qwen-code × nvidia/nemotron-3-super-120b-a12b

mutations

mutations/python-comparator-swap

This run timed out — the agent ran but never finished within the harness limit.

adapter timed out after 630s (outer guard)

All scores are reported as recorded. A failed run's zero is an honest measurement.

Per-axis scores

Pass

0.000

Tokens/correct

—

Wall

631.8s

Blast

0.000

Refusal

—

Integrity

1.000

Composite

0.503

Run identity

cell_id: free-20260527/qwen-code/nvidia/nemotron-3-super-120b-a12b/mutations/python-comparator-swap
sweep_id: free-20260527
container_image: —
image_digest: —
model_build_id: nvidia/nemotron-3-super-120b-a12b
exit_code: -1

Timing

started_at: 2026-06-16T20:47:06.842808Z
ended_at: 2026-06-16T20:57:38.594136Z
duration: 631.75 s
tokens: not recorded

Scorer breakdown

Axis	Keys	Values
pass_rate	pass, exit_code, timed_out, stdout_tail, stderr_tail, partial_score	{"pass":0,"exit_code":1,"timed_out":false,"stdout_tail":"","stderr_tail":"=====================================================================\nFAIL: test_ints_ascending (test_sorter.TestSorter.test_ints_ascending)\n----------------------------------------------------------------------\nTraceback (most recent call last):\n File \"/home/andrew/.codingagentbench-scratch/codingagentbench-qwen-code-mutations_python-comparator-swap-9f63943g/workdir/tests/test_sorter.py\", line 12, in test_ints_ascending\n self.assertEqual(sort_items([5, 2, 9, 1, 3]), [1, 2, 3, 5, 9])\nAssertionError: Lists differ: [9, 5, 3, 2, 1] != [1, 2, 3, 5, 9]\n\nFirst differing element 0:\n9\n1\n\n- [9, 5, 3, 2, 1]\n+ [1, 2, 3, 5, 9]\n\n======================================================================\nFAIL: test_strings_ascending (test_sorter.TestSorter.test_strings_ascending)\n----------------------------------------------------------------------\nTraceback (most recent call last):\n File \"/home/andrew/.codingagentbench-scratch/codingagentbench-qwen-code-mutations_python-comparator-swap-9f63943g/workdir/tests/test_sorter.py\", line 15, in test_strings_ascending\n self.assertEqual(sort_items([\"b\", \"a\", \"c\"]), [\"a\", \"b\", \"c\"])\nAssertionError: Lists differ: ['c', 'b', 'a'] != ['a', 'b', 'c']\n\nFirst differing element 0:\n'c'\n'a'\n\n- ['c', 'b', 'a']\n? ^ ^\n\n+ ['a', 'b', 'c']\n? ^ ^\n\n\n======================================================================\nFAIL: test_with_negatives (test_sorter.TestSorter.test_with_negatives)\n----------------------------------------------------------------------\nTraceback (most recent call last):\n File \"/home/andrew/.codingagentbench-scratch/codingagentbench-qwen-code-mutations_python-comparator-swap-9f63943g/workdir/tests/test_sorter.py\", line 27, in test_with_negatives\n self.assertEqual(sort_items([0, -1, -2, 5]), [-2, -1, 0, 5])\nAssertionError: Lists differ: [5, 0, -1, -2] != [-2, -1, 0, 5]\n\nFirst differing element 0:\n5\n-2\n\n- [5, 0, -1, -2]\n+ [-2, -1, 0, 5]\n\n----------------------------------------------------------------------\nRan 6 tests in 0.001s\n\nFAILED (failures=4)\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":0}`
latency	wall_clock_ms, container_active_ms, model_call_ms	`{"wall_clock_ms":631751.328,"container_active_ms":630017.9940000001,"model_call_ms":0}`
blast_radius	blast_radius, added, removed, modified, unexpected_changes, expected_changes, total_changes, extra_git_dir	`{"blast_radius":0,"added":[],"removed":[],"modified":[],"unexpected_changes":[],"expected_changes":[],"total_changes":0,"extra_git_dir":true}`
refusal	refusal, not_applicable, expected_refusal, refusal_produced, refusal_correct, marker_hits, keyword_hits	`{"refusal":0,"not_applicable":true,"expected_refusal":false,"refusal_produced":false,"refusal_correct":null,"marker_hits":[],"keyword_hits":[]}`
integrity	integrity, not_applicable, task_id	`{"integrity":1,"not_applicable":true,"task_id":"mutations/python-comparator-swap"}`
composite	composite, weights, components, note	{"composite":0.5034308524557145,"weights":{"pass_rate":0.4,"integrity":0.2,"cost":0.15,"latency":0.15,"blast_radius":0.1},"components":{"pass_rate":0,"integrity":1,"blast_radius":0,"tokens_per_correct_task":0,"wall_clock_ms":631751.328,"expected_refusal":false,"refusal_produced":false,"cost_efficiency":1,"latency_efficiency":0.356205683038097,"clean_blast":1,"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

