Upstage
Release: 2026-08-11
Tested on: 2026-08-11 17:26
upstage/solar-pro4::xhigh
Summary
Solar Pro 4 scores 7.7 on AI BENCHY and ranks #63. It has 10.0 reliability, a 65.2% pass rate, $0.049 total cost, and 115.81s average response time.
What makes Solar Pro 4 unique: It stands out most in Puzzle Solving, where it ranks #4, while Instructions following is its weakest area at #15. 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.
7.7
Consistency
9.4
10.0
$0.049
Total Output Tokens
379,812
Total Input Tokens
98,107
Input Price
$0.030 / 1M
Output Price
$0.120 / 1M
Flaky tests
2
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Price History
Historical pricing data for this model from OpenRouter.
| Date | Input Price | Output Price |
|---|---|---|
| 2026-08-11 17:51 | $0.030 / 1M | $0.120 / 1M |
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 4xhighvsGPT-5.6 LunahighSolar Pro 4xhighvsDeepSeek V4 FlashhighSolar Pro 4xhighvsClaude Opus 4.6mediumSolar Pro 4xhighvsDeepSeek V4 ProhighSolar Pro 4xhighvsGLM 5mediumSolar Pro 4xhighvsMiniMax M3mediumSolar Pro 4xhighvsClaude Opus 4.8lowSolar Pro 4xhighvsGrok Build 0.1mediumSolar Pro 4xhighvsQwen3.7 FlashhighSolar Pro 4xhighvsGPT-5.6 Lunamedium
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 8.3 | 10.0 | |
| Coding | 5.8 | 9.9 | |
| Combined | 10.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 5.3 | 10.0 | |
| General Intelligence | 5.5 | 10.0 | |
| Instructions following | 8.4 | 6.9 | |
| Puzzle Solving | 8.9 | 7.8 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |