HISTORICAL RECORD · 2026-10-08 · invoice-14
Accounting software $80 with complete invoice details.
Accounting software $80 with complete invoice details.
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: false
| Model | Run 1 | Run 2 | Run 3 | Changed answer? |
|---|---|---|---|---|
| Clef | false | false | false | No |
| Clef-flash | false | false | false | No |
| Jev 1.13 | false | false | false | 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: software
- 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 | software | software | software | No |
| Clef-flash | software | software | software | No |
| Jev 1.13 | software | software | software | 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: 0
- 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 | 0.1525 | 0.1525 | 0.1525 | No |
| Clef-flash | 0.5733Differs from reference | 0.5733Differs from reference | 0.5733Differs from reference | No |
| Jev 1.13 | 0.56Differs from reference | 0.58Differs from reference | 0.51Differs from reference | 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: 635 ms · $0.00009912
- Clef-flash · run 1: 403 ms · $0.00003717
- Jev 1.13 · run 1: 340 ms · $0.00001970
- Clef-flash · run 2: 426 ms · $0.00003717
- Jev 1.13 · run 2: 334 ms · $0.00001970
- Clef · run 2: 608 ms · $0.00009912
- Jev 1.13 · run 3: 356 ms · $0.00001970
- Clef · run 3: 850 ms · $0.00009912
- Clef-flash · run 3: 393 ms · $0.00003717
Full task, reference answers and raw recorded responses
{
"sample": {
"state": "Accounting software $80 with complete invoice details.",
"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": false,
"category": "software",
"severity": 0
},
"runs": [
{
"caseId": "invoice-14",
"repeat": 1,
"outcome": {
"model": "clef",
"measuredAt": "2026-10-08T09:26:44.282Z",
"durationMs": 635,
"status": "success",
"result": {
"id": "gen-dec-1791451604-DsaPhuD2cKs56bpZwQWA",
"model": "cloudflare/clef",
"provider": "Cloudflare",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.0145
},
"category": {
"type": "choice",
"choice": "software",
"probabilities": {
"hardware": 0.0064,
"software": 0.9778,
"services": 0.0128,
"travel": 0.003
},
"confidence": 0.9417
},
"severity": {
"type": "score",
"score": 0.1525,
"probabilities": {
"0": 0.9201,
"1": 0.017,
"2": 0.0532,
"3": 0.0097
},
"confidence": 0.7997,
"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": 413,
"output_tokens": 0,
"cost": 0.00009912
}
}
}
},
{
"caseId": "invoice-14",
"repeat": 1,
"outcome": {
"model": "clef-flash",
"measuredAt": "2026-10-08T09:26:44.927Z",
"durationMs": 403,
"status": "success",
"result": {
"id": "gen-dec-1791451604-ME4HrP6l3pfV38PvDb1S",
"model": "cloudflare/clef-flash",
"provider": "Cloudflare",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.0857
},
"category": {
"type": "choice",
"choice": "software",
"probabilities": {
"hardware": 0.0151,
"software": 0.9034,
"services": 0.077,
"travel": 0.0045
},
"confidence": 0.763
},
"severity": {
"type": "score",
"score": 0.5733,
"probabilities": {
"0": 0.6925,
"1": 0.1015,
"2": 0.1462,
"3": 0.0598
},
"confidence": 0.353,
"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": 413,
"output_tokens": 0,
"cost": 0.00003717
}
}
}
},
{
"caseId": "invoice-14",
"repeat": 1,
"outcome": {
"model": "jev",
"measuredAt": "2026-10-08T09:26:45.338Z",
"durationMs": 340,
"status": "success",
"result": {
"id": "gen-dec-1791451605-fpmi3uK8cxTPJjxQrl0K",
"model": "typesafe/jev-1.13-20260917",
"provider": "TypeSafe",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.46
},
"category": {
"type": "choice",
"choice": "software",
"probabilities": {
"hardware": 0,
"software": 1,
"services": 0,
"travel": 0
},
"confidence": 1
},
"severity": {
"type": "score",
"score": 0.56,
"probabilities": {
"0": 0.68,
"1": 0.09,
"2": 0.23,
"3": 0
},
"confidence": 0.44,
"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": 469,
"output_tokens": 75,
"cost": 0.000019698
}
}
}
},
{
"caseId": "invoice-14",
"repeat": 2,
"outcome": {
"model": "clef-flash",
"measuredAt": "2026-10-08T09:28:14.665Z",
"durationMs": 426,
"status": "success",
"result": {
"id": "gen-dec-1791451694-84P8L81YEBNwFO8nkkEc",
"model": "cloudflare/clef-flash",
