HISTORICAL RECORD · 2026-10-08 · invoice-05
Server purchase $4500
Server purchase $4500. Supplier identity and bank account cannot be verified.
Synthetic case. References were set by ClefBench and have not received an independent second review. These are recorded results, not a new model call.
urgent
Does this invoice need review because any required field is missing, supplier or banking details are unverified, or fraud is confirmed?
Reference: true
| Model | Run 1 | Run 2 | Run 3 | Changed answer? |
|---|---|---|---|---|
| Clef | true | true | true | No |
| Clef-flash | true | true | true | No |
| Jev 1.13 | true | true | true | No |
Yes/no uses a 50% threshold. Score values are weighted scale indices; error flags and stability use the nearest level. Use the rule and full distribution to judge whether a difference matters for your task.
category
Classify the purchased item.
Reference: hardware
- hardware: Physical computers, printers, monitors or servers
- software: Software licenses, applications or cloud storage subscriptions
- services: Professional or contractor work
- travel: Transport, accommodation or taxi expenses
| Model | Run 1 | Run 2 | Run 3 | Changed answer? |
|---|---|---|---|---|
| Clef | hardware | hardware | hardware | No |
| Clef-flash | hardware | hardware | hardware | No |
| Jev 1.13 | hardware | hardware | hardware | No |
Yes/no uses a 50% threshold. Score values are weighted scale indices; error flags and stability use the nearest level. Use the rule and full distribution to judge whether a difference matters for your task.
severity
Rate invoice risk from the stated evidence.
Reference: 2
- 0: Complete invoice with no reported issue
- 1: A required invoice field is missing
- 2: Supplier identity or banking details are unverified
- 3: Fraud, forgery or fabrication is confirmed
| Model | Run 1 | Run 2 | Run 3 | Changed answer? |
|---|---|---|---|---|
| Clef | 1.996 | 1.996 | 1.996 | No |
| Clef-flash | 1.9592 | 1.9592 | 1.9592 | No |
| Jev 1.13 | 2 | 2 | 2 | No |
Yes/no uses a 50% threshold. Score values are weighted scale indices; error flags and stability use the nearest level. Use the rule and full distribution to judge whether a difference matters for your task.
Time and provider cost for this case
- Clef · run 1: 644 ms · $0.00010056
- Clef-flash · run 1: 431 ms · $0.00003771
- Jev 1.13 · run 1: 369 ms · $0.00001991
- Clef-flash · run 2: 441 ms · $0.00003771
- Jev 1.13 · run 2: 351 ms · $0.00001991
- Clef · run 2: 636 ms · $0.00010056
- Jev 1.13 · run 3: 381 ms · $0.00001991
- Clef · run 3: 513 ms · $0.00010056
- Clef-flash · run 3: 466 ms · $0.00003771
Full task, reference answers and raw recorded responses
{
"sample": {
"state": "Server purchase $4500. Supplier identity and bank account cannot be verified.",
"questions": {
"urgent": {
"type": "noul",
"instructions": "Does this invoice need review because any required field is missing, supplier or banking details are unverified, or fraud is confirmed?"
},
"category": {
"type": "choice",
"instructions": "Classify the purchased item.",
"criteria": {
"hardware": "Physical computers, printers, monitors or servers",
"software": "Software licenses, applications or cloud storage subscriptions",
"services": "Professional or contractor work",
"travel": "Transport, accommodation or taxi expenses"
}
},
"severity": {
"type": "score",
"instructions": "Rate invoice risk from the stated evidence.",
"criteria": [
"Complete invoice with no reported issue",
"A required invoice field is missing",
"Supplier identity or banking details are unverified",
"Fraud, forgery or fabrication is confirmed"
]
}
}
},
"reference": {
"urgent": true,
"category": "hardware",
"severity": 2
},
"runs": [
{
"caseId": "invoice-05",
"repeat": 1,
"outcome": {
"model": "clef",
"measuredAt": "2026-10-08T09:26:30.167Z",
"durationMs": 644,
"status": "success",
"result": {
"id": "gen-dec-1791451590-HnaEJ1orowlJWPIVH389",
"model": "cloudflare/clef",
"provider": "Cloudflare",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.9919
},
