[
  {
    "benchmark": "swe-bench",
    "score": 73.4,
    "metric": "accuracy",
    "cost_per_instance": 1.06,
    "average_runtime": 1435.0,
    "full_archive": "https://results.eval.all-hands.dev/swebench/litellm_proxy-openrouter-z-ai-glm-5/22118959539/results.tar.gz",
    "tags": [
      "swe-bench"
    ],
    "agent_version": "v1.11.5",
    "submission_time": "2026-02-18T19:24:52+00:00",
    "eval_visualization_page": "https://laminar.sh/shared/evals/58f92ff8-e886-40ab-a636-8337fc8c9bfe"
  },
  {
    "benchmark": "commit0",
    "score": 31.2,
    "metric": "accuracy",
    "cost_per_instance": 2.23,
    "average_runtime": 1725.0,
    "full_archive": "https://results.eval.all-hands.dev/commit0/litellm_proxy-openrouter-z-ai-glm-5/25008748071/results.tar.gz",
    "tags": [
      "commit0"
    ],
    "agent_version": "v1.17.0",
    "submission_time": "2026-04-27T22:07:02+00:00",
    "eval_visualization_page": "https://laminar.sh/shared/evals/76ea5306-b580-47c0-a9ad-67a1c995bfba"
  },
  {
    "benchmark": "swt-bench",
    "score": 47.3,
    "metric": "accuracy",
    "cost_per_instance": 0.91,
    "average_runtime": 1085.0,
    "full_archive": "https://results.eval.all-hands.dev/swtbench/litellm_proxy-openrouter-z-ai-glm-5/22240291718/results.tar.gz",
    "tags": [
      "swt-bench"
    ],
    "agent_version": "v1.11.5",
    "submission_time": "2026-02-21T09:26:31+00:00",
    "eval_visualization_page": "https://laminar.sh/shared/evals/a7d29286-6810-4ca8-8a11-21d6ae33822b"
  },
  {
    "benchmark": "gaia",
    "score": 60.0,
    "metric": "accuracy",
    "cost_per_instance": 0.36,
    "average_runtime": 1328.0,
    "full_archive": "https://results.eval.all-hands.dev/gaia/litellm_proxy-openrouter-z-ai-glm-5/22117141473/results.tar.gz",
    "tags": [
      "gaia"
    ],
    "agent_version": "v1.11.5",
    "submission_time": "2026-02-18T03:25:43+00:00",
    "eval_visualization_page": "https://laminar.sh/shared/evals/c37cd7c9-3839-402d-bdf6-a0c10c4c085b"
  },
  {
    "benchmark": "swe-bench-multimodal",
    "score": 35.3,
    "metric": "solveable_accuracy",
    "cost_per_instance": 0.58,
    "average_runtime": 1140.0,
    "full_archive": "https://results.eval.all-hands.dev/swebenchmultimodal/litellm_proxy-openrouter-z-ai-glm-5/22881368139/results.tar.gz",
    "tags": [
      "swe-bench-multimodal"
    ],
    "agent_version": "v1.11.5",
    "submission_time": "2026-03-10T15:12:57+00:00",
    "component_scores": {
      "solveable_accuracy": 35.3,
      "unsolveable_accuracy": 8.8,
      "combined_accuracy": 26.5
    },
    "eval_visualization_page": "https://laminar.sh/shared/evals/756a9904-f7f3-4c23-a663-8a7dd853d6dd"
  }
]