"provider": "Cloudflare",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.0857
},
"category": {
"type": "choice",
"choice": "software",
"probabilities": {
"hardware": 0.0151,
"software": 0.9034,
"services": 0.077,
"travel": 0.0045
},
"confidence": 0.763
},
"severity": {
"type": "score",
"score": 0.5733,
"probabilities": {
"0": 0.6925,
"1": 0.1015,
"2": 0.1462,
"3": 0.0598
},
"confidence": 0.353,
"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": 413,
"output_tokens": 0,
"cost": 0.00003717
}
}
}
},
{
"caseId": "invoice-14",
"repeat": 2,
"outcome": {
"model": "jev",
"measuredAt": "2026-10-08T09:28:15.104Z",
"durationMs": 334,
"status": "success",
"result": {
"id": "gen-dec-1791451695-MCAFmUppoLwHl7SnoxSr",
"model": "typesafe/jev-1.13-20260917",
"provider": "TypeSafe",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.4
},
"category": {
"type": "choice",
"choice": "software",
"probabilities": {
"services": 0,
"hardware": 0,
"software": 1,
"travel": 0
},
"confidence": 1
},
"severity": {
"type": "score",
"score": 0.58,
"probabilities": {
"0": 0.68,
"1": 0.08,
"2": 0.24,
"3": 0
},
"confidence": 0.44,
"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": 469,
"output_tokens": 75,
"cost": 0.000019698
}
}
}
},
{
"caseId": "invoice-14",
"repeat": 2,
"outcome": {
"model": "clef",
"measuredAt": "2026-10-08T09:28:15.452Z",
"durationMs": 608,
"status": "success",
"result": {
"id": "gen-dec-1791451695-InPHroSq3O4S9kv7ulRd",
"model": "cloudflare/clef",
"provider": "Cloudflare",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.0145
},
"category": {
"type": "choice",
"choice": "software",
"probabilities": {
"hardware": 0.0064,
"software": 0.9778,
"services": 0.0128,
"travel": 0.003
},
"confidence": 0.9417
},
"severity": {
"type": "score",
"score": 0.1525,
"probabilities": {
"0": 0.9201,
"1": 0.017,
"2": 0.0532,
"3": 0.0097
},
"confidence": 0.7997,
"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": 413,
"output_tokens": 0,
"cost": 0.00009912
}
}
}
},
{
"caseId": "invoice-14",
"repeat": 3,
"outcome": {
"model": "jev",
"measuredAt": "2026-10-08T09:29:45.401Z",
"durationMs": 356,
"status": "success",
"result": {
"id": "gen-dec-1791451785-RCuXQ9xztORRwycYqKbG",
"model": "typesafe/jev-1.13-20260917",
"provider": "TypeSafe",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.42
},
"category": {
"type": "choice",
"choice": "software",
"probabilities": {
"services": 0,
"hardware": 0,
"travel": 0,
"software": 1
},
"confidence": 1
},
"severity": {
"type": "score",
"score": 0.51,
"probabilities": {
"0": 0.71,
"1": 0.08,
"2": 0.21,
"3": 0
},
"confidence": 0.5,
"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": 469,
"output_tokens": 75,
"cost": 0.000019698
}
}
}
},
{
"caseId": "invoice-14",
"repeat": 3,
"outcome": {
"model": "clef",
"measuredAt": "2026-10-08T09:29:45.775Z",
"durationMs": 850,
"status": "success",
"result": {
"id": "gen-dec-1791451785-AcS1dlUx7Yn1B5fyfKTA",
"model": "cloudflare/clef",
"provider": "Cloudflare",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.0145
},
"category": {
"type": "choice",
"choice": "software",
"probabilities": {
"hardware": 0.0064,
"software": 0.9778,
"services": 0.0128,
"travel": 0.003
},
"confidence": 0.9417
},
"severity": {
"type": "score",
"score": 0.1525,
"probabilities": {
"0": 0.9201,
"1": 0.017,
"2": 0.0532,
"3": 0.0097
},
"confidence": 0.7997,
"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": 413,
"output_tokens": 0,
"cost": 0.00009912
}
}
}
},
{
"caseId": "invoice-14",
"repeat": 3,
"outcome": {
"model": "clef-flash",
"measuredAt": "2026-10-08T09:29:46.641Z",
"durationMs": 393,
"status": "success",
"result": {
"id": "gen-dec-1791451786-xZRfIjbbB9vXbZbIAlfp",
"model": "cloudflare/clef-flash",
"provider": "Cloudflare",
"answers": {
"urgent": {
"type": "noul",
"noul": 0.0857
},
"category": {
"type": "choice",
"choice": "software",
"probabilities": {
"hardware": 0.0151,
"software": 0.9034,
"services": 0.077,
"travel": 0.0045
},
"confidence": 0.763
},
"severity": {
"type": "score",
"score": 0.5733,
"probabilities": {
"0": 0.6925,
"1": 0.1015,
"2": 0.1462,
"3": 0.0598
},
"confidence": 0.353,
"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": 413,
"output_tokens": 0,
"cost": 0.00003717
}
}
}
}
]
}