{ "updatedAt": "2026-09-29T03:17:38.971Z", "source": "openrouter-models-api", "rankingVersion": "2026-09-29.v1", "probeMode": "active", "refreshMode": "fullEval", "liteEvalMode": "active", "liteEvalSuite": "lite-agent-eval-v1", "rankingConfidence": "high", "rankingConfidenceReason": "No unevaluated candidate can overtake the primary even with a perfect lite eval score.", "evalCoverage": { "evaluated": 2, "completedToday": 2, "attemptedToday": 2, "totalRanked": 19, "candidatePool": 19, "unevaluatedCanStillWin": false, "unevaluatedThreatCount": 0, "topUnevaluatedThreat": null, "maxUnevaluatedPossibleScore": null }, "baseUrl": "https://openrouter.ai/api/v1", "createKeyUrl": "https://openrouter.ai/settings/keys", "fallback": { "id": "openrouter/free", "reason": "OpenRouter-managed free model router" }, "count": 6, "models": [ { "rank": 1, "id": "dots-studio/dots-3-note-preview:free", "name": "Dots Studio: Dots3-Note Preview (free)", "score": 1560, "metadataScore": 585, "healthScore": 250, "latencyScore": 75, "liteEvalScore": 650, "contextLength": 512000, "maxCompletionTokens": 460800, "supportsTools": true, "supportsToolChoice": true, "supportsStructuredOutputs": true, "supportsResponseFormat": true, "supportsReasoning": true, "supportsIncludeReasoning": true, "supportsSeed": false, "supportsStop": false, "latencyMs": 652, "healthStatus": "imperfect", "evalSuite": "lite-agent-eval-v1", "evalSummary": { "suite": "lite-agent-eval-v1", "status": "completed", "passed": 2, "total": 3, "updatedAt": "2026-09-29T03:17:38.971Z", "tasks": [ { "id": "task_files_lite", "source": "pinchbench/task_files", "points": 350, "maxPoints": 350, "score": 1, "status": "passed", "details": { "usedTool": true, "mainPyCreated": true, "helloPython": true, "readmeCreated": true, "readmeHasTitle": true, "gitignoreCreated": true, "gitignoreHasPycache": true, "noUnsafePaths": true } }, { "id": "task_shell_command_lite", "source": "pinchbench/task_shell_command_generator", "points": 300, "maxPoints": 300, "score": 1, "status": "passed", "details": { "command": "find . -name \"*.log\" -exec grep -l \"FATAL:\" {} +", "wroteCommandFile": true, "shellOnly": true, "recursiveSearch": true, "restrictsToLogFiles": true, "matchesFatalExactly": true, "printsEachFileOnce": true, "plausiblyExecutable": true } }, { "id": "babylonian_clock_lite", "source": "shir-man/custom", "points": 0, "maxPoints": 100, "score": 0, "status": "failed", "details": { "expected": "02:12:48", "received": "" } } ] }, "reason": "Tools, structured outputs, reasoning; lite eval 2/3", "instabilityPenalty": 0 }, { "rank": 2, "id": "nvidia/nemotron-3-super-120b-a12b:free", "name": "NVIDIA: Nemotron 3 Super (free)", "score": 1325, "metadataScore": 560, "healthScore": 250, "latencyScore": 20, "liteEvalScore": 495, "contextLength": 262144, "maxCompletionTokens": 235929, "supportsTools": true, "supportsToolChoice": true, "supportsStructuredOutputs": true, "supportsResponseFormat": true, "supportsReasoning": true, "supportsIncludeReasoning": true, "supportsSeed": true, "supportsStop": false, "latencyMs": 6097, "healthStatus": "imperfect", "evalSuite": "lite-agent-eval-v1", "evalSummary": { "suite": "lite-agent-eval-v1", "status": "completed", "passed": 1, "total": 3, "updatedAt": "2026-09-29T03:17:38.971Z", "tasks": [ { "id": "task_files_lite", "source": "pinchbench/task_files", "points": 220, "maxPoints": 350, "score": 0.629, "status": "partial", "details": { "usedTool": true, "mainPyCreated": true, "helloPython": true, "readmeCreated": false, "readmeHasTitle": false, "gitignoreCreated": false, "gitignoreHasPycache": false, "noUnsafePaths": true } }, { "id": "task_shell_command_lite", "source": "pinchbench/task_shell_command_generator", "points": 275, "maxPoints": 300, "score": 0.917, "status": "passed", "details": { "command": "grep -rl 