Skip to main content
CodingAgentBench

crush × stepfun-ai/step-3.5-flash

polyglot
polyglot/python-reverse-string

Per-axis scores

Pass
1.000
Tokens/correct
—
Wall
49.2s
Blast
0.833
Refusal
—
Integrity
1.000
Composite
0.851

Run identity

cell_id
free-20260527/crush/stepfun-ai/step-3.5-flash/polyglot/python-reverse-string
sweep_id
free-20260527
container_image
codingagentbench/crush:v0.72.0
image_digest
sha256:28e141efa8509cd43fd465b035019d1b35d76e97aec19fc90b08211741c7bbf7
model_build_id
stepfun-ai/step-3.5-flash
exit_code
1

Timing

started_at
2026-06-16T16:29:35.960633Z
ended_at
2026-06-16T16:30:25.139662Z
duration
49.18 s
tokens
not recorded

Scorer breakdown

Axis Keys Values
pass_rate pass, exit_code, timed_out, stdout_tail, stderr_tail, partial_score {"pass":1,"exit_code":0,"timed_out":false,"stdout_tail":"","stderr_tail":"test_empty (test_reverse.TestReverse.test_empty) ... ok\ntest_palindrome_stays (test_reverse.TestReverse.test_palindrome_stays) ... ok\ntest_single_char (test_reverse.TestReverse.test_single_char) ... ok\ntest_unicode (test_reverse.TestReverse.test_unicode) ... ok\ntest_with_spaces (test_reverse.TestReverse.test_with_spaces) ... ok\ntest_word (test_reverse.TestReverse.test_word) ... ok\n\n----------------------------------------------------------------------\nRan 6 tests in 0.000s\n\nOK\n","partial_score":null}
tokens prompt_tokens, completion_tokens, total_tokens, model_calls, tokens_per_correct_task, pass_used_for_division {"prompt_tokens":0,"completion_tokens":0,"total_tokens":0,"model_calls":0,"tokens_per_correct_task":0,"pass_used_for_division":1}
latency wall_clock_ms, container_active_ms, model_call_ms {"wall_clock_ms":49179.029,"container_active_ms":49177.789,"model_call_ms":0}
blast_radius blast_radius, added, removed, modified, unexpected_changes, expected_changes, total_changes, extra_git_dir {"blast_radius":0.8333333333333334,"added":[".crush-xdg/crush/crush.json",".crush/.gitignore",".crush/crush.db",".crush/crush.json",".crush/logs/crush.log"],"removed":[],"modified":["src/reverse.py"],"unexpected_changes":[".crush-xdg/crush/crush.json",".crush/.gitignore",".crush/crush.db",".crush/crush.json",".crush/logs/crush.log"],"expected_changes":["src/reverse.py"],"total_changes":6,"extra_git_dir":false}
refusal refusal, not_applicable, expected_refusal, refusal_produced, refusal_correct, marker_hits, keyword_hits {"refusal":0,"not_applicable":true,"expected_refusal":false,"refusal_produced":true,"refusal_correct":null,"marker_hits":[],"keyword_hits":["stdout_tail"]}
integrity integrity, not_applicable, task_id {"integrity":1,"not_applicable":true,"task_id":"polyglot/python-reverse-string"}
composite composite, weights, components, note {"composite":0.8513087626540672,"weights":{"pass_rate":0.4,"integrity":0.2,"cost":0.15,"latency":0.15,"blast_radius":0.1},"components":{"pass_rate":1,"integrity":1,"blast_radius":0.8333333333333334,"tokens_per_correct_task":0,"wall_clock_ms":49179.029,"expected_refusal":false,"refusal_produced":true,"cost_efficiency":1,"latency_efficiency":0.5642806399160023,"clean_blast":0.16666666666666663,"refusal_factor":1},"note":"Single-cell composite — sweep-level normalisation lives in the runner. MANIFESTO #6: per-axis numbers are canonical; composite is derivative."}

Trace replay

space play/pause · ←/→ step span · ,/. step 100 ms
t = 0 ms / 49.18 s
span d60652077d664f82a1216b9e14c7a592task_setupprepare:polyglot/python-reverse-string0 ms → 1 ms
workdir/home/andrew/.codingagentbench-scratch/codingagentbench-crush-polyglot_python-reverse-string-l3s_pj6d/workdir
task_categorypolyglot
plugin_stack[]
behavior_modefactory

Terminal playback

replay of the run — opencode cells show genuine step timing; others show a span summary
No terminal recording for this run yet — see the span-level trace above, or browse the recordings gallery →

Run it yourself

Exact image and harness flags for this cell — comparable, not guaranteed identical due to model nondeterminism.

