Run 994f70d3
Jul 10, 2026, 12:44
OpenRouter · 4 models · repeat ×1
994f70d3-7e59-4879-8cf8-62b85eb66dba
Downloads
Audit pack
Results
4 models
| # | Adapter | Model | Think | Pass % | Cover % | Score | Outcomes | Time |
|---|---|---|---|---|---|---|---|---|
| 1 | OpenRouter | gpt-oss-20b | Low | 0.0% | 100.0% | 50.0% | 0/1/0/0 | 4.8s |
#1 gpt-oss-20bLowPass rate0.0% 0 pass · 1 scored Coverage100.0% 1 / 1 evidence-bearing Verified score50.0% 95% interval — · 1 run(s) pass@k0.0% 0/1 fixtures ever solved Outcome mix
Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel
Run facts
Latest run fixtures0/1 passed in linked runplayer-iterator | ||||||||
| 2 | OpenRouter | gemma-4-26b-a4b-it | — | 0.0% | 0.0% | 0.0% | 0/0/0/1 | 798ms |
#2 gemma-4-26b-a4b-itPass rate0.0% 0 pass · 0 scored Coverage0.0% 0 / 1 evidence-bearing Verified score0.0% 95% interval — · 1 run(s) pass@k0.0% 0/1 fixtures ever solved Outcome mix
Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel
Run facts
Latest run fixtures0/1 passed in linked runplayer-iterator | ||||||||
| 3 | OpenRouter | llama-3.2-3b-instruct | — | 0.0% | 0.0% | 0.0% | 0/0/0/1 | 1.3s |
#3 llama-3.2-3b-instructPass rate0.0% 0 pass · 0 scored Coverage0.0% 0 / 1 evidence-bearing Verified score0.0% 95% interval — · 1 run(s) pass@k0.0% 0/1 fixtures ever solved Outcome mix
Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel
Run facts
Latest run fixtures0/1 passed in linked runplayer-iterator | ||||||||
| 4 | OpenRouter | qwen3-coder | — | 0.0% | 0.0% | 0.0% | 0/0/0/1 | 1.1s |
#4 qwen3-coderPass rate0.0% 0 pass · 0 scored Coverage0.0% 0 / 1 evidence-bearing Verified score0.0% 95% interval — · 1 run(s) pass@k0.0% 0/1 fixtures ever solved Outcome mix
Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel
Run facts
Latest run fixtures0/1 passed in linked runplayer-iterator | ||||||||
Verified score aggregates compatible runs. Outcomes = pass / partial / wrong / invalid output; harness failures are excluded. Click a row for evidence and the linked run's fixtures.
Fixtures
1
gmod.player-iterator.v1