live / results / 2026-08-26-google-gemma-4-26b-a4b-qat.json
live / results / 2026-08-26-google-gemma-4-26b-a4b-qat.json
{
"date": "2026-08-26",
"modelId": "google/gemma-4-26b-a4b-qat",
"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": 12,
"toolCallsByName": {
"workspace_inspect": 3,
"workspace_tasks": 6,
"workspace_edit": 2,
"workspace_command": 1
},
"rounds": 13,
"invalidToolRequests": 0,
"envelopeViolations": 0,
"wallMs": 11254,
"contextOverflow": false,
"promptTokens": 80640,
"predictedTokens": 1414
},
"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: 1",
"ok": true
}
],
"metrics": {
"toolCalls": 10,
"toolCallsByName": {
"workspace_inspect": 3,
"workspace_tasks": 2,
"workspace_plan": 2,
"workspace_edit": 2,
"workspace_command": 1
},
"rounds": 12,
"invalidToolRequests": 0,
"envelopeViolations": 0,
"wallMs": 13587,
"contextOverflow": false,
"promptTokens": 79786,
"predictedTokens": 1789
},
"contextLength": 16384
},
{
"scenario": "S5",
"title": "foreground command, background job, cancel",
"driver": "in-process",
"success": false,
"checks": [
{
"name": "foreground run reported an exit code",
"ok": true
},
{
"name": "background job started",
"ok": true
},
{
"name": "job was canceled",
"ok": false,
"detail": "0 cancel envelopes; final status \"running\""
}
],
"metrics": {
"toolCalls": 9,
"toolCallsByName": {
"workspace_notes": 2,
"workspace_inspect": 1,
"workspace_tasks": 4,
"workspace_command": 2
},
"rounds": 10,
"invalidToolRequests": 0,
"envelopeViolations": 0,
"wallMs": 9937,
"contextOverflow": false,
"promptTokens": 52260,
"predictedTokens": 994
},
"contextLength": 16384
},
{
"scenario": "S9",
"title": "full project from an empty directory",
"driver": "in-process",
"success": false,
"checks": [
{
"name": "package.json parses with scripts.test running node --test",
"ok": false,
"detail": "no package.json"
},
{
"name": "at least one file under src/",
"ok": false,
"detail": "src/ is empty or missing"
},
{
"name": "at least one test file under tests/",
"ok": false,
"detail": "tests/ has no .js file"
},
{
"name": "node --test exits 0 with at least three ok lines",
"ok": false,
"detail": "exit 0, 0 ok lines | TAP version 13 | 1..0 | # tests 0 | # suites 0 | # pass 0 | # fail 0 | # cancelled 0 | # skipped 0 | # todo 0 | # duration_ms 5.3759 |"
},
{
"name": "score: 0/4",
"ok": true
},
{
"name": "files created: none",
"ok": true
},
{
"name": "ok lines: 0",
"ok": true
},
{
"name": "node --test exit: 0",
"ok": true
},
{
"name": "package private: absent",
"ok": true
},
{
"name": "applied transactions: 0",
"ok": true
},
{
"name": "model ran node --test: no",
"ok": true
}
],
"metrics": {
"toolCalls": 4,
"toolCallsByName": {
"workspace_inspect": 1,
"workspace_tasks": 3
},
"rounds": 6,
"invalidToolRequests": 1,
"envelopeViolations": 0,
"wallMs": 62841,
"contextOverflow": true,
"promptTokens": 26096,
"predictedTokens": 11803
},
"contextLength": 16384
}
]
}
{
"date": "2026-08-26",
"modelId": "google/gemma-4-26b-a4b-qat",
"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": 12,
"toolCallsByName": {
"workspace_inspect": 3,
"workspace_tasks": 6,
"workspace_edit": 2,
"workspace_command": 1
},
"rounds": 13,
"invalidToolRequests": 0,
"envelopeViolations": 0,
"wallMs": 11254,
"contextOverflow": false,
"promptTokens": 80640,
"predictedTokens": 1414
},
"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: 1",
"ok": true
}
],
"metrics": {
"toolCalls": 10,
"toolCallsByName": {
"workspace_inspect": 3,
"workspace_tasks": 2,
"workspace_plan": 2,
"workspace_edit": 2,
"workspace_command": 1
},
"rounds": 12,
"invalidToolRequests": 0,
"envelopeViolations": 0,
"wallMs": 13587,
"contextOverflow": false,
"promptTokens": 79786,
"predictedTokens": 1789
},
"contextLength": 16384
},
{
"scenario": "S5",
"title": "foreground command, background job, cancel",
"driver": "in-process",
"success": false,
"checks": [
{
"name": "foreground run reported an exit code",
"ok": true
},
{
"name": "background job started",
"ok": true
},
{
"name": "job was canceled",
"ok": false,
"detail": "0 cancel envelopes; final status \"running\""
}
],
"metrics": {
"toolCalls": 9,
"toolCallsByName": {
"workspace_notes": 2,
"workspace_inspect": 1,
"workspace_tasks": 4,
"workspace_command": 2
},
"rounds": 10,
"invalidToolRequests": 0,
"envelopeViolations": 0,
"wallMs": 9937,
"contextOverflow": false,
"promptTokens": 52260,
"predictedTokens": 994
},
"contextLength": 16384
},
{
"scenario": "S9",
"title": "full project from an empty directory",
"driver": "in-process",
"success": false,
"checks": [
{
"name": "package.json parses with scripts.test running node --test",
"ok": false,
"detail": "no package.json"
},
{
"name": "at least one file under src/",
"ok": false,
"detail": "src/ is empty or missing"
},
{
"name": "at least one test file under tests/",
"ok": false,
"detail": "tests/ has no .js file"
},
{
"name": "node --test exits 0 with at least three ok lines",
"ok": false,
"detail": "exit 0, 0 ok lines | TAP version 13 | 1..0 | # tests 0 | # suites 0 | # pass 0 | # fail 0 | # cancelled 0 | # skipped 0 | # todo 0 | # duration_ms 5.3759 |"
},
{
"name": "score: 0/4",
"ok": true
},
{
"name": "files created: none",
"ok": true
},
{
"name": "ok lines: 0",
"ok": true
},
{
"name": "node --test exit: 0",
"ok": true
},
{
"name": "package private: absent",
"ok": true
},
{
"name": "applied transactions: 0",
"ok": true
},
{
"name": "model ran node --test: no",
"ok": true
}
],
"metrics": {
"toolCalls": 4,
"toolCallsByName": {
"workspace_inspect": 1,
"workspace_tasks": 3
},
"rounds": 6,
"invalidToolRequests": 1,
"envelopeViolations": 0,
"wallMs": 62841,
"contextOverflow": true,
"promptTokens": 26096,
"predictedTokens": 11803
},
"contextLength": 16384
}
]
}