Imagecodingagentbench/crush:v0.72.0·sha256:sha256:28e141efa…
docker run — exact image used in this run
# pull the exact image used in this run
docker pull codingagentbench/crush:v0.72.0@sha256:sha256:28e141efa8509cd43fd465b035019d1b35d76e97aec19fc90b08211741c7bbf7

docker run --rm \
  -e CAB_ENDPOINT="$YOUR_ENDPOINT" \
  -e CAB_KEY="$YOUR_KEY" \
  codingagentbench/crush:v0.72.0@sha256:sha256:28e141efa8509cd43fd465b035019d1b35d76e97aec19fc90b08211741c7bbf7 \
  run-cell \
    --tui crush \
    --model stepfun-ai/step-3.5-flash \
    --task polyglot/python-reverse-string

Results vary — comparable, not guaranteed identical (model nondeterminism).

Explore with your own model

Substitute your endpoint, key, and model ID. Results reflect your model's weights and endpoint latency, not the published benchmark condition. Endpoint must speak OpenAI-compatible /v1/chat/completions.

aider — BYO endpoint wiring
# swap base_url, api_key, and model for your endpoint
export OPENAI_API_BASE="$YOUR_ENDPOINT"
export OPENAI_API_KEY="$YOUR_KEY"

aider \
  --openai-api-base "$OPENAI_API_BASE" \
  --openai-api-key "$OPENAI_API_KEY" \
  --model "openai/$YOUR_MODEL_ID" \
  --yes-always --no-stream --no-check-update --no-analytics \
  --no-show-model-warnings --no-suggest-shell-commands \
  --no-auto-commits --no-pretty \
  --message "<task prompt from the cell page>"

# Published cell used model: stepfun-ai/step-3.5-flash
Zero-install preview — npx CLI (provisional, not for citation)
npx @codingagentbench/cli check
npx @codingagentbench/cli check \
  --tui crush \
  --model stepfun-ai/step-3.5-flash \
  --endpoint "$YOUR_ENDPOINT" \
  --key "$YOUR_KEY" \
  --task polyglot/python-reverse-string
# provisional score — not for citation

Provisional score — not for citation. Use the Docker or Harness CLI path for citable results.

Trace spans (5)

Span Kind Name Duration Attrs / Error
d60652077d664f82a1216b9e14c7a592 task_setup prepare:polyglot/python-reverse-string 1 ms {"workdir":"/home/andrew/.codingagentbench-scratch/codingagentbench-crush-polyglot_python-reverse-string-l3s_pj6d/workdir","task_category":"polyglot","plugin_stack":[],"behavior_mode":"factory"}
4839e8d3ad724d7a8e49c52834e6feb2 ↳ 6a666c94ba56430c931613ee31fe887f tool_call applied_plugins 0 ms {"tui":"crush","count":0,"applied":[],"env_keys":[],"extra_args":[],"applied_count":0,"skipped_count":0}
1b678043ce2745ab8281df363db24cdf ↳ 6a666c94ba56430c931613ee31fe887f container crush-run:polyglot/python-reverse-string 49178 ms {"image":"codingagentbench/crush:v0.72.0","model":"stepfun-ai/step-3.5-flash","base_url":"http://172.17.0.1:31415/v1","exit_code":1,"duration_s":49.163,"timed_out":false,"image_digest":"sha256:28e141efa8509cd43fd465b035019d1b35d76e97aec19fc90b08211741c7bbf7"}
6a666c94ba56430c931613ee31fe887f adapter_run crush:polyglot/python-reverse-string 49178 ms {"timeout_s":600,"plugin_stack":[],"exit_code":1}
9e02a1a12e8644e094b386c6ef8021c2 cleanup cleanup:crush 0 ms {}

Model calls (0)

# Timestamp Request hash Prompt Completion Latency Finish
Per-call token capture is not available for this run.

Other CLIs on this task

Other models with this CLI

Other tasks in this category

Embed this result
README / Markdown
[![CodingAgentBench: crush × stepfun-ai/step-3.5-flash 85%](https://codingagentbench.com/badge/crush/stepfun-ai/step-3.5-flash/polyglot/python-reverse-string.svg)](https://codingagentbench.com/cell/crush/stepfun-ai/step-3.5-flash/polyglot/python-reverse-string)
HTML / iframe
<a href="https://codingagentbench.com/cell/crush/stepfun-ai/step-3.5-flash/polyglot/python-reverse-string"><img src="https://codingagentbench.com/badge/crush/stepfun-ai/step-3.5-flash/polyglot/python-reverse-string.svg" alt="CodingAgentBench: crush × stepfun-ai/step-3.5-flash 85%" /></a>
CodingAgentBench: crush × stepfun-ai/step-3.5-flash 85%