UpstageSolar Pro 4
Best configuration ranks #167 of 610 on the BenchLeader Index at 56.0 ±5.2. Last measured 8 Sept 2026. Released 6 Aug 2026.
- Blended price
- $0.525/M
- $0.300 in · $1.20 out
- Output speed
- 68 tok/s
- First answer
- 32 s
- first token 2.81 s
- Context
- 524k
- Overall index56
- Reasoning57
- Coding48
- Knowledge64
- Human preference56
- Long context63
- Composite64
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | default | Source | Trend |
|---|---|---|---|
| LMArena Hard Prompts | 1405#148 | LMArena | |
| GPQA Diamond (AA)not in index | 89.1%#82 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 29.2%#110 | Artificial Analysis |
Coding
| Benchmark | default | Source | Trend |
|---|---|---|---|
| LMArena Coding | 1448#129 | LMArena | |
| LMArena WebDev | 1371#82 | LMArena | |
| SciCode (AA)not in index | 44.6%#96 | Artificial Analysis |
Knowledge
| Benchmark | default | Source | Trend |
|---|---|---|---|
| AA-Omniscience | -0.8#101 | Artificial Analysis |
Human preference
| Benchmark | default | Source | Trend |
|---|---|---|---|
| LMArena Text | 1377#155 | LMArena |
Long context
| Benchmark | default | Source | Trend |
|---|---|---|---|
| AA-LCR | 74.0%#120 | Artificial Analysis |
Composite
| Benchmark | default | Source | Trend |
|---|---|---|---|
| AA Intelligence Index | 28.1#93 | Artificial Analysis |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Upstage | 26 tok/s | 2.09 s | $0.030 | $0.120 | 524k | – |
| Upstage (ZDR) | 25 tok/s | 3.53 s | $0.030 | $0.120 | 524k | – |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.060 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0005 | $0.0004 | 36.0 s |
| Summarise a 30-page report | 12,000 / 600 | $0.0043 | $0.0022 | 40.4 s |
| Code edit | 6,000 / 1,500 | $0.0036 | $0.0025 | 53.7 s |
| Agentic coding session | 60,000 / 4,000 | $0.023 | $0.012 | 1.5 min |
| Structured extraction | 2,000 / 200 | $0.0008 | $0.0005 | 34.5 s |
See also
Data as of 9 Sept 2026. Compare with another model.