"category": {
"type": "choice",
"choice": "hardware",
"probabilities": {
"hardware": 0.9427,
"software": 0.0179,
"services": 0.0205,
"travel": 0.0189
},
"confidence": 0.853
},
"severity": {
"type": "score",
"score": 1.996,
"probabilities": {
"0": 0.0031,
"1": 0.006,
"2": 0.9829,
"3": 0.008
},
"confidence": 0.955,
"legend": {
"0": "Complete invoice with no reported issue",
"1": "A required invoice field is missing",
"2": "Supplier identity or banking details are unverified",
"3": "Fraud, forgery or fabrication is confirmed"
}
}
},
"usage": {
"input_tokens": 419,
"output_tokens": 0,
"cost": 0.00010056
}
}
}
},
{
"caseId": "invoice-05",
"repeat": 1,
"outcome": {
"model": "clef-flash",
"measuredAt": "2026-10-08T09:26:30.820Z",
"durationMs": 431,
"status": "success",
"result": {
"id": "gen-dec-1791451590-QWKfDC1fDdZFhsWcVjf5",
"model": "cloudflare/clef-flash",
"provider": "Cloudflare",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.971
},
"category": {
"type": "choice",
"choice": "hardware",
"probabilities": {
"hardware": 0.9154,
"software": 0.0324,
"services": 0.0311,
"travel": 0.0211
},
"confidence": 0.7873
},
"severity": {
"type": "score",
"score": 1.9592,
"probabilities": {
"0": 0.0221,
"1": 0.0668,
"2": 0.8408,
"3": 0.0703
},
"confidence": 0.6224,
"legend": {
"0": "Complete invoice with no reported issue",
"1": "A required invoice field is missing",
"2": "Supplier identity or banking details are unverified",
"3": "Fraud, forgery or fabrication is confirmed"
}
}
},
"usage": {
"input_tokens": 419,
"output_tokens": 0,
"cost": 0.00003771
}
}
}
},
{
"caseId": "invoice-05",
"repeat": 1,
"outcome": {
"model": "jev",
"measuredAt": "2026-10-08T09:26:31.261Z",
"durationMs": 369,
"status": "success",
"result": {
"id": "gen-dec-1791451591-FqXTRHf80zAKAow1NvXM",
"model": "typesafe/jev-1.13-20260917",
"provider": "TypeSafe",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.96
},
"category": {
"type": "choice",
"choice": "hardware",
"probabilities": {
"hardware": 1,
"services": 0,
"travel": 0,
"software": 0
},
"confidence": 1
},
"severity": {
"type": "score",
"score": 2,
"probabilities": {
"0": 0,
"1": 0,
"2": 1,
"3": 0
},
"confidence": 1,
"legend": {
"0": "Complete invoice with no reported issue",
"1": "A required invoice field is missing",
"2": "Supplier identity or banking details are unverified",
"3": "Fraud, forgery or fabrication is confirmed"
}
}
},
"usage": {
"input_tokens": 474,
"output_tokens": 75,
"cost": 0.000019908
}
}
}
},
{
"caseId": "invoice-05",
"repeat": 2,
"outcome": {
"model": "clef-flash",
"measuredAt": "2026-10-08T09:28:01.908Z",
"durationMs": 441,
"status": "success",
"result": {
"id": "gen-dec-1791451681-Pi62VrbqdQH0PdFZwc6z",
"model": "cloudflare/clef-flash",
"provider": "Cloudflare",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.971
},
"category": {
"type": "choice",
"choice": "hardware",
"probabilities": {
"hardware": 0.9154,
"software": 0.0324,
"services": 0.0311,
"travel": 0.0211
},
"confidence": 0.7873
},
"severity": {
"type": "score",
"score": 1.9592,
"probabilities": {
"0": 0.0221,
"1": 0.0668,
"2": 0.8408,
"3": 0.0703
},
"confidence": 0.6224,
"legend": {
"0": "Complete invoice with no reported issue",
"1": "A required invoice field is missing",
"2": "Supplier identity or banking details are unverified",
"3": "Fraud, forgery or fabrication is confirmed"
}
}
},
"usage": {
"input_tokens": 419,
"output_tokens": 0,
"cost": 0.00003771
}
}
}
},
{
"caseId": "invoice-05",
"repeat": 2,
"outcome": {
"model": "jev",
"measuredAt": "2026-10-08T09:28:02.361Z",
"durationMs": 351,
"status": "success",
"result": {
"id": "gen-dec-1791451682-0WDXwkp3uP3sPn1yHlhA",
"model": "typesafe/jev-1.13-20260917",
"provider": "TypeSafe",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.96
},
"category": {
"type": "choice",
"choice": "hardware",
"probabilities": {
"hardware": 1,
"software": 0,
"travel": 0,
"services": 0
},
"confidence": 1
},
"severity": {
"type": "score",
"score": 2,
"probabilities": {
"0": 0,
"1": 0,
"2": 1,
"3": 0
},
"confidence": 1,
"legend": {
