live / results / 2026-08-26-qwen-qwen3.8-27b-2.json
live / results / 2026-08-26-qwen-qwen3.8-27b-2.json
{
"date": "2026-08-26",
"modelId": "qwen/qwen3.8-27b",
"driver": "in-process",
"contextLength": 16384,
"results": [
{
"scenario": "S1",
"title": "inspect → read → edit → verify",
"driver": "in-process",
"success": true,
"checks": [
{
"name": "bug fixed in src/math.js",
"ok": true
},
{
"name": "node --test passes",
"ok": true
},
{
"name": "test file untouched",
"ok": true
},
{
"name": "at least one applied transaction",
"ok": true
},
{
"name": "inspected before editing",
"ok": true
},
{
"name": "ran node --test through workspace_command",
"ok": true
}
],
"metrics": {
"toolCalls": 8,
"toolCallsByName": {
"workspace_inspect": 4,
"workspace_notes": 1,
"workspace_command": 2,
"workspace_edit": 1
},
"rounds": 6,
"invalidToolRequests": 0,
"envelopeViolations": 0,
"wallMs": 18230,
"contextOverflow": false,
"promptTokens": 36997,
"predictedTokens": 1377
},
"contextLength": 16384
},
{
"scenario": "S3",
"title": "plan mode: propose, /accept, execute",
"driver": "in-process",
"success": true,
"checks": [
{
"name": "no mutation before approval",
"ok": true
},
{
"name": "plan proposed in phase 1",
"ok": true
},
{
"name": "exactly one plan approved",
"ok": true
},
{
"name": "bug fixed in src/math.js",
"ok": true
},
{
"name": "node --test passes",
"ok": true
},
{
"name": "test file untouched",
"ok": true
},
{
"name": "plan proposals after /accept: 0",
"ok": true
},
{
"name": "plan final status: completed",
"ok": true
},
{
"name": "workspace_plan complete called: true",
"ok": true
},
{
"name": "APPROVAL_REQUIRED before approval: 0",
"ok": true
},
{
"name": "stray planned transactions: 0",
"ok": true
}
],
"metrics": {
"toolCalls": 9,
"toolCallsByName": {
"workspace_inspect": 4,
"workspace_notes": 1,
"workspace_plan": 2,
"workspace_edit": 1,
"workspace_command": 1
},
"rounds": 8,
"invalidToolRequests": 0,
"envelopeViolations": 0,
"wallMs": 23072,
"contextOverflow": false,
"promptTokens": 61491,
"predictedTokens": 1810
},
"contextLength": 16384
},
{
"scenario": "S5",
"title": "foreground command, background job, cancel",
"driver": "in-process",
"success": true,
"checks": [
{
"name": "foreground run reported an exit code",
"ok": true
},
{
"name": "background job started",
"ok": true
},
{
"name": "job was canceled",
"ok": true
}
],
"metrics": {
"toolCalls": 7,
"toolCallsByName": {
"workspace_inspect": 2,
"workspace_notes": 1,
"workspace_command": 4
},
"rounds": 5,
"invalidToolRequests": 0,
"envelopeViolations": 0,
"wallMs": 22578,
"contextOverflow": false,
"promptTokens": 31204,
"predictedTokens": 1596
},
"contextLength": 16384
}
]
}
{
"date": "2026-08-26",
"modelId": "qwen/qwen3.8-27b",
"driver": "in-process",
"contextLength": 16384,
"results": [
{
"scenario": "S1",
"title": "inspect → read → edit → verify",
"driver": "in-process",
"success": true,
"checks": [
{
"name": "bug fixed in src/math.js",
"ok": true
},
{
"name": "node --test passes",
"ok": true
},
{
"name": "test file untouched",
"ok": true
},
{
"name": "at least one applied transaction",
"ok": true
},
{
"name": "inspected before editing",
"ok": true
},
{
"name": "ran node --test through workspace_command",
"ok": true
}
],
"metrics": {
"toolCalls": 8,
"toolCallsByName": {
"workspace_inspect": 4,
"workspace_notes": 1,
"workspace_command": 2,
"workspace_edit": 1
},
"rounds": 6,
"invalidToolRequests": 0,
"envelopeViolations": 0,
"wallMs": 18230,
"contextOverflow": false,
"promptTokens": 36997,
"predictedTokens": 1377
},
"contextLength": 16384
},
{
"scenario": "S3",
"title": "plan mode: propose, /accept, execute",
"driver": "in-process",
"success": true,
"checks": [
{
"name": "no mutation before approval",
"ok": true
},
{
"name": "plan proposed in phase 1",
"ok": true
},
{
"name": "exactly one plan approved",
"ok": true
},
{
"name": "bug fixed in src/math.js",
"ok": true
},
{
"name": "node --test passes",
"ok": true
},
{
"name": "test file untouched",
"ok": true
},
{
"name": "plan proposals after /accept: 0",
"ok": true
},
{
"name": "plan final status: completed",
"ok": true
},
{
"name": "workspace_plan complete called: true",
"ok": true
},
{
"name": "APPROVAL_REQUIRED before approval: 0",
"ok": true
},
{
"name": "stray planned transactions: 0",
"ok": true
}
],
"metrics": {
"toolCalls": 9,
"toolCallsByName": {
"workspace_inspect": 4,
"workspace_notes": 1,
"workspace_plan": 2,
"workspace_edit": 1,
"workspace_command": 1
},
"rounds": 8,
"invalidToolRequests": 0,
"envelopeViolations": 0,
"wallMs": 23072,
"contextOverflow": false,
"promptTokens": 61491,
"predictedTokens": 1810
},
"contextLength": 16384
},
{
"scenario": "S5",
"title": "foreground command, background job, cancel",
"driver": "in-process",
"success": true,
"checks": [
{
"name": "foreground run reported an exit code",
"ok": true
},
{
"name": "background job started",
"ok": true
},
{
"name": "job was canceled",
"ok": true
}
],
"metrics": {
"toolCalls": 7,
"toolCallsByName": {
"workspace_inspect": 2,
"workspace_notes": 1,
"workspace_command": 4
},
"rounds": 5,
"invalidToolRequests": 0,
"envelopeViolations": 0,
"wallMs": 22578,
"contextOverflow": false,
"promptTokens": 31204,
"predictedTokens": 1596
},
"contextLength": 16384
}
]
}