'FATAL:' . --include='*.log'", "wroteCommandFile": true, "shellOnly": true, "recursiveSearch": true, "restrictsToLogFiles": true, "matchesFatalExactly": true, "printsEachFileOnce": false, "plausiblyExecutable": true } }, { "id": "babylonian_clock_lite", "source": "shir-man/custom", "points": 0, "maxPoints": 100, "score": 0, "status": "failed", "details": { "expected": "02:12:48", "received": "We need to decode the time after the em dash. Input: \n\"𒌚𒁹𒁹𒁹𒁹 𒌓𒌋𒌋𒁹𒁹𒁹𒁹" } } ] }, "reason": "Tools, structured outputs, reasoning; lite eval 1/3", "instabilityPenalty": 0 }, { "rank": 3, "id": "qwen/qwen3.8-27b:free", "name": "Qwen: Qwen3.8 27B (free)", "score": 695, "metadataScore": 575, "healthScore": 100, "latencyScore": 20, "liteEvalScore": 0, "contextLength": 262144, "maxCompletionTokens": 235929, "supportsTools": true, "supportsToolChoice": true, "supportsStructuredOutputs": true, "supportsResponseFormat": false, "supportsReasoning": true, "supportsIncludeReasoning": true, "supportsSeed": false, "supportsStop": true, "latencyMs": 5153, "healthStatus": "http_429", "evalSuite": "lite-agent-eval-v1", "evalSummary": { "suite": "lite-agent-eval-v1", "status": "not_evaluated", "passed": 0, "total": 0, "updatedAt": null, "tasks": [] }, "reason": "Tools, structured outputs, reasoning", "instabilityPenalty": 0 }, { "rank": 4, "id": "google/gemma-4-26b-a4b-it:free", "name": "Google: Gemma 4 26B A4B (free)", "score": 655, "metadataScore": 530, "healthScore": 100, "latencyScore": 25, "liteEvalScore": 0, "contextLength": 262144, "maxCompletionTokens": 32768, "supportsTools": true, "supportsToolChoice": true, "supportsStructuredOutputs": false, "supportsResponseFormat": true, "supportsReasoning": true, "supportsIncludeReasoning": true, "supportsSeed": true, "supportsStop": false, "latencyMs": null, "healthStatus": "not_probed", "evalSuite": "lite-agent-eval-v1", "evalSummary": { "suite": "lite-agent-eval-v1", "status": "not_evaluated", "passed": 0, "total": 0, "updatedAt": null, "tasks": [] }, "reason": "Tools, reasoning, 262k context", "instabilityPenalty": 0 }, { "rank": 5, "id": "google/gemma-4-31b-it:free", "name": "Google: Gemma 4 31B (free)", "score": 655, "metadataScore": 530, "healthScore": 100, "latencyScore": 25, "liteEvalScore": 0, "contextLength": 262144, "maxCompletionTokens": 32768, "supportsTools": true, "supportsToolChoice": true, "supportsStructuredOutputs": false, "supportsResponseFormat": true, "supportsReasoning": true, "supportsIncludeReasoning": true, "supportsSeed": true, "supportsStop": false, "latencyMs": null, "healthStatus": "not_probed", "evalSuite": "lite-agent-eval-v1", "evalSummary": { "suite": "lite-agent-eval-v1", "status": "not_evaluated", "passed": 0, "total": 0, "updatedAt": null, "tasks": [] }, "reason": "Tools, reasoning, 262k context", "instabilityPenalty": 0 }, { "rank": 6, "id": "inclusionai/ling-3.0-flash-sante:free", "name": "inclusionAI: Ling 3.0 Flash Sante (free)", "score": 655, "metadataScore": 530, "healthScore": 100, "latencyScore": 25, "liteEvalScore": 0, "contextLength": 262144, "maxCompletionTokens": 32768, "supportsTools": true, "supportsToolChoice": true, "supportsStructuredOutputs": false, "supportsResponseFormat": false, "supportsReasoning": true, "supportsIncludeReasoning": true, "supportsSeed": true, "supportsStop": true, "latencyMs": null, "healthStatus": "not_probed", "evalSuite": "lite-agent-eval-v1", "evalSummary": { "suite": "lite-agent-eval-v1", "status": "not_evaluated", "passed": 0, "total": 0, "updatedAt": null, "tasks": [] }, "reason": "Tools, reasoning, 262k context", "instabilityPenalty": 0 } ], "notes": [ "Free model availability and rate limits can vary.", "Top candidates also received a lite agent eval for small file-writing, shell-command, and symbolic decoding tasks.", "The lite eval is a practical heuristic, not an official PinchBench result.", "Use openrouter/free if the recommended model is temporarily unavailable." ] }