HISTORICAL RECORD · 2026-10-08 · invoice-13
Printer purchase $400 with a confirmed forged supplier identity.
Printer purchase $400 with a confirmed forged supplier identity.
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: 3
- 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 | 2.9785 | 2.9785 | 2.9785 | No |
| Clef-flash | 2.914 | 2.914 | 2.914 | No |
| Jev 1.13 | 3 | 3 | 3 | 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: 614 ms · $0.00009960
- Clef-flash · run 1: 438 ms · $0.00003735
- Jev 1.13 · run 1: 320 ms · $0.00001974
- Clef-flash · run 2: 391 ms · $0.00003735
- Jev 1.13 · run 2: 343 ms · $0.00001974
- Clef · run 2: 614 ms · $0.00009960
- Jev 1.13 · run 3: 347 ms · $0.00001974
- Clef · run 3: 509 ms · $0.00009960
- Clef-flash · run 3: 456 ms · $0.00003735
Full task, reference answers and raw recorded responses
{
"sample": {
"state": "Printer purchase $400 with a confirmed forged supplier identity.",
"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": 3
},
"runs": [
{
"caseId": "invoice-13",
"repeat": 1,
"outcome": {
"model": "clef",
"measuredAt": "2026-10-08T09:26:42.883Z",
"durationMs": 614,
"status": "success",
"result": {
"id": "gen-dec-1791451602-EYUPwweZYjwjQz9AWjtd",
"model": "cloudflare/clef",
"provider": "Cloudflare",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.9889
},
"category": {
"type": "choice",
"choice": "hardware",
"probabilities": {
"hardware": 0.9621,
"software": 0.011,
"services": 0.0141,
"travel": 0.0128
},
"confidence": 0.9015
},
"severity": {
"type": "score",
"score": 2.9785,
"probabilities": {
"0": 0.0028,
"1": 0.0027,
"2": 0.0076,
"3": 0.9869
},
"confidence": 0.9653,
"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": 415,
"output_tokens": 0,
"cost": 0.0000996
}
}
}
},
{
"caseId": "invoice-13",
"repeat": 1,
"outcome": {
"model": "clef-flash",
"measuredAt": "2026-10-08T09:26:43.506Z",
"durationMs": 438,
"status": "success",
"result": {
"id": "gen-dec-1791451603-uIPqhRmMZIJl7qWLHtXj",
"model": "cloudflare/clef-flash",
"provider": "Cloudflare",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.9545
},
"category": {
"type": "choice",
"choice": "hardware",
"probabilities": {
"hardware": 0.9266,
"software": 0.0261,
"services": 0.0261,
"travel": 0.0212
},
"confidence": 0.8138
},
"severity": {
"type": "score",
"score": 2.914,
"probabilities": {
"0": 0.0099,
"1": 0.0175,
"2": 0.0212,
"3": 0.9514
},
"confidence": 0.8746,
"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": 415,
"output_tokens": 0,
"cost": 0.00003735
}
}
}
},
{
"caseId": "invoice-13",
"repeat": 1,
"outcome": {
"model": "jev",
"measuredAt": "2026-10-08T09:26:43.954Z",
"durationMs": 320,
"status": "success",
"result": {
"id": "gen-dec-1791451603-5L9RCdXjx39c1d9IH5Pq",
"model": "typesafe/jev-1.13-20260917",
"provider": "TypeSafe",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.98
},
"category": {
"type": "choice",
"choice": "hardware",
"probabilities": {
"hardware": 1,
"software": 0,
"services": 0,
"travel": 0
},
"confidence": 1
},
"severity": {
"type": "score",
"score": 3,
"probabilities": {
"0": 0,
"1": 0,
"2": 0,
"3": 1
},
"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": 470,
"output_tokens": 75,
"cost": 0.00001974
}
}
}
},
{
"caseId": "invoice-13",
"repeat": 2,
"outcome": {
"model": "clef-flash",
"measuredAt": "2026-10-08T09:28:13.277Z",
"durationMs": 391,
"status": "success",
"result": {
"id": "gen-dec-1791451693-JrB5WhhJEqQ7TP6Z0MK7",
"model": "cloudflare/clef-flash",
"provider": "Cloudflare",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.9545
},
"category": {
"type": "choice",
"choice": "hardware",
"probabilities": {
"hardware": 0.9266,
"software": 0.0261,
"services": 0.0261,
"travel": 0.0212
},
"confidence": 0.8138
},
"severity": {
"type": "score",
"score": 2.914,
"probabilities": {
"0": 0.0099,
"1": 0.0175,
