DeepSeekDSH
Independent community guideNot affiliated with DeepSeek.Official source snapshot

Coding AI Benchmark Template: Compare DeepSeek, GPT, Claude & Gemini in DSH

Benchmark coding models in DSH with the same repository, commit, mode, tools, prompt and acceptance tests; track pass rate, score, retries, time, API cost and human review cost.

Independent editorial review: DeepSeekDSHSource checked: 0.1.5-rc.2 · 2026-09-11
On this page
Production benchmark template · September 11, 2026

This does not replace SWE-bench or Terminal-Bench. Public benchmarks give standardized reference points; this template answers which model is actually better for your repository, DSH setup and acceptance bar.

Freeze the variables before you compare models

Same repository baseline

Start every run from the same Git commit. Do not let model B inherit model A's patch.

Same DSH version

Record the DSH version and hold mode/preset, workspace, tools, permissions and environment constant.

Same task and prompt

Keep prompt, input files, screenshots/PDFs and acceptance criteria identical.

Fresh session every run

Avoid contaminating the A/B with an existing session's model record or prior context.

Fixed resource limits

Define retries, time limit, network access and tools before the run; do not grant one model extra help midway.

Repeat runs

When budget allows, run each model 3–5 times per task and record both pass rate and median performance.

SWE-bench evaluates real GitHub issues with test-based acceptance, while Terminal-Bench standardizes task environments, timeouts and resources. Both reinforce the same rule: hold the harness and acceptance conditions fixed when comparing models.

Use a small representative task pack, not one cherry-picked bug

Task typeSuggested constraintWhat it tests
Bug fixOne reproducible failure with objective testsCan the model isolate the cause and make the smallest safe patch?
Targeted refactorBehavior must remain unchangedCan it improve structure without expanding scope or breaking tests?
Test generationKnown behavior with missing coverageCan it understand behavior and add useful, non-brittle tests?
Multi-file changeSmall feature or compatibility changeCan it plan across files without losing consistency?
Multimodal taskOptional screenshot/PDF/UI bugUseful when comparing models that accept visual inputs.
Low-cost starting design

Start with 3 tasks × 3 repeats × 2 models = 18 runs. If the result is close, expand the task set or model set instead of paying for dozens of runs up front.

Standard benchmark prompt

Replace Task and Acceptance Criteria with your real task. Give every model exactly the same version.

You are participating in a reproducible Coding Agent Benchmark.

Repository base commit: <BASE_COMMIT>
Task: <TASK>

Constraints:
1. Inspect the repository and relevant tests before editing.
2. Do not change public APIs unless the task explicitly requires it.
3. Modify only files necessary to complete the task.
4. Run tests directly relevant to the change; if tests cannot run, state why accurately.
5. Do not delete, skip or weaken tests merely to make the run pass.
6. At the end report: files changed, tests run, known risks and whether acceptance criteria were met.

Acceptance criteria:
<ACCEPTANCE_TESTS>

If the task genuinely requires public-API changes, network access or images, state that before the run. Do not relax the rules only after one model gets stuck.

100-point rubric: keep quality separate from acceptance

Acceptance should be decided by objective gates such as required tests passing, forbidden files untouched and no critical review issue. The 100-point rubric differentiates runs that all technically passed.

CriterionPointsHow to score
Functional correctness40Required tests and acceptance checks pass; the task is actually solved.
Regression safety20Existing relevant tests still pass and the change does not introduce obvious breakage.
Scope control15The model changes only what the task requires and avoids unrelated rewrites.
Tool efficiency10Uses tools purposefully, avoids repeated loops and does not waste calls on irrelevant exploration.
Code quality10The patch is maintainable, consistent with the repository and avoids unnecessary complexity.
Final report accuracy5The summary correctly states files changed, tests run, unresolved risks and limitations.
Total100Do not let a composite score override hard acceptance gates.

The cost metric that matters: accepted-task cost

Human review cost = review minutes ÷ 60 × reviewer hourly rate Total cost = API cost + sandbox/infra cost + human review cost Accepted-task cost = total cost across a model's runs ÷ number of accepted runs
  • Pass rate = accepted runs ÷ total runs.
  • If accepted runs = 0, accepted-task cost is not zero; it is undefined because the model did not clear the production bar on that test set.
  • When quality is comparable, prefer accepted-task cost over raw token price.
  • When engineering review is expensive, human review time can dominate token price.

Download the score sheet

The CSV includes the model, provider, model ID, reasoning setting, DSH version, mode, base commit, accepted flag, 100-point score, wall time, tool calls, retries, tokens, API cost and human review fields.

Download the Coding AI Benchmark CSV template ↓

ModelAcceptedScoreTimeAPI $Review minRetries
DeepSeek V4.1 Flash— / 100
GPT-6 Astra— / 100
Claude Fable 5.1— / 100
Gemini 3.8 Flash— / 100

Do not collapse the result into one universal winner

Quality winner

Start with pass rate, then compare median rubric score among accepted runs.

Cost winner

Among models that clear your quality bar, compare accepted-task cost.

Speed winner

Use accepted runs only, then compare median wall-clock time.

Stability winner

Look at pass rate, retries, tool loops and variance instead of cherry-picking the best run.

For example, repository-scale batch work may favor a cheap model, the hardest debugging may justify a frontier model, and screenshot-heavy tasks may favor a multimodal model. A production system can have multiple winners by workload.

FAQ

How many runs should I do per model?

Three to five runs per task is a practical starting point when budget allows. It is not statistically definitive, but it is much more useful than judging a model from one lucky or unlucky run.

Why should every model use a fresh DSH session?

DeepSeek Harness records the model used by an existing session. A fresh session helps keep model identity and prior context from contaminating the comparison.

Can I compare different agent harnesses with this template?

Yes, but then you are benchmarking complete systems rather than models. For a model-only comparison, keep DSH version, preset, tools, permissions and workspace fixed.

What if a model has zero accepted runs?

Do not report an accepted-task cost of zero. The denominator is zero, so cost per accepted task is undefined for that test set; operationally, the model failed your acceptance bar.

Should I use public leaderboard tasks?

Public benchmarks are useful reference points, but a production decision is stronger when you also use held-out tasks from your own repository that reflect the work you actually ship.

Why this template does not copy a public leaderboard

One of SWE-bench Verified's strengths is evaluating real software issues in reproducible environments with tests deciding whether a patch resolves the task. Terminal-Bench 2.1 also demonstrates that benchmarks themselves need continuous validation because task definitions, resources and external dependencies can materially change results.

This private benchmark borrows that evaluation discipline without pretending that three to five internal tasks produce a score directly comparable with a public leaderboard.