Solar Pro 3: benchmark scores, price and ranking
Solar Pro 3 from Upstage ranks #625 of 743 LLMs on the LLMs Tiger aggregate benchmark score (44.7), based on 2 benchmark results captured up to 2026-10-13.
- Organisation
- Upstage
- Type
- Frontier model
- Open weights
- No
- Released
- 2026-01-27 (source: epoch)
- Cheapest API price
- $0.150 in / $0.600 out per million tokens (via openrouter, observed 2026-10-13T21:47Z)
- Aggregate rank
- #625 of 743 (score 44.7)
Across the 2 benchmarks where at least ten models are scored, Solar Pro 3 is in the top 10% on 0 and in the top half on 0.
Its cheapest listed input price, $0.150 per million tokens, is lower than that of 72% of the 427 models with a listed price.
Solar Pro 3 benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| SciCode | 24.7% | #100 of 106 | Epoch AI Benchmarking Hub | 2026-10-13 |
| CritPt | 0.0% | #115 of 115 | Epoch AI Benchmarking Hub | 2026-10-13 |
About Solar Pro 3
Solar Pro 3 is a frontier model from Upstage. It was released on 2026-01-27, according to Epoch AI. The cheapest API listing we track charges $0.150 per million input tokens and $0.600 per million output tokens, through openrouter. We hold 2 benchmark results for it across 2 areas, and none is in the top tenth of its board.
Where Solar Pro 3 stands
On our aggregate score, Solar Pro 3 is #625 of 743 ranked models, in the lower half. Its score is 44.7; the scale is centred on 50, so it sits 5.3 points below the typical model. That beats 16% of the ranked field.
Solar Pro 3, benchmark by benchmark
SciCode is a weak spot. Solar Pro 3 scores 24.7%, #100 of 106, behind 93% of the models measured. The leader, Claude Opus 5.5 (max), reaches 66.9%. It covers scientific research code. The board median is 44.3%, so Solar Pro 3 is 19.7 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
CritPt is a weak spot. Solar Pro 3 scores 0.0%, #115 of 115, behind 99% of the models measured. The leader, GPT-5.6 Sol (max), reaches 32.3%. It covers unpublished research-level physics problems. The board median is 2.9%, so Solar Pro 3 is 2.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
Solar Pro 3 has too few results on boards with ten or more models to say where it is strong or weak. Treat any single score as a data point, not a verdict.
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so Solar Pro 3 costs less than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on Phi-3-medium-128k-instruct ($0.170) and Llama 4 Maverick (FP8) ($0.188).
Reading these numbers
The 2 scores on this page come from 1 source: Epoch AI Benchmarking Hub (2). No official leaderboard supplied any of them, so treat them as third-party measurements. With 2 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #622 o1-mini-2024-09-12 (44.8)
- #623 mistral-small-2501 (44.8)
- #624 Qwen2.5-1.5B (44.7)
- #626 Gemini 2.0 Flash (44.6)
- #627 gemini-2.5-flash-lite-preview-06-17 (Default thinking length) (44.6)
- #628 DeepSeek-R1-Distill-Qwen-1.5B (44.6)
Compare it on the live leaderboard → · How the aggregate score works