{
    "metadata": {
        "benchmark": "Vibe Code Bench 1-100 v1.1",
        "slug": "vcb-1-100-v1-1",
        "description": "Can models extend a working web application across a long sequence of dependent requests?",
        "benchmark_id": "vcb_1_100_v1_1",
        "family": "vcb_1_100",
        "version": "1.1",
        "updated": "2026-11-13",
        "dataset_type": "private",
        "industry": "coding",
        "tasks": {
            "overall": "Overall"
        },
        "models": [
            "anthropic/claude-opus-5-5",
            "deepseek/deepseek-v4.1-flash-1017",
            "google/gemini-4-carbon",
            "grok/grok-4.7",
            "minimax/MiniMax-M3.1-flash",
            "xiaomi/mimo-v2.6-flash",
            "xiaomi/mimo-v2.6-pro",
            "zai/glm-5.3"
        ],
        "partners": [],
        "showBadge": false,
        "visible": true,
        "use_cost_per_test": true,
        "token_tasks_measured": 50,
        "runner": "external",
        "mode": "agentic",
        "archived": false,
        "partner": false,
        "total_models": 8
    },
    "tasks": {
        "overall": {
            "google/gemini-4-carbon": {
                "accuracy": 49.733,
                "latency": 14811.867,
                "stderr": 4.911,
                "cost_per_test": 57.920793,
                "token_totals": {
                    "input_tokens": 2292758253,
                    "output_tokens": 44964034,
                    "reasoning_tokens": 10221370,
                    "cache_read_tokens": 1887966848,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 1048576,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": "OpenHands"
            },
            "anthropic/claude-opus-5-5": {
                "accuracy": 30.95,
                "latency": 24382.305,
                "stderr": 3.594,
                "cost_per_test": 115.100768,
                "token_totals": {
                    "input_tokens": 3855329877,
                    "output_tokens": 146171531,
                    "reasoning_tokens": 83885330,
                    "cache_read_tokens": 3426285932,
                    "cache_write_tokens": 428953790
                },
                "token_tasks_measured": 50,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": "OpenHands"
            },
            "zai/glm-5.3": {
                "accuracy": 29.75,
                "latency": 6099.942,
                "stderr": 4.326,
                "cost_per_test": 13.443888,
                "token_totals": {
                    "input_tokens": 1582626154,
                    "output_tokens": 26764775,
                    "reasoning_tokens": 16750547,
                    "cache_read_tokens": 1457234423,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 131072,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Fireworks AI",
                "harness": "OpenHands"
            },
            "xiaomi/mimo-v2.6-pro": {
                "accuracy": 26.411,
                "latency": 11017.089,
                "stderr": 4.205,
                "cost_per_test": 1.32472,
                "token_totals": {
                    "input_tokens": 1113373609,
                    "output_tokens": 19288011,
                    "reasoning_tokens": 12468292,
                    "cache_read_tokens": 1008025216,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Xiaomi",
                "harness": "OpenHands"
            },
            "grok/grok-4.7": {
                "accuracy": 26.35,
                "latency": 13074.345,
                "stderr": 4.223,
                "cost_per_test": 41.710712,
                "token_totals": {
                    "input_tokens": 2331618201,
                    "output_tokens": 53930755,
                    "reasoning_tokens": 36960930,
                    "cache_read_tokens": 1934190208,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": null,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": "OpenHands"
            },
            "deepseek/deepseek-v4.1-flash-1017": {
                "accuracy": 26.15,
                "latency": 6027.931,
                "stderr": 4.135,
                "cost_per_test": 2.682746,
                "token_totals": {
                    "input_tokens": 3198133462,
                    "output_tokens": 42961255,
                    "reasoning_tokens": 25485502,
                    "cache_read_tokens": 2982504319,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": 1.0,
                "top_p": 1.0,
                "max_output_tokens": 384000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "DeepSeek",
                "harness": "OpenHands"
            },
            "xiaomi/mimo-v2.6-flash": {
                "accuracy": 24.5,
                "latency": 9261.386,
                "stderr": 4.058,
                "cost_per_test": 0.441904,
                "token_totals": {
                    "input_tokens": 1127487673,
                    "output_tokens": 17067970,
                    "reasoning_tokens": 9919047,
                    "cache_read_tokens": 1024286400,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Xiaomi",
                "harness": "OpenHands"
            },
            "minimax/MiniMax-M3.1-flash": {
                "accuracy": 19.833,
                "latency": 16842.587,
                "stderr": 3.58,
                "cost_per_test": 3.716478,
                "token_totals": {
                    "input_tokens": 4910306633,
                    "output_tokens": 97508579,
                    "reasoning_tokens": 65515353,
                    "cache_read_tokens": 4512794403,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 262144,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "MiniMax",
                "harness": "OpenHands"
            }
        }
    }
}
