Run #7done_with_warnings
pxchat/pxchat • isolated
Customer Service sources / GLM 5.3 Flash (Q8_0) • Created Aug 31, 2026, 09:13 AM
- Pass
- 73%
- Avg
- 4.54
- Gate
- fail
- Errors
- 10
- Cases
- 262
Runs
Runs
Review eval history without switching into raw diagnostics. Use quick filters first; deeper filters stay tucked away.
Results
7 runs
Run #6done_with_warnings
pxchat/pxchat • isolated
Customer Service sources / Qwen3.8 Flash Next (Q8_0) • Created Aug 31, 2026, 09:13 AM
- Pass
- 64.9%
- Avg
- 4.24
- Gate
- fail
- Errors
- 11
- Cases
- 262
Run #5done_with_warnings
pxchat/pxchat • isolated
Customer Service sources / Bifrost Qwen 3.8 27B (Q8_K_XL) • Created Aug 20, 2026, 03:04 PM
- Pass
- 91.3%
- Avg
- 4.81
- Gate
- fail
- Errors
- 7
- Cases
- 296
Run #4done_with_warnings
pxchat/pxchat • isolated
Customer Service sources / Bifrost Qwen 3.5 (no thinking) • Created Aug 17, 2026, 10:57 AM
- Pass
- 61.4%
- Avg
- 4.52
- Gate
- fail
- Errors
- 1
- Cases
- 296
Run #3done_with_warnings
pxchat/pxchat • isolated
Customer Service sources / Bifrost Qwen 3.5 (no thinking) • Created Aug 17, 2026, 10:56 AM
- Pass
- 100%
- Avg
- 5
- Gate
- pass
- Errors
- 0
- Cases
- 1
Run #2done_with_warnings
pxchat/pxchat • isolated
Customer Service sources / Bifrost Qwen 3.5 (no thinking) • Created Aug 17, 2026, 10:52 AM
- Pass
- 0%
- Avg
- 4
- Gate
- pass
- Errors
- 0
- Cases
- 1
Run #1done_with_warnings
pxchat/pxchat • isolated
Customer Service sources / Bifrost Qwen 3.5 (no thinking) • Created Aug 17, 2026, 10:40 AM
- Pass
- 0%
- Avg
- 4
- Gate
- pass
- Errors
- 0
- Cases
- 1