884309536958
        
         | thinkingtoilet wrote:
         | This is classic Goodhart's law. "When a measure becomes a
         | target, it ceases to be a good measure"
         | 
         | https://en.wikipedia.org/wiki/Goodhart%27s_law
        
           | ambicapter wrote:
           | It's really not that hard to _not_ build a custom bench setup
           | to game the benchmark instead of just using your product
           | straight out of the box, though.
        
             | jasonjmcghee wrote:
             | Right. Building a custom setup is blatant- that will wildly
             | overfit.
             | 
             | But let's say a group uses it as a metric as part of CI and
             | each new idea / feature they create runs against SWE bench.
             | Maybe they have parameterized bits and pieces they adjust,
             | maybe they have multiple candidates datasets for fine
             | tuning, maybe they're choosing between checkpoints.
             | 
             | This will also end up overfitting - especially if done
             | habitually. It might be a great metric and result in a more
             | powerful overall model. Or it might not.
        
             | VikingCoder wrote:
             | Right, other than financial pressure. Which is, of course,
             | immense.
        
           | clutchdude wrote:
           | Also see the VW dieselgate and numerous other "gaming the
           | system" examples.
        
           | kelipso wrote:
           | A specific setup for the benchmark is just plain cheating,
           | not Goodhart's law.
        
         | eddd-ddde wrote:
         | I think multiple attempts are completely understandable and
         | even expected? How is that defeating the purpose of the
         | benchmark?
        
           | gronky_ wrote:
           | It's a pass@1 benchmark. When submitting you need to check a
           | box that there was only 1 attempt per problem. See here for
           | example: https://github.com/SWE-bench/experiments/pull/219
           | 
           | Building multiple attempts into your agent is stretching the
           | rules, even if technically it's acceptable
        
             | terminalshort wrote:
             | From my perspective as a potential user the number of
             | attempts is the number of times I have to tell it what to
             | do. If you have an agent that makes a single attempt and is
             | 60% accurate vs another that makes 5 attempts and is 80%
             | accurate, why would you care that each individual attempt
             | of the 2nd model is less accurate than the first?
        
               | mcintyre1994 wrote:
               | I think it depends on "But the top rated submissions
               | aren't running production products" It sounds like
               | they're shipping a product without the debug agent/try-
               | again logic, and that's just for the benchmark, so you
               | wouldn't get the performance they get as a user.
        
               | gronky_ wrote:
               | This ok from your perspective then?
               | 
               | def make_pass@1_agent(agent, n):                   def
               | retry_agent(problem):                  for attempt in
               | range(n):                      result = agent(problem)
               | if result.success:                          return result
               | return result              return retry_agent
        
               | gronky_ wrote:
               | Keep in mind that this isn't about users - the top agents
               | on the leaderboard aren't running an actual product on
               | the benchmark.
               | 
               | If they are running their production product as is, then
               | of course whatever is built into the product is fine.
        
               | DougBTX wrote:
               | Absolutely fine, as long as the success flag is predicted
               | by the model ensemble under test. That's how Claude Code
               | works for example, it will continue to iterate until
               | success (or it will give up with failure at a certain
               | point).
        
               | terminalshort wrote:
               | Definitely wouldn't have written the code that way, but
               | yes, if (and this is a massive "if") the agent has an
               | accurate and meaningful way to determine which way to set
               | the success boolean. The obvious caveat would be if n
               | needed to be large enough to set the costs higher than I
               | am willing to pay for the additional performance or it
               | makes it take longer than I'm willing to wait.
               | 
               | Think of the agent like an employee. If he delivers the
               | code within the expected time and to the expected quality
               | standards, his process of getting there means almost
               | nothing. Do I care if he tried 4 different approaches
               | along the way and threw out the first 3? Not a bit.
        
               | whymauri wrote:
               | Papers have been doing rollouts that involve a model
               | proposing N solutions and then self-reviewing to choose
               | the best one (prior to the verifier). So far, I think
               | that's been counted as one pass.
        
               | radarsat1 wrote:
               | I was thinking about this recently with respect to how
               | many agent systems now let you specify a smaller/faster
               | model for easier tasks and a bigger model for harder
               | tasks.
               | 
               | It's interesting to think about what the trade-offs are.
               | Assuming the system can properly classify a task as easy
               | or hard (big "if" but I guess there are ways), there is
               | nonetheless more to think about, depending on your
               | pricing plan.
               | 
               | For subscription pricing, I guess you don't really care
               | which model runs and in fact it's hard to find a reason
               | to ever run the smaller model, so choosing between the
               | models is more in the provider's interests for cost
               | efficiency.
               | 
               | But for pay-per-use pricing, But if you have a bigger
               | model that can get the answer right 80% of the time, and
               | a smaller model that can handle smaller changes and get
               | things right 60% of the time but correct its mistakes,
               | then the system should try to run it on as many tasks as
               | possible to save you money.. but in the end if ends up
               | having to make a lot of corrections, then maybe you end
               | up needing _more_ total requests than the larger model.
               | In that case maybe it 's actually _cheaper_ to run the
               | larger model, if it takes fewer requests.
               | 
               | So I wonder how that kind of trade-off could be
               | effectively calculated. I guess if you can figure out
               | when "retries" happen you can count them and do some
               | statistics on which model is more likely to work out in
               | fewer shots. It's pretty complicated though, when you
               | start to think about it in detail.
               | 
               | I do wonder if even having BOTH the smaller and bigger
               | model make hypotheses, and try the smaller model's idea
               | first, then if it fails, try the bigger model's idea,
               | might be the way to go.
        
