← Back to matrix · All model evidence for this question

piq50v2_cyclic_symbols × Qwen 2.5 14B ✓ PASS

BENCHMARK QUESTION

Question ID

piq50v2_cyclic_symbols

Prompt

A marker cycles through positions North, East, South, West, then repeats. It is North at step 1. Where is it at step 8?

Options

—

GOLD / BENCHMARK TRUTH

Raw expected value

West

Evaluation rule type

normalized_exact

Raw evaluation rule

{
  "expected": "West",
  "type": "normalized_exact"
}

CANDIDATE / MODEL OBSERVATION

Model display name

Qwen 2.5 14B

Model ID

qwen2.5-14b

Raw model response

West

Execution status

success

Structured output

—

Model configuration

{
  "adapter": "transformers_local",
  "base_url": null,
  "device": "cuda",
  "dtype": "auto",
  "extra_headers": {},
  "generation": {
    "do_sample": false
  },
  "id": "qwen2.5-14b",
  "local_files_only": true,
  "max_new_tokens": 32,
  "model": "[local-model-path-redacted]/qwen2.5-14b",
  "quantization_method": null,
  "secret_env": null,
  "supports_json_mode": false,
  "timeout": 60
}

EVALUATION RESULT

Result

PASS

Stored evaluation status

passed

Score

1.0

gate_status

pass

conclusive

true

evaluator_name

pegasus.normalized_exact

evaluator_version

rule_type

normalized_exact

Reason

deterministic rule satisfied

Evaluator error

—

GRADER EVIDENCE

evaluation.evidence

{
  "actual_normalized": "west",
  "expected_normalized": "west"
}

EXECUTION EVIDENCE

effective_candidate_prompt

A marker cycles through positions North, East, South, West, then repeats. It is North at step 1. Where is it at step 8?

Return only the final answer. Do not include explanation or reasoning.

Return only the final answer. Do not include explanation.

benchmark_prompt

A marker cycles through positions North, East, South, West, then repeats. It is North at step 1. Where is it at step 8?

latency_ms

58.09747199236881

usage

{
  "input_tokens": 85,
  "output_tokens": 2
}

provider_metadata

{
  "adapter": "transformers_local",
  "cuda_version": "12.8",
  "device": "cuda",
  "dtype": "auto",
  "generation_latency_ms": 57.609904994023964,
  "gpu_compute_capability": [
    12,
    0
  ],
  "gpu_name": "NVIDIA GeForce RTX 5090",
  "model": "[local-model-path-redacted]/qwen2.5-14b",
  "model_load_ms": 71984.59202000231,
  "peak_cuda_memory_allocated_bytes": 29576930816,
  "provider": "transformers_local",
  "torch_version": "2.9.0+cu128",
  "transformers_version": "4.51.3"
}

timestamp

2026-08-25T18:06:38.638366+00:00

response_id

dc41f8bcdcf6477f86ff27c2f3ee3085

run_id

88792604e7e84090a9746aa06ff4ea8b

Execution error

—

Run artifact directory

runs/pattern-iq/qwen-2.5-14b

Raw stored response

{
  "benchmark_prompt": "A marker cycles through positions North, East, South, West, then repeats. It is North at step 1. Where is it at step 8?",
  "effective_candidate_prompt": "A marker cycles through positions North, East, South, West, then repeats. It is North at step 1. Where is it at step 8?\n\nReturn only the final answer. Do not include explanation or reasoning.\n\nReturn only the final answer. Do not include explanation.",
  "error": null,
  "execution_status": "success",
  "latency_ms": 58.09747199236881,
  "model_id": "qwen2.5-14b",
  "provider_metadata": {
    "adapter": "transformers_local",
    "cuda_version": "12.8",
    "device": "cuda",
    "dtype": "auto",
    "generation_latency_ms": 57.609904994023964,
    "gpu_compute_capability": [
      12,
      0
    ],
    "gpu_name": "NVIDIA GeForce RTX 5090",
    "model": "[local-model-path-redacted]/qwen2.5-14b",
    "model_load_ms": 71984.59202000231,
    "peak_cuda_memory_allocated_bytes": 29576930816,
    "provider": "transformers_local",
    "torch_version": "2.9.0+cu128",
    "transformers_version": "4.51.3"
  },
  "question_id": "piq50v2_cyclic_symbols",
  "response_id": "dc41f8bcdcf6477f86ff27c2f3ee3085",
  "run_id": "88792604e7e84090a9746aa06ff4ea8b",
  "structured_output": null,
  "text": "West",
  "timestamp": "2026-08-25T18:06:38.638366+00:00",
  "usage": {
    "input_tokens": 85,
    "output_tokens": 2
  }
}

Raw stored evaluation

{
  "conclusive": true,
  "error": null,
  "evaluator_name": "pegasus.normalized_exact",
  "evaluator_version": "1",
  "evidence": {
    "actual_normalized": "west",
    "expected_normalized": "west"
  },
  "gate_status": "pass",
  "reason": "deterministic rule satisfied",
  "response_id": "dc41f8bcdcf6477f86ff27c2f3ee3085",
  "rule_type": "normalized_exact",
  "score": 1.0,
  "status": "passed"
}