Skip to main content
CodingAgentBench

openhands × meta/llama-4-maverick-17b-128e-instruct

polyglot
polyglot/python-two-sum

Per-axis scores

Pass
0.000
Tokens/correct
—
Wall
12.8s
Blast
0.000
Refusal
—
Integrity
1.000
Composite
0.560

Run identity

cell_id
expansion-20260616/openhands/meta/llama-4-maverick-17b-128e-instruct/polyglot/python-two-sum
sweep_id
expansion-20260616
container_image
codingagentbench/openhands:1.7.0
image_digest
sha256:7fcaf222644a5cb0afffe018f038d270130b5af3b8af366cd960f2d596a4342c
model_build_id
meta/llama-4-maverick-17b-128e-instruct
exit_code
0

Timing

started_at
2026-06-17T07:14:20.257000Z
ended_at
2026-06-17T07:14:33.104461Z
duration
12.85 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":"est_middle\n self.assertEqual(two_sum([3, 2, 4], 6), (1, 2))\nAssertionError: Tuples differ: (0, 0) != (1, 2)\n\nFirst differing element 0:\n0\n1\n\n- (0, 0)\n+ (1, 2)\n\n======================================================================\nFAIL: test_same_value_two_indices (test_two_sum.TestTwoSum.test_same_value_two_indices)\n----------------------------------------------------------------------\nTraceback (most recent call last):\n File \"/home/andrew/.codingagentbench-scratch/codingagentbench-openhands-polyglot_python-two-sum-1rs2vlnl/workdir/tests/test_two_sum.py\", line 22, in test_same_value_two_indices\n self.assertEqual(two_sum([3, 3], 6), (0, 1))\nAssertionError: Tuples differ: (0, 0) != (0, 1)\n\nFirst differing element 1:\n0\n1\n\n- (0, 0)\n? ^\n\n+ (0, 1)\n? ^\n\n\n======================================================================\nFAIL: test_target_double_unique_element (test_two_sum.TestTwoSum.test_target_double_unique_element)\n----------------------------------------------------------------------\nTraceback (most recent call last):\n File \"/home/andrew/.codingagentbench-scratch/codingagentbench-openhands-polyglot_python-two-sum-1rs2vlnl/workdir/tests/test_two_sum.py\", line 26, in test_target_double_unique_element\n self.assertIsNone(two_sum([4], 8))\nAssertionError: (0, 0) is not None\n\n======================================================================\nFAIL: test_target_double_with_other_pair (test_two_sum.TestTwoSum.test_target_double_with_other_pair)\n----------------------------------------------------------------------\nTraceback (most recent call last):\n File \"/home/andrew/.codingagentbench-scratch/codingagentbench-openhands-polyglot_python-two-sum-1rs2vlnl/workdir/tests/test_two_sum.py\", line 30, in test_target_double_with_other_pair\n self.assertEqual(two_sum([4, 1, 7], 8), (1, 2))\nAssertionError: Tuples differ: (0, 0) != (1, 2)\n\nFirst differing element 0:\n0\n1\n\n- (0, 0)\n+ (1, 2)\n\n----------------------------------------------------------------------\nRan 8 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":12847.461,"container_active_ms":12846.726999999999,"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":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":"polyglot/python-two-sum"}
composite composite, weights, components, note {"composite":0.5603884393192954,"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":12847.461,"expected_refusal":false,"refusal_produced":false,"cost_efficiency":1,"latency_efficiency":0.7359229287953031,"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
t = 0 ms / 12.85 s
span 5c9e0f5c217d466ead4e5d7eae66b01dadapter_runopenhands:polyglot/python-two-sum0 ms → 12.85 s
timeout_s600
plugin_stack[]
exit_code0

Terminal playback

replay of the run — opencode cells show genuine step timing; others show a span summary

Run it yourself

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

Imagecodingagentbench/openhands:1.7.0·sha256:sha256:7fcaf2226…
docker run — exact image used in this run
# pull the exact image used in this run
docker pull codingagentbench/openhands:1.7.0@sha256:sha256:7fcaf222644a5cb0afffe018f038d270130b5af3b8af366cd960f2d596a4342c

docker run --rm \
  -e CAB_ENDPOINT="$YOUR_ENDPOINT" \
  -e CAB_KEY="$YOUR_KEY" \
  codingagentbench/openhands:1.7.0@sha256:sha256:7fcaf222644a5cb0afffe018f038d270130b5af3b8af366cd960f2d596a4342c \
  run-cell \
    --tui openhands \
    --model meta/llama-4-maverick-17b-128e-instruct \
    --task polyglot/python-two-sum

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: meta/llama-4-maverick-17b-128e-instruct
Zero-install preview — npx CLI (provisional, not for citation)
npx @codingagentbench/cli check
npx @codingagentbench/cli check \
  --tui openhands \
  --model meta/llama-4-maverick-17b-128e-instruct \
  --endpoint "$YOUR_ENDPOINT" \
  --key "$YOUR_KEY" \
  --task polyglot/python-two-sum
# 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
acee8437c2234d949cd8908ea715d267 task_setup prepare:polyglot/python-two-sum 0 ms {"workdir":"/home/andrew/.codingagentbench-scratch/codingagentbench-openhands-polyglot_python-two-sum-1rs2vlnl/workdir","task_category":"polyglot","plugin_stack":[],"behavior_mode":"factory"}
5f8a4e029a0d439ba6d2b441ee2053b9 ↳ 5c9e0f5c217d466ead4e5d7eae66b01d tool_call applied_plugins 0 ms {"tui":"openhands","count":0,"applied":[],"env_keys":[],"extra_args":[],"applied_count":0,"skipped_count":0}
bddb9f68193140d298dc3422c0ca89bf ↳ 5c9e0f5c217d466ead4e5d7eae66b01d container openhands:run 12847 ms {"image":"codingagentbench/openhands:1.7.0","command":["/app/.venv/bin/python","/opt/openhands_run.py","-t","Find two indices summing to target; broken hash-map walk returns the same index twice","--workspace","/workspace"],"deviation":"root+docker.sock; see module docstring","exit_code":0,"timed_out":false,"docker_sock_mounted":true,"read_only":false}
5c9e0f5c217d466ead4e5d7eae66b01d adapter_run openhands:polyglot/python-two-sum 12847 ms {"timeout_s":600,"plugin_stack":[],"exit_code":0}
9c74c653d2f8400d895f24e7137b3d77 cleanup cleanup:openhands 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: openhands × meta/llama-4-maverick-17b-128e-instruct 56%](https://codingagentbench.com/badge/openhands/meta/llama-4-maverick-17b-128e-instruct/polyglot/python-two-sum.svg)](https://codingagentbench.com/cell/openhands/meta/llama-4-maverick-17b-128e-instruct/polyglot/python-two-sum)
HTML / iframe
<a href="https://codingagentbench.com/cell/openhands/meta/llama-4-maverick-17b-128e-instruct/polyglot/python-two-sum"><img src="https://codingagentbench.com/badge/openhands/meta/llama-4-maverick-17b-128e-instruct/polyglot/python-two-sum.svg" alt="CodingAgentBench: openhands × meta/llama-4-maverick-17b-128e-instruct 56%" /></a>
CodingAgentBench: openhands × meta/llama-4-maverick-17b-128e-instruct 56%