Upstage Solar pro4

1 appearance · meta-score 67.9/100 · last seen 2026-08-11 · scored under rubric v15

Pooled composite across 1 primary run: 75.9 - no interval, a single run proves nothing about spread provisional: n < 3, treat as unsettled

$1.13Total cost
49,759,920Tokens
35.1%Cache hit
816Requests
1.96%Failure rate
1.29Tools/response
44,054,624Tokens per $

Agent role scores

Per-agent-role scores for Upstage Solar pro4
Agent role	Score / 10
Sprint-Review Agent	8.00
Develop Agent	7.93
Orchestrator	7.47
Platform Agent	7.14
Build Agent	7.13
Code-Review Agent	6.69
Code Agent	6.50
Test Agent	6.44
Sprint-Plan Agent	6.14
Spec Agent	5.59
Scout Agent	5.57
Pseudocode Agent	5.40

Run history (primary model)

Runs where Upstage Solar pro4 was the primary model, oldest first
Run	SoW	Date	Composite
Solar pro4	circles	Aug 2026	75.9

Every run on Favur Evals is scored by the same deterministic engine, on the same Statements of Work. The benchmark is self-funded - no vendor sponsorship, credits, or grants.