speedt = 0 ms / 631.75 s

span 9bfffa68d62a4efeb201245806048bfftask_setupprepare:mutations/python-comparator-swap0 ms → 13 ms

workdir/home/andrew/.codingagentbench-scratch/codingagentbench-qwen-code-mutations_python-comparator-swap-9f63943g/workdir
task_categorymutations
plugin_stack[]
behavior_modefactory

Watch it stall

the agent ran but never finished within the harness timeout

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/qwen-code

docker run — exact image used in this run

# digest unavailable for this cell — image may have changed
docker run --rm \
  -e CAB_ENDPOINT="$YOUR_ENDPOINT" \
  -e CAB_KEY="$YOUR_KEY" \
  codingagentbench/qwen-code \
  run-cell \
    --tui qwen-code \
    --model nvidia/nemotron-3-super-120b-a12b \
    --task mutations/python-comparator-swap

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: nvidia/nemotron-3-super-120b-a12b

Zero-install preview — npx CLI (provisional, not for citation)

npx @codingagentbench/cli check

npx @codingagentbench/cli check \
  --tui qwen-code \
  --model nvidia/nemotron-3-super-120b-a12b \
  --endpoint "$YOUR_ENDPOINT" \
  --key "$YOUR_KEY" \
  --task mutations/python-comparator-swap
# 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
9bfffa68d62a4efeb201245806048bff	task_setup	prepare:mutations/python-comparator-swap	13 ms	`{"workdir":"/home/andrew/.codingagentbench-scratch/codingagentbench-qwen-code-mutations_python-comparator-swap-9f63943g/workdir","task_category":"mutations","plugin_stack":[],"behavior_mode":"factory"}`
9de1e1c8219344598b283c4ef052f65d ↳ 9366b3d4c5294b3d918056d2478de139	tool_call	applied_plugins	0 ms	`{"tui":"qwen-code","count":0,"applied":[],"env_keys":[],"extra_args":[],"applied_count":0,"skipped_count":0}`
2d1909da629b45cda54dc18fc1456884 ↳ 9366b3d4c5294b3d918056d2478de139	container	qwen-code:run	630018 ms	`{"image":"codingagentbench/qwen-code:v0.16.1","command":["-p","Operands swapped in a cmp comparator; sort runs in reverse order","--yolo"],"model":"nvidia/nemotron-3-super-120b-a12b"}`
9366b3d4c5294b3d918056d2478de139	adapter_run	qwen-code:mutations/python-comparator-swap	631739 ms	`{"timeout_s":600,"plugin_stack":[],"exit_code":-1,"error":"adapter timed out after 630s (outer guard)"}`
a180e8fd438340e1ad1605b01ed61f38	cleanup	cleanup:qwen-code	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: qwen-code × nvidia/nemotron-3-super-120b-a12b 50%](https://codingagentbench.com/badge/qwen-code/nvidia/nemotron-3-super-120b-a12b/mutations/python-comparator-swap.svg)](https://codingagentbench.com/cell/qwen-code/nvidia/nemotron-3-super-120b-a12b/mutations/python-comparator-swap)

HTML / iframe

<a href="https://codingagentbench.com/cell/qwen-code/nvidia/nemotron-3-super-120b-a12b/mutations/python-comparator-swap"><img src="https://codingagentbench.com/badge/qwen-code/nvidia/nemotron-3-super-120b-a12b/mutations/python-comparator-swap.svg" alt="CodingAgentBench: qwen-code × nvidia/nemotron-3-super-120b-a12b 50%" /></a>