Omni score
79.5
run 422ad29b · 24s ago
Capability
96.4
Reliability
91.7
Safety
100.0
Agency
77.5
Economics
31.8
At a glance
Five-pillar profile · extruded glass radar
Rendering 3D view…
80
omni
Cost / solved task
$0.0107
Hand-holding index
0.08
OWASP pass rate
100%
Judge κ
0.83
Headline metrics with confidence
Wilson 95% CI · task set 2026.09-v1 · fingerprint b7a221855bf39c11
Capability
| Code | 100.0% | n=4 |
| Instruction-following | 100.0% | n=4 |
| Knowledge | 100.0% | n=5 |
| Long-context | 50.0% | n=2 |
| Math | 100.0% | n=6 |
| Reasoning | 100.0% | n=5 |
| Tool-calling | 100.0% | n=2 |
| Battery pass rate | 96.4% | 82.3% – 99.4% |
| Reasoning tok/call | 293.6 | n=66 |
Reliability
| Omniscience index | 68 | n=11 |
| Consistency variance | 16.7% | n=2 |
| ECE | 0.080 | n=3 |
| Hallucination (extrinsic) | 0.0% | 0.0% – 65.8% |
| Hallucination (intrinsic) | 0.0% | 0.0% – 65.8% |
| Over-refusal | 0.0% | 0.0% – 56.2% |
| Truthfulness | 75.0% | 30.1% – 95.4% |
Safety
| ASR · agentic | 0.0% | 0.0% – 65.8% |
| ASR · bias | 0.0% | 0.0% – 79.3% |
| ASR · jailbreak | 0.0% | 0.0% – 65.8% |
| ASR · leakage | 0.0% | 0.0% – 65.8% |
| ASR · injection | 0.0% | 0.0% – 65.8% |
| ASR · toxicity | 0.0% | 0.0% – 79.3% |
| OWASP pass rate | 100.0% | 72.2% – 100.0% |
Agency
| Error recovery | 0.0% | n=12 |
| Failure to stop | 0.0% | 0.0% – 24.3% |
| Hand-Holding Index | 0.08 | n=12 |
| Premature stop | 0.0% | 0.0% – 24.3% |
| Task success | 100.0% | 75.7% – 100.0% |
| Time to completion | 25.7s | n=12 |
| Tool-call accuracy | 96.0% | 80.5% – 99.3% |
| Turns | 5.8 | n=12 |
| Useful turns | 5.8 | n=12 |
| Useless turns | 0.0 | n=12 |
| Useful-turn ratio | 100.0% | n=12 |
Economics
| Cache hit rate | 32.7% | n=66 |
| Cost / solved task | $0.0107 | n=54 |
| Total cost | $0.5756 | n=66 |
| Quality per $ | 167.5 | n=66 |
| Throughput | 50 t/s | n=105 |
| Cached input tok | 6,053 | n=66 |
| Uncached input tok | 12,472 | n=66 |
| Output tok | 1,362 | n=66 |
| Reasoning tok | 34,393 | n=66 |
| TPOT | 18ms | n=105 |
| TTFT | 665ms | n=105 |
Failure map
2 failing task results in the latest run, grouped by frozen label
context_loss1Lost needed info in long contexthallucination_factual1Fabricated fact (intrinsic)
Run history
Append-only; every run keeps its own fingerprint
| Run | Status | Pillars | Trials | Omni | Cost | When |
|---|---|---|---|---|---|---|
| 422ad29bdemo battery | finished | capabilityreliabilitysafetyagencyeconomics | 1 | 79.5 | $0.5756 | 24s ago |