Skip to main content
CodingAgentBench

crush × nvidia/nemotron-3-super-120b-a12b

mutations
mutations/java-null-deref

Per-axis scores

Pass
1.000
Tokens/correct
—
Wall
108.7s
Blast
0.833
Refusal
—
Integrity
1.000
Composite
0.839

Run identity

cell_id
free-20260527/crush/nvidia/nemotron-3-super-120b-a12b/mutations/java-null-deref
sweep_id
free-20260527
container_image
codingagentbench/crush:v0.72.0
image_digest
sha256:28e141efa8509cd43fd465b035019d1b35d76e97aec19fc90b08211741c7bbf7
model_build_id
nvidia/nemotron-3-super-120b-a12b
exit_code
1

Timing

started_at
2026-06-16T16:31:41.868652Z
ended_at
2026-06-16T16:33:30.539053Z
duration
108.67 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":"ok values win over defaults\nok fallback to defaults\nok missing returns null\nok nullDefaultsReturnsNull\nok values still work with null defaults\nok null values, key in defaults\nok null values, missing key\nall tests passed\n","stderr_tail":"","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":108670.401,"container_active_ms":108668.58600000001,"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/Config.java"],"unexpected_changes":[".crush-xdg/crush/crush.json",".crush/.gitignore",".crush/crush.db",".crush/crush.json",".crush/logs/crush.log"],"expected_changes":["src/Config.java"],"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":false,"refusal_correct":null,"marker_hits":[],"keyword_hits":[]}
integrity integrity, not_applicable, task_id {"integrity":1,"not_applicable":true,"task_id":"mutations/java-null-deref"}
composite composite, weights, components, note {"composite":0.8389787397769024,"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":108670.401,"expected_refusal":false,"refusal_produced":false,"cost_efficiency":1,"latency_efficiency":0.4820804874015709,"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 / 108.67 s
span f217589dc7ee491dba5d7f10dcf166e2task_setupprepare:mutations/java-null-deref0 ms → 1 ms
workdir/home/andrew/.codingagentbench-scratch/codingagentbench-crush-mutations_java-null-deref-dm0mhtq3/workdir
task_categorymutations
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 nvidia/nemotron-3-super-120b-a12b \
    --task mutations/java-null-deref

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 crush \
  --model nvidia/nemotron-3-super-120b-a12b \
  --endpoint "$YOUR_ENDPOINT" \
  --key "$YOUR_KEY" \
  --task mutations/java-null-deref
# 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
f217589dc7ee491dba5d7f10dcf166e2 task_setup prepare:mutations/java-null-deref 1 ms {"workdir":"/home/andrew/.codingagentbench-scratch/codingagentbench-crush-mutations_java-null-deref-dm0mhtq3/workdir","task_category":"mutations","plugin_stack":[],"behavior_mode":"factory"}
ae2aed55c0aa42b99ab56e6cfb9e7d8b ↳ 0f0ece15129f42838e73e1e00ff26219 tool_call applied_plugins 0 ms {"tui":"crush","count":0,"applied":[],"env_keys":[],"extra_args":[],"applied_count":0,"skipped_count":0}
980f11a38cba44d695346f9f128cf3e3 ↳ 0f0ece15129f42838e73e1e00ff26219 container crush-run:mutations/java-null-deref 108669 ms {"image":"codingagentbench/crush:v0.72.0","model":"nvidia/nemotron-3-super-120b-a12b","base_url":"http://172.17.0.1:31415/v1","exit_code":1,"duration_s":108.644,"timed_out":false,"image_digest":"sha256:28e141efa8509cd43fd465b035019d1b35d76e97aec19fc90b08211741c7bbf7"}
0f0ece15129f42838e73e1e00ff26219 adapter_run crush:mutations/java-null-deref 108669 ms {"timeout_s":600,"plugin_stack":[],"exit_code":1}
9ae83d8b154f439c8b1ab46430c8d93f cleanup cleanup:crush 1 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 × nvidia/nemotron-3-super-120b-a12b 84%](https://codingagentbench.com/badge/crush/nvidia/nemotron-3-super-120b-a12b/mutations/java-null-deref.svg)](https://codingagentbench.com/cell/crush/nvidia/nemotron-3-super-120b-a12b/mutations/java-null-deref)
HTML / iframe
<a href="https://codingagentbench.com/cell/crush/nvidia/nemotron-3-super-120b-a12b/mutations/java-null-deref"><img src="https://codingagentbench.com/badge/crush/nvidia/nemotron-3-super-120b-a12b/mutations/java-null-deref.svg" alt="CodingAgentBench: crush × nvidia/nemotron-3-super-120b-a12b 84%" /></a>
CodingAgentBench: crush × nvidia/nemotron-3-super-120b-a12b 84%