- Cases
- varies
- Scored runs
- 5
- Configurations
- 5
- Top score
- 93.3%
Specification Method · grading · caveat
This suite has runs in the record but no entry in the published suite documentation, so there is no stated method, grading rule or caveat to show.
Recorded runs 5 runs · sorted by accuracy
Sorted by accuracy. The bar shows the 95 percent confidence interval. Where intervals overlap, the models are not distinguishable on this suite at this number of cases.
Top of the suite granite-guardian-4.1-8b-q4_0-ibm-np1-c64k-b11846 93.3% 95% interval 84.1–97.4
| Model | Score | 95% interval | Passed | Runtime · profile | Recorded |
|---|---|---|---|---|---|
| granite-guardian-4.1-8b-q4_0-ibm-np1-c64k-b11846 | 93.3% | 84.1–97.4 | Passed 56/60 | llama.cpp extraction | 2026-10-26 |
| granite-guardian-4.1-8b-q4_0-np1-c64k-b11846 | 90.0% | 79.9–95.3 overlaps the top interval | Passed 54/60 | llama.cpp extraction | 2026-10-26 |
| granite-guardian-4.1-8b-q4_0-np1-c64k-kvq4-b11846 | 88.3% | 77.8–94.2 overlaps the top interval | Passed 53/60 | llama.cpp extraction | 2026-10-26 |
| granite-guardian-4.1-8b-q4_0-np1-c8k-kvq4-b11846 | 88.3% | 77.8–94.2 overlaps the top interval | Passed 53/60 | llama.cpp extraction | 2026-10-26 |
| granite-guardian-4.1-8b-q4km-ibm-np1-c64k-b11846 | 88.3% | 77.8–94.2 overlaps the top interval | Passed 53/60 | llama.cpp extraction | 2026-10-26 |
From 24 October 2026, each benchmark released records how its server was set up, and its name says it: np1-c64k means one request at a time with 64K of context. Earlier runs didn't record it, so a gap between an older run and a newer one can come from the setup as well as the model.
Run log 5 logged runs of this suite
Every logged run, newest first (5)
| Finished | Model | Runtime · profile | Score | Coverage | Grader · dataset · config |
|---|---|---|---|---|---|
| granite-guardian-4.1-8b-q4_0-ibm-np1-c64k-b11846 | llama.cpp extraction | 93.3% | Coverage 60/60 | g c25afcd28397516f d 4f4dd926349b70a0 c dde9b0957de6d134 | |
| granite-guardian-4.1-8b-q4km-ibm-np1-c64k-b11846 | llama.cpp extraction | 88.3% | Coverage 60/60 | g c25afcd28397516f d 4f4dd926349b70a0 c 2a2539b427fe41ed | |
| granite-guardian-4.1-8b-q4_0-np1-c8k-kvq4-b11846 | llama.cpp extraction | 88.3% | Coverage 60/60 | g c25afcd28397516f d 4f4dd926349b70a0 c b485bf201e54b22e | |
| granite-guardian-4.1-8b-q4_0-np1-c64k-kvq4-b11846 | llama.cpp extraction | 88.3% | Coverage 60/60 | g c25afcd28397516f d 4f4dd926349b70a0 c 37c021d6dba9d648 | |
| granite-guardian-4.1-8b-q4_0-np1-c64k-b11846 | llama.cpp extraction | 90.0% | Coverage 60/60 | g c25afcd28397516f d 4f4dd926349b70a0 c 37c021d6dba9d648 |