Upstage
Release: 2026-08-11
Tested on: 2026-08-11 16:51
upstage/solar-pro4::low
~100BDenseClosedEstimated
Summary
Solar Pro 4 scores 6.8 on AI BENCHY and ranks #115. It has 9.6 reliability, a 62.1% pass rate, $0.042 total cost, and 113.12s average response time.
What makes Solar Pro 4 unique: Its total benchmark cost is unusually low for its score range.
Model facts
Researched on 2026-08-12
- 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.
6.8
Consistency
7.9
9.6
$0.042
Total Output Tokens
323,822
Total Input Tokens
90,547
Input Price
$0.030 / 1M
Output Price
$0.120 / 1M
Flaky tests
6
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-08-14 03:59 Re-test | 6.8 | 10.0 | $0.044 | Compare | |
| 2026-08-11 16:51 Initial run | 6.8 | 9.6 | $0.042 | Current run |
Charts
Choose the first model, then click a second model to open a side-by-side page.
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
Solar Pro 4lowvsGLM 5.3 FlashXhighSolar Pro 4lowvsSolar Pro 4mediumSolar Pro 4lowvsSeed-2.0-CodemediumSolar Pro 4lowvsDeepSeek V4 PrononeSolar Pro 4lowvsStep 3.7 FlashhighSolar Pro 4lowvsGLM 5.3lowSolar Pro 4lowvsQwen3.6 FlashmediumSolar Pro 4lowvsMiMo-V2.5-PromediumSolar Pro 4lowvsGemini 3.5 FlashnoneSolar Pro 4lowvsMercury 2.5medium
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 8.2 | 7.9 | |
| Coding | 5.5 | 7.4 | |
| Combined | 6.3 | 5.8 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 3.6 | 7.2 | |
| General Intelligence | 5.5 | 10.0 | |
| Instructions following | 8.0 | 6.8 | |
| Puzzle Solving | 9.0 | 7.9 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |