Skip to main content
Glama
benchmark_20250812_142029.json2.86 kB
{ "prompt": "Compare these models", "models": [ "openai/gpt-4", "anthropic/claude-3-opus" ], "results": { "openai/gpt-4": [ { "model_id": "openai/gpt-4", "prompt": "Compare these models", "response": "GPT-4 response", "response_time_ms": 0.2880096435546875, "tokens_used": 30, "cost": 0.0, "timestamp": "2025-08-12T14:20:27.824997+00:00", "error": null, "prompt_tokens": null, "completion_tokens": null, "input_cost_per_1k_tokens": null, "output_cost_per_1k_tokens": null, "quality_score": null, "response_length": null, "contains_code_example": null, "language_coherence_score": null, "throughput_tokens_per_second": null } ], "anthropic/claude-3-opus": [ { "model_id": "anthropic/claude-3-opus", "prompt": "Compare these models", "response": "Claude response", "response_time_ms": 0.6499290466308594, "tokens_used": 25, "cost": 0.0, "timestamp": "2025-08-12T14:20:28.839926+00:00", "error": null, "prompt_tokens": null, "completion_tokens": null, "input_cost_per_1k_tokens": null, "output_cost_per_1k_tokens": null, "quality_score": null, "response_length": null, "contains_code_example": null, "language_coherence_score": null, "throughput_tokens_per_second": null } ] }, "metrics": { "openai/gpt-4": { "avg_response_time_ms": 0.2880096435546875, "avg_tokens_used": 30.0, "avg_cost": 0.0, "total_cost": 0.0, "success_rate": 1.0, "sample_count": 1, "avg_quality_score": null, "avg_throughput": null, "avg_prompt_tokens": null, "avg_completion_tokens": null, "cost_per_quality_point": null }, "anthropic/claude-3-opus": { "avg_response_time_ms": 0.6499290466308594, "avg_tokens_used": 25.0, "avg_cost": 0.0, "total_cost": 0.0, "success_rate": 1.0, "sample_count": 1, "avg_quality_score": null, "avg_throughput": null, "avg_prompt_tokens": null, "avg_completion_tokens": null, "cost_per_quality_point": null } }, "rankings": { "speed": [ { "model": "openai/gpt-4", "metric": 0.2880096435546875, "unit": "ms" }, { "model": "anthropic/claude-3-opus", "metric": 0.6499290466308594, "unit": "ms" } ], "cost": [], "reliability": [ { "model": "openai/gpt-4", "metric": 100.0, "unit": "%" }, { "model": "anthropic/claude-3-opus", "metric": 100.0, "unit": "%" } ] }, "timestamp": "2025-08-12T14:20:29.842057+00:00" }

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/physics91/openrouter-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server