         | oblio wrote:
         | https://github.com/auchenberg/volkswagen
        
         | Roritharr wrote:
         | Finally someone mentions Refact, I was in contact with the
         | team, rooting for them really.
        
           | bluelightning2k wrote:
           | Just looked them up. Their pricing is around buying "coins"
           | with no transparency as to what that gets. Hard pass
        
             | Roritharr wrote:
             | You realize that you can self-host their stuff?
             | https://github.com/smallcloudai/refact
        
         | terminalshort wrote:
         | Is there something in this multi-agent approach that makes the
         | setup more specific to just the test at hand and less general
         | to real engineering tasks? If not, then this multi-agent system
         | will just become what you get out of the box in a future
         | product. Multiple attempts per problem (as long as there's no
         | human intervention or selection between them) is a perfectly
         | fine approach for agents because that's not an issue from the
         | perspective of an engineer using the product. A single agent is
         | already a multi-step usage of LLMs and it sounds like this is
         | just another meta level of that.
        
         | ai-christianson wrote:
         | One thing with SWE bench is making sure there's zero leakage of
         | information into the LLM context.
         | 
         | I.e. the agent cannot even know which tests are failing.
         | 
         | It has to both fix the issue based just on the issue text _and
         | fix it in the specific way the unit test, which it cannot see,
         | expects_.
         | 
         | For this reason I find the benchmark a little disconnected from
         | the reality of software engineering.
        
       | orangebread wrote:
       | I've been using Warp for the past few weeks and it's been
       | incredibly impressive over other agentic coding
       | services/platforms. Curious how Qodo stacks up.
        
         | lightbendover wrote:
         | When I tried warp I was convinced that was where the industry
         | was going (agents as terminal replacement), but it felt a bit
         | too heavy to me so I haven't been using it lately. Still think
         | all things will converge on terminal and browser replacement.
        
       | rs186 wrote:
       | So this is from the same company that wrote a blog post with
       | sentences that don't even make sense:
       | 
       | https://news.ycombinator.com/item?id=44833929, my comment
       | https://news.ycombinator.com/item?id=44835939
        
       | khalic wrote:
       | We need some international body to start running these tests... I
       | just can't trust these numbers any longer. We need a platform for
       | this, something at least we can get some peer reviews
        
         | redman25 wrote:
         | That sounds like an interesting idea to me. It would at least
         | resolve the problem of companies gaming the metric.
         | 
         | Another approach might be the LiveBench approach where new
         | tests are released on a regular basis.
        
       | mupuff1234 wrote:
       | I'm curious how do these LLM wrapper companies think they'll
       | survive long term - especially coding related wrappers.
       | 
       | I could understand focusing on a niche business use case, but
       | coding is a main focus of the foundation models themselves.
        
         | M4R5H4LL wrote:
         | Labeling them as "wrappers" and "niche business" indicates a
         | strong cognitive bias already. Value can be created on both
         | sides of the equation.
        
           | dgfitz wrote:
           | How so? They are wrappers, and it is niche.
        
             | choilive wrote:
             | Wrappers are a bit pejorative and reductive - everything is
             | a wrapper around something else.
        
               | dgfitz wrote:
               | If everything is a wrapper around something else, how can
               | the description be a pejorative?
        
       | itamarcode wrote:
       | Unlike most SWE bench submissions, Qodo Command one uses the
       | product directly.
       | 
       | I think that the next step is getting an official "checked" mark
       | by the SWE bench team
        
         | whymauri wrote:
         | I feel like the bash only SWE Bench Verified (a.k.a model +
         | mini-swe-agent) is the closest thing to measuring the inherent
         | ability of the model vs. the scaffolding.
         | 
         | https://github.com/SWE-agent/mini-swe-agent
        
           | NitpickLawyer wrote:
           | There's swe-rebench, where they take "bugs/issues" by date,
           | and you can drag a slider on their top scores to see issues
           | solved _after_ the model was released (obviously only truly
           | working for open models).
        
       | OldGreenYodaGPT wrote:
       | Was using their bot for code review for last 2 years but just
       | dropped it for BugBot
        
       | esafak wrote:
       | If Qodo is reading: please compare your efficiency too. Run some
       | tasks on various agents using the same models, and report the
       | cost.
        
       | zuzuen_1 wrote:
       | Does anyone have a benchmark on the effectiveness of using
       | embeddings for mapping bug reports to code files as opposed to
       | extensive grepping as Qodo, Cursor and a number of tools I use do
       | to localize faults?
        
       | zuzuen_1 wrote:
       | I would be more interested in Qodo's performance on the swe-
       | bench-multilingual benchmark. Swe-bench-verified only includes
       | bugs related to python breakages.
       | 
       | The best submission is swe-bench-multilingual is Claude 3.7
       | Sonnet which solves ~43% of the issues in the dataset.
        
       | OldfieldFund wrote:
       | do we know anything about the size of the model? I can't find the
       | answer.
        
       | afro88 wrote:
       | If Qodo are reading this: please introduce a plan that isn't for
       | teams or enterprise. A "pro" plan for individuals who want more
       | than 250 credits per month.
        
       ___________________________________________________________________
       (page generated 2025-08-12 23:01 UTC)