"2": 0.0212,
"3": 0.9514
},
"confidence": 0.8746,
"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": 415,
"output_tokens": 0,
"cost": 0.00003735
}
}
}
},
{
"caseId": "invoice-13",
"repeat": 2,
"outcome": {
"model": "jev",
"measuredAt": "2026-10-08T09:28:13.681Z",
"durationMs": 343,
"status": "success",
"result": {
"id": "gen-dec-1791451693-7v4KxEomBw7qiU8hoUls",
"model": "typesafe/jev-1.13-20260917",
"provider": "TypeSafe",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.98
},
"category": {
"type": "choice",
"choice": "hardware",
"probabilities": {
"software": 0,
"services": 0,
"hardware": 1,
"travel": 0
},
"confidence": 1
},
"severity": {
"type": "score",
"score": 3,
"probabilities": {
"0": 0,
"1": 0,
"2": 0,
"3": 1
},
"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": 470,
"output_tokens": 75,
"cost": 0.00001974
}
}
}
},
{
"caseId": "invoice-13",
"repeat": 2,
"outcome": {
"model": "clef",
"measuredAt": "2026-10-08T09:28:14.037Z",
"durationMs": 614,
"status": "success",
"result": {
"id": "gen-dec-1791451694-V1x27V6axTqNwo7gblAM",
"model": "cloudflare/clef",
"provider": "Cloudflare",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.9889
},
"category": {
"type": "choice",
"choice": "hardware",
"probabilities": {
"hardware": 0.9621,
"software": 0.011,
"services": 0.0141,
"travel": 0.0128
},
"confidence": 0.9015
},
"severity": {
"type": "score",
"score": 2.9785,
"probabilities": {
"0": 0.0028,
"1": 0.0027,
"2": 0.0076,
"3": 0.9869
},
"confidence": 0.9653,
"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": 415,
"output_tokens": 0,
"cost": 0.0000996
}
}
}
},
{
"caseId": "invoice-13",
"repeat": 3,
"outcome": {
"model": "jev",
"measuredAt": "2026-10-08T09:29:44.040Z",
"durationMs": 347,
"status": "success",
"result": {
"id": "gen-dec-1791451784-7ldTrLsQBwgulFRjTEGD",
"model": "typesafe/jev-1.13-20260917",
"provider": "TypeSafe",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.98
},
"category": {
"type": "choice",
"choice": "hardware",
"probabilities": {
"travel": 0,
"hardware": 1,
"services": 0,
"software": 0
},
"confidence": 1
},
"severity": {
"type": "score",
"score": 3,
"probabilities": {
"0": 0,
"1": 0,
"2": 0,
"3": 1
},
"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": 470,
"output_tokens": 75,
"cost": 0.00001974
}
}
}
},
{
"caseId": "invoice-13",
"repeat": 3,
"outcome": {
"model": "clef",
"measuredAt": "2026-10-08T09:29:44.402Z",
"durationMs": 509,
"status": "success",
"result": {
"id": "gen-dec-1791451784-YlWLegXxskCjK6SkRcaU",
"model": "cloudflare/clef",
"provider": "Cloudflare",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.9889
},
"category": {
"type": "choice",
"choice": "hardware",
"probabilities": {
"hardware": 0.9621,
"software": 0.011,
"services": 0.0141,
"travel": 0.0128
},
"confidence": 0.9015
},
"severity": {
"type": "score",
"score": 2.9785,
"probabilities": {
"0": 0.0028,
"1": 0.0027,
"2": 0.0076,
"3": 0.9869
},
"confidence": 0.9653,
"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": 415,
"output_tokens": 0,
"cost": 0.0000996
}
}
}
},
{
"caseId": "invoice-13",
"repeat": 3,
"outcome": {
"model": "clef-flash",
"measuredAt": "2026-10-08T09:29:44.929Z",
"durationMs": 456,
"status": "success",
"result": {
"id": "gen-dec-1791451784-mscpgosnIy30VnHWpJve",
"model": "cloudflare/clef-flash",
"provider": "Cloudflare",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.9545
},
"category": {
"type": "choice",
"choice": "hardware",
"probabilities": {
"hardware": 0.9266,
"software": 0.0261,
"services": 0.0261,
"travel": 0.0212
},
"confidence": 0.8138
},
"severity": {
"type": "score",
"score": 2.914,
"probabilities": {
"0": 0.0099,
"1": 0.0175,
"2": 0.0212,
"3": 0.9514
},
"confidence": 0.8746,
"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": 415,
"output_tokens": 0,
"cost": 0.00003735
}
}
}
}
]
}