✨ Add swe-bench-pro--ansible-qwen3-6-35b-nvfp4-opencode
Browse files
results/swe-bench-pro--ansible-qwen3-6-35b-nvfp4-opencode.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"benchmark": {
|
| 3 |
+
"name": "swe-bench-pro--ansible",
|
| 4 |
+
"repo": "ScaleAI/SWE-bench_Pro",
|
| 5 |
+
"num_tasks": 96,
|
| 6 |
+
"url": "https://huggingface.co/datasets/ScaleAI/SWE-bench_Pro"
|
| 7 |
+
},
|
| 8 |
+
"harness": {
|
| 9 |
+
"name": "OpenCode",
|
| 10 |
+
"skills": [],
|
| 11 |
+
"is_oss": true,
|
| 12 |
+
"url": "https://github.com/anomalyco/opencode"
|
| 13 |
+
},
|
| 14 |
+
"model": {
|
| 15 |
+
"name": "Qwen3.6-35B-A3B",
|
| 16 |
+
"repo": "RedHatAI/Qwen3.6-35B-A3B-NVFP4",
|
| 17 |
+
"is_oss": true,
|
| 18 |
+
"num_params": 35,
|
| 19 |
+
"precision": "nvfp4",
|
| 20 |
+
"url": "https://huggingface.co/RedHatAI/Qwen3.6-35B-A3B-NVFP4"
|
| 21 |
+
},
|
| 22 |
+
"environment": {
|
| 23 |
+
"name": "harbor",
|
| 24 |
+
"config": {
|
| 25 |
+
"path": null,
|
| 26 |
+
"name": "scale-ai/swe-bench-pro",
|
| 27 |
+
"version": null,
|
| 28 |
+
"ref": "sha256:88411d32ff27e53a4c1a7e29f0c2aeba180c8e5d60f221cab5ed56325f33549d",
|
| 29 |
+
"registry_url": null,
|
| 30 |
+
"registry_path": null,
|
| 31 |
+
"overwrite": false,
|
| 32 |
+
"download_dir": null,
|
| 33 |
+
"task_names": [
|
| 34 |
+
"*ansible*"
|
| 35 |
+
],
|
| 36 |
+
"exclude_task_names": null,
|
| 37 |
+
"n_tasks": null
|
| 38 |
+
},
|
| 39 |
+
"url": "https://github.com/harbor-framework/harbor"
|
| 40 |
+
},
|
| 41 |
+
"metrics": {
|
| 42 |
+
"n_tasks": 96,
|
| 43 |
+
"n_errors": 4,
|
| 44 |
+
"score": 0.375,
|
| 45 |
+
"n_input_tokens": 207164679,
|
| 46 |
+
"n_cache_tokens": 0,
|
| 47 |
+
"n_output_tokens": 1598703,
|
| 48 |
+
"n_total_tokens": 208763382,
|
| 49 |
+
"agent_time_seconds": 49450,
|
| 50 |
+
"total_time_seconds": 57287,
|
| 51 |
+
"cost_usd": 12.21,
|
| 52 |
+
"mean_input_tokens_per_task": 2157965,
|
| 53 |
+
"mean_cache_tokens_per_task": 0,
|
| 54 |
+
"mean_output_tokens_per_task": 16653,
|
| 55 |
+
"mean_tokens_per_task": 2174618,
|
| 56 |
+
"mean_cost_usd_per_task": 0.13,
|
| 57 |
+
"mean_total_time_seconds_per_task": 596,
|
| 58 |
+
"mean_agent_time_seconds_per_task": 515
|
| 59 |
+
}
|
| 60 |
+
}
|