Quality
Highest overall scores
- 1
Upstage: Solar Pro 441.6 - 2Upstage: Solar Pro 314.5
Upstage model benchmarks.
Compare Upstage models across answer quality, coding, complex tasks, speed, price, and context size.
Response speed
Fastest output in this sample
- 1Upstage: Solar Pro 435 t/s
- 2Upstage: Solar Pro 313 t/s
Input price
Lowest price per 1M tokens
- 1Upstage: Solar Pro 4$0.03/1M
- 2Upstage: Solar Pro 3$0.15/1M
Highlights
Quality
Overall capability · Higher is better
Speed
Output tokens per second · Higher is better
Input price
USD per 1M tokens · Lower is better
Quality benchmarks
Compare Upstage model capability.
Performance and price
Compare practical tradeoffs.
All Upstage models.
2 models in the current catalogue.
| Model | Links | |||||
|---|---|---|---|---|---|---|
| Upstage: Solar Pro 4 | 41.6 | 35 t/s | 524.3K | $0.03 | $0.12 | |
| Upstage: Solar Pro 3 | 14.5 | 13 t/s | 131.1K | $0.15 | $0.60 |
Upstage technical benchmarks.
Compare named evaluation records available for Upstage models. Missing results remain blank rather than being estimated.
| Benchmark | Area | Solar Pro 4 | Solar Pro 3 | Source |
|---|---|---|---|---|
| Intelligence Index | overallQuality | 41.6 | 14.5 | OpenRouter / artificial-analysis |
| Coding Index | coding | 52.7 | 16.2 | OpenRouter / artificial-analysis |
| Agentic Index | agentic | 33.6 | 2.9 | OpenRouter / artificial-analysis |
| GPQA | GPQA Diamond | 89.1 | 72.4 | OpenRouter model benchmarks |
| Humanity's Last Exam | HLE | 29.2 | 10.3 | OpenRouter model benchmarks |
| AA-LCR | AA-LCR | 70.7 | 31 | OpenRouter model benchmarks |
| GDPval-AA | GDPval-AA | 38.8 | 0 | OpenRouter model benchmarks |
| CritPt | CritPt | 5.4 | 0 | OpenRouter model benchmarks |
| SciCode | SciCode | 43.6 | 24.7 | OpenRouter model benchmarks |
| AA-Omniscience Accuracy | AA-Omniscience Accuracy | 18.9 | 18.5 | OpenRouter model benchmarks |
| AA-Omniscience Non-Hallucination Rate | AA-Omniscience Non-Hallucination Rate | 75.6 | 11.8 | OpenRouter model benchmarks |
| IFBench | IFBench | — | 71.2 | OpenRouter model benchmarks |
| τ²-Bench Telecom | τ²-Bench Telecom | — | 86.3 | OpenRouter model benchmarks |
| Terminal-Bench Hard | Terminal-Bench Hard | — | 7.6 | OpenRouter model benchmarks |