"0": "Complete invoice with no reported issue",
"1": "A required invoice field is missing",
"2": "Supplier identity or banking details are unverified",
"3": "Fraud, forgery or fabrication is confirmed"
}
}
},
"usage": {
"input_tokens": 474,
"output_tokens": 75,
"cost": 0.000019908
}
}
}
},
{
"caseId": "invoice-05",
"repeat": 2,
"outcome": {
"model": "clef",
"measuredAt": "2026-10-08T09:28:02.724Z",
"durationMs": 636,
"status": "success",
"result": {
"id": "gen-dec-1791451682-deaPxKLvY0ChkB8ra0Sb",
"model": "cloudflare/clef",
"provider": "Cloudflare",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.9919
},
"category": {
"type": "choice",
"choice": "hardware",
"probabilities": {
"hardware": 0.9427,
"software": 0.0179,
"services": 0.0205,
"travel": 0.0189
},
"confidence": 0.853
},
"severity": {
"type": "score",
"score": 1.996,
"probabilities": {
"0": 0.0031,
"1": 0.006,
"2": 0.9829,
"3": 0.008
},
"confidence": 0.955,
"legend": {
"0": "Complete invoice with no reported issue",
"1": "A required invoice field is missing",
"2": "Supplier identity or banking details are unverified",
"3": "Fraud, forgery or fabrication is confirmed"
}
}
},
"usage": {
"input_tokens": 419,
"output_tokens": 0,
"cost": 0.00010056
}
}
}
},
{
"caseId": "invoice-05",
"repeat": 3,
"outcome": {
"model": "jev",
"measuredAt": "2026-10-08T09:29:32.566Z",
"durationMs": 381,
"status": "success",
"result": {
"id": "gen-dec-1791451772-kTOQHP29r3ICdWWqwQv1",
"model": "typesafe/jev-1.13-20260917",
"provider": "TypeSafe",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.96
},
"category": {
"type": "choice",
"choice": "hardware",
"probabilities": {
"hardware": 1,
"travel": 0,
"services": 0,
"software": 0
},
"confidence": 1
},
"severity": {
"type": "score",
"score": 2,
"probabilities": {
"0": 0,
"1": 0,
"2": 1,
"3": 0
},
"confidence": 1,
"legend": {
"0": "Complete invoice with no reported issue",
"1": "A required invoice field is missing",
"2": "Supplier identity or banking details are unverified",
"3": "Fraud, forgery or fabrication is confirmed"
}
}
},
"usage": {
"input_tokens": 474,
"output_tokens": 75,
"cost": 0.000019908
}
}
}
},
{
"caseId": "invoice-05",
"repeat": 3,
"outcome": {
"model": "clef",
"measuredAt": "2026-10-08T09:29:32.963Z",
"durationMs": 513,
"status": "success",
"result": {
"id": "gen-dec-1791451772-BBazInZG6dqjUh8Bv14E",
"model": "cloudflare/clef",
"provider": "Cloudflare",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.9919
},
"category": {
"type": "choice",
"choice": "hardware",
"probabilities": {
"hardware": 0.9427,
"software": 0.0179,
"services": 0.0205,
"travel": 0.0189
},
"confidence": 0.853
},
"severity": {
"type": "score",
"score": 1.996,
"probabilities": {
"0": 0.0031,
"1": 0.006,
"2": 0.9829,
"3": 0.008
},
"confidence": 0.955,
"legend": {
"0": "Complete invoice with no reported issue",
"1": "A required invoice field is missing",
"2": "Supplier identity or banking details are unverified",
"3": "Fraud, forgery or fabrication is confirmed"
}
}
},
"usage": {
"input_tokens": 419,
"output_tokens": 0,
"cost": 0.00010056
}
}
}
},
{
"caseId": "invoice-05",
"repeat": 3,
"outcome": {
"model": "clef-flash",
"measuredAt": "2026-10-08T09:29:33.487Z",
"durationMs": 466,
"status": "success",
"result": {
"id": "gen-dec-1791451773-xKob3sO2O3EoWdK6bbwd",
"model": "cloudflare/clef-flash",
"provider": "Cloudflare",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.971
},
"category": {
"type": "choice",
"choice": "hardware",
"probabilities": {
"hardware": 0.9154,
"software": 0.0324,
"services": 0.0311,
"travel": 0.0211
},
"confidence": 0.7873
},
"severity": {
"type": "score",
"score": 1.9592,
"probabilities": {
"0": 0.0221,
"1": 0.0668,
"2": 0.8408,
"3": 0.0703
},
"confidence": 0.6224,
"legend": {
"0": "Complete invoice with no reported issue",
"1": "A required invoice field is missing",
"2": "Supplier identity or banking details are unverified",
"3": "Fraud, forgery or fabrication is confirmed"
}
}
},
"usage": {
"input_tokens": 419,
"output_tokens": 0,
"cost": 0.00003771
}
}
}
}
]
}