Upstage, proprietary
Solar Pro4
Solar Pro4 by Upstage ranks 121st of 354 ranked models on the Noometry Index as of October 2026, with a score of 42.1. Its strongest category is reasoning, where it ranks 104th. API pricing starts at $0.30 per million input tokens and $1.20 per million output tokens, with a 524K-token context window.
Last verified
Specifications
- Noometry rank
- #121 of 354
- Index score
- 42.1
- Evidence
- Confirmed 18 results
- Provider
Upstage- Released
- August 6, 2026
- Weights
- Proprietary
- Reasoning
- Yes
- Context window
- 524K
- Max output
- 131K
- Input price
- $0.30 / M
- Output price
- $1.20 / M
- Blended price
- $0.52 / M
- Output speed
- Not measured
- Value
- #75 of 219
- Knowledge cutoff
- February 2026
- Input
- text
Category scores
Each category score combines every public result we have in that category.
- Coding 40.1
- Reasoning 28.5
- Math 38.8
- Knowledge 39.8
- Multilingual 48.7
- Instruction Following 72.7
- Long Context 42.1
- Writing & Preference 56.5
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 40.1 | #149 | 2 |
| Reasoning | 28.5 | #104 | 1 |
| Math | 38.8 | #128 | 1 |
| Knowledge | 39.8 | #129 | 1 |
| Multilingual | 48.7 | #139 | 1 |
| Instruction Following | 72.7 | #132 | 1 |
| Long Context | 42.1 | #130 | 1 |
| Writing & Preference | 56.5 | #138 | 3 |
Strengths and weaknesses
Categories where Solar Pro4 places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Multilingual | 48.7 | +1.3 | #139 of 297, top 47% |
| Writing & Preference | 56.5 | +2.7 | #138 of 312, top 45% |
| Long Context | 42.1 | +1.2 | #130 of 296, top 44% |
Closest competitors
The models ranked just above and below Solar Pro4. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Qwen3.6 27B | #117 | 42.2 | $1.35 | — | Compare |
| Amazon Nova Experimental Chat 10 20 | #118 | 42.1 | — | — | Compare |
| Qwen3.5 122B-A10B | #119 | 42.1 | $1.10 | — | Compare |
| Longcat Flash Chat | #120 | 42.1 | — | 69 | Compare |
| GLM-4.5 | #122 | 42.0 | $1 | 32 | Compare |
| Qwen3.5 35B-A3B | #123 | 42.0 | $0.69 | — | Compare |
| GLM-4.7 | #124 | 42.0 | $1 | — | Compare |
| GPT-5.4 nano | #125 | 41.9 | $0.46 | 19 | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena WebDev | 1371 | #81 of 113, top 72% | LMArena | 2026-10-08 | |
| LMArena Coding | 1437 | #101 of 294, top 35% | LMArena | 2026-10-08 |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Hard Prompts | 1399 | #129 of 297, top 44% | LMArena | 2026-10-08 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Math | 1416 | #107 of 285, top 38% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Expert | 1427 | #100 of 273, top 37% | LMArena | 2026-10-08 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1361 | #139 of 297, top 47% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1415 | #132 of 285, top 47% | LMArena | 2026-10-08 | |
| LMArena French | 1397 | #121 of 223, top 55% | LMArena | 2026-10-08 | |
| LMArena German | 1364 | #121 of 231, top 53% | LMArena | 2026-10-08 | |
| LMArena Japanese | 1309 | #117 of 211, top 56% | LMArena | 2026-10-08 | |
| LMArena Korean | 1382 | #76 of 213, top 36% | LMArena | 2026-10-08 | |
| LMArena Russian | 1360 | #141 of 283, top 50% | LMArena | 2026-10-08 | |
| LMArena Spanish | 1401 | #109 of 226, top 49% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1377 | #125 of 298, top 42% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1381 | #132 of 291, top 46% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1386 | #131 of 297, top 45% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1316 | #158 of 295, top 54% | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 1385 | #132 of 295, top 45% | LMArena | 2026-10-08 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| openrouter | $0.09 | $0.36 | $0.018 | 2026-10-10 |
| upstage | $0.30 | $1.20 | $0.06 | 2026-10-10 |
Compare Solar Pro4
- Solar Pro4 vs Longcat Flash Chat
- Solar Pro4 vs GLM-4.5
- Solar Pro4 vs Qwen3.5 122B-A10B
- Solar Pro4 vs Qwen3.5 35B-A3B
- Solar Pro4 vs Amazon Nova Experimental Chat 10 20
- Solar Pro4 vs GLM-4.7
- Solar Pro4 vs GPT-6 Astra
- Solar Pro4 vs Claude Fable 5.1
- Solar Pro4 vs Gemini 3.8 Flash
- Solar Pro4 vs Kimi K3
- Solar Pro4 vs Grok 4.6
- Solar Pro4 vs Qwen3.8 Max
- Solar Pro4 vs GLM-5.3
- Solar Pro4 vs Muse Spark 1.3
Other Upstage models
Frequently asked questions
How good is Solar Pro4?
Solar Pro4 by Upstage ranks 121st of 354 ranked models on the Noometry Index as of October 2026, with a score of 42.1. Its strongest category is reasoning, where it ranks 104th. API pricing starts at $0.30 per million input tokens and $1.20 per million output tokens, with a 524K-token context window.
How much does Solar Pro4 cost?
Solar Pro4 costs $0.30 per million input tokens and $1.20 per million output tokens on Upstage's own API, with cached input at $0.06.
What is Solar Pro4's context window?
Solar Pro4 accepts up to 524K tokens of input and can write up to 131K tokens in one response.
Is Solar Pro4 open source?
No. Solar Pro4 is proprietary and available only through Upstage's API and partner platforms.
What are Solar Pro4's strengths and weaknesses?
Relative to other ranked models, Solar Pro4 places best in reasoning, math, knowledge and lowest in multilingual, writing & preference, long context.
What is Solar Pro4 best at?
Its best category is reasoning, where it ranks 104th on Noometry.