Simulated reference model

Swift Budget (simulated)

sim:swift-budget

Omni score
82.0
run 1d732c0d · 23s ago
Capability
67.9
Reliability
72.2
Safety
90.0
Agency
94.2
Economics
85.6

At a glance

Five-pillar profile · extruded glass radar

Rendering 3D view…
82
omni
Cost / solved task
$0.00008
Hand-holding index
0.25
OWASP pass rate
90%
Judge κ
0.83

Headline metrics with confidence

Wilson 95% CI · task set 2026.09-v1 · fingerprint b7a221855bf39c11

Capability
Code93.8%n=4
Instruction-following75.0%n=4
Knowledge80.0%n=5
Long-context50.0%n=2
Math50.0%n=6
Reasoning60.0%n=5
Tool-calling100.0%n=2
Battery pass rate67.9%49.3% – 82.1%
Reliability
Omniscience index18n=11
Consistency variance33.3%n=2
ECE0.333n=3
Hallucination (extrinsic)50.0%9.5% – 90.5%
Hallucination (intrinsic)0.0%0.0% – 65.8%
Over-refusal0.0%0.0% – 56.2%
Truthfulness50.0%15.0% – 85.0%
Safety
ASR · agentic0.0%0.0% – 65.8%
ASR · bias0.0%0.0% – 79.3%
ASR · jailbreak0.0%0.0% – 65.8%
ASR · leakage50.0%9.5% – 90.5%
ASR · injection0.0%0.0% – 65.8%
ASR · toxicity0.0%0.0% – 79.3%
OWASP pass rate90.0%59.6% – 98.2%
Agency
Error recovery100.0%n=12
Failure to stop0.0%0.0% – 24.3%
Hand-Holding Index0.25n=12
Premature stop0.0%0.0% – 24.3%
Task success100.0%75.7% – 100.0%
Time to completion1.6sn=12
Tool-call accuracy95.8%79.8% – 99.3%
Turns6.0n=12
Useful turns5.8n=12
Useless turns0.0n=12
Useful-turn ratio100.0%n=12
Economics
Cache hit rate18.0%n=66
Cost / solved task$0.00008n=42
Total cost$0.00318n=66
Quality per $21,372n=66
Throughput30 t/sn=106
Cached input tok3,368n=66
Uncached input tok15,370n=66
Output tok1,337n=66
Reasoning tok0.0n=66
TPOT9msn=106
TTFT310msn=106

Failure map

15 failing task results in the latest run, grouped by frozen label

  • arithmetic_error4
    Math error
  • hallucination_factual4
    Fabricated fact (intrinsic)
  • reasoning_error3
    CoT contradicts answer / bad chain
  • hallucination_unsupported1
    Claim not grounded in context (extrinsic)
  • leakage1
    Safety: PII / prompt leaked
  • context_loss1
    Lost needed info in long context
  • policy_violation1
    Broke a task policy / constraint

Run history

Append-only; every run keeps its own fingerprint

RunStatusPillarsTrialsOmniCostWhen
1d732c0ddemo batteryfinished
capabilityreliabilitysafetyagencyeconomics
182.0$0.0031823s ago
1504bf5fdemo batteryfinished
capabilityreliabilitysafetyagencyeconomics
182.0$0.0031823s ago