AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com
#93

Solar Pro 4

Upstage Release: 2026-08-11 Tested on: 2026-08-11 16:35 upstage/solar-pro4::high
~100BDenseClosedEstimated

Summary

Solar Pro 4 scores 7.2 on AI BENCHY and ranks #93. It has 9.9 reliability, a 63.6% pass rate, $0.045 total cost, and 100.28s average response time.

What makes Solar Pro 4 unique: Its total benchmark cost is unusually low for its score range. It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.

Model facts

Researched on 2026-08-12

Estimated
Parameters
~100B
Architecture
Dense
Availability
Closed
License
-

Best estimate from public evidence; the vendor did not disclose every value. Vendor does not disclose the parameter count.

Score

7.2

Consistency

8.7

Total Output Tokens

353,055

Total Input Tokens

79,731

Input Price

$0.030 / 1M

Output Price

$0.120 / 1M

Tests Correct

Wrong Tests: 10

Attempt pass rate: 63.6%

Flaky tests

4

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

100.28s

Response Time (max): 404.04s

Response Time (total): 2206.10s

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-08-14 03:57 Re-test 7.1 10.0 $0.046 Compare
2026-08-11 16:35 Initial run 7.2 9.9 $0.045 Current run

Run comparison

RunBenchmark coverageScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-08-11 16:35 · Initial run66/66 attempts7.28.79.912/224353,05579,731$0.045100.28s
2026-08-14 03:57 · Re-test66/66 attempts7.18.310.011/225363,19479,740$0.046120.58s
Difference—+0.1+0.4-0.1+1-1-10139-9-$0.002-20304ms

These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 8.7 7.9
Coding 5.7 9.9
Combined 7.3 5.8
Data parsing and extraction 10.0 10.0
Domain specific 5.3 10.0
General Intelligence 5.5 10.0
Instructions following 7.9 6.9
Puzzle Solving 8.7 7.9
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models