Data as of October 25, 2026 · How the score is built
Released Aug 11, 2026512K contextUpstage Solar Pro 4 launch post
Solar Pro 4
Decision readingSolar Pro 4 is tracked, but not publicly ranked yet. The profile exposes 11 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Released Aug 11, 2026 — see all recent releases
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Capability
Unranked
field median 50Not eligible for a public rank
Price
$0.30input / $1.20 output
input median $0.75cached $0.060 · blended $0.75
Speed
121tok/s
field median 96 tok/sFirst token 18.19 s
Context
512Ktokens
field median 256,000Maximum output length is tracked separately
Strongest published evidence
Published rows are visible, but no category has enough eligible evidence for a comparative rank.
Validate before choosing
11 published rows leave some tracked benchmark slots empty.
Source-linked · 11 displayable benchmark rows
Category score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank Not rankedWeight 22%4 benchmarksVerified | 24.4 | 4 benchmarks | Verified | |||
| CodingRank Not rankedWeight 20%3 benchmarksVerified | 72.7 | 3 benchmarks | Verified | |||
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| KnowledgeRank Not rankedWeight 12%2 benchmarksVerified | 80.3 | 2 benchmarks | Verified | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MathRank Not rankedWeight 5%1 benchmarkVerified | 85.5 | 1 benchmark | Verified |
11 of 766 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic4/4 verified
- Coding3/3 verified
- ReasoningNot measured
- MultimodalNot measured
- Knowledge2/2 verified
- MultilingualNot measured
- Inst. FollowingNot measured
- Math1/1 verified
Benchmark ledger
Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Coding3 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| Terminal-Bench 2.1 | Score57.0% | Versus best verified row Best verified: SWE-2 · 92.8% | Gap35.8 behind | WeightDisplay only | Provider exact |
| SWE-bench VerifiedSoftware Engineering Benchmark Verified | Score70.6% | Versus best verified row Best verified: Claude Opus 5 · 96% | Gap25.4 behind | WeightDisplay only | Provider exact |
| LiveCodeBenchLiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code | Score87.8% | Versus best verified row Best verified: Solar Pro 4 · 87.8% | GapBest verified | WeightDisplay only | Provider exact |
Agentic4 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| Terminal-Bench 2.1 | Score57.0% | Versus best verified row Best verified: SWE-2 · 92.8% | Gap35.8 behind | WeightDisplay only | Provider exact |
| BrowseComp | Score49.2% | Versus best verified row Best verified: Atria Dawn Preview · 92.5% | Gap43.3 behind | WeightDisplay only | Provider exact |
| MCP Atlas | Score61.4% | Versus best verified row Best verified: Muse Spark Open · 89.2% | Gap27.8 behind | WeightDisplay only | Provider exact |
| APEX-Agents | Score18.7% | Versus best verified row Best verified: Kimi K3.1 Pro · 67.2% | Gap48.5 behind | WeightDisplay only | Provider exact |
Knowledge2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| MMLU-ProMassive Multitask Language Understanding Professional | Score86.3% | Versus best verified row Best verified: Qwen3.7 Max · 89.6% | Gap3.3 behind | WeightDisplay only | Provider exact |
| GPQA-DGPQA Diamond | Score89.0% | Versus best verified row Best verified: GPT-6 Astra · 96.0% | Gap7 behind | WeightDisplay only | Provider exact |
Math1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| AIME26AIME 2026 | Score95.3% | Versus best verified row Best verified: GLM-5.2 · 99.2% | Gap3.9 behind | WeightDisplay only | Provider exact |
Korean1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| KMMLU-Pro | Score79.2% | Versus best verified row Best verified: A.X K2 · 80.5% | Gap1.3 behind | WeightDisplay only | Provider exact |
Bars run 0–100; the dark tick marks the best source-verified value
All 11 rowsLineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- solar-pro4Upstage Solar Pro 4 launch post
- Context window
- 512KUpstage Solar Pro 4 launch post
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not disclosed by the provider
- Availability
- Available through the Upstage Console API as solar-pro4 with a 512K context window and 128K maximum output, text in and text out. Upstage ran a launch discount through September 10, 2026 and a 70% promotion through October 10, 2026.
- Cloud regions
- Not tracked yet
- Lifecycle
- Current
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Published at $0.060 per million cached input tokensUpstage Solar Pro 4 launch post
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track Solar Pro 4, but the public leaderboard excludes this profile until enough non-generated benchmark coverage is available. Only published rows appear above.
Solar Pro 4 is a proprietary model with a 512K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Available through the Upstage Console API as solar-pro4 with a 512K context window and 128K maximum output, text in and text out. Upstage ran a launch discount through September 10, 2026 and a 70% promotion through October 10, 2026.
Solar Pro 4 sits in the Solar family with Solar Pro 2, Solar Pro 3. Its explicit predecessor is Solar Pro 3. 11 of 766 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Last updated October 25, 2026. Runtime fields remain blank until a sourced snapshot exists.
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Where to run Solar Pro 4 by API
OpenRouter is the one host we track that publishes a per-token price for it. Prices read from each host’s own pages on October 20, 2026.
| Host | Input /1M | Output /1M | Cached /1M | Context |
|---|---|---|---|---|
| OpenRouter | $0.15 | $0.60 | $0.03 | 524K |
Questions
How does Solar Pro 4 perform overall in AI benchmarks?
Solar Pro 4 has 11 source-displayable benchmark rows, but it does not qualify for a public overall rank. The available rows remain visible by category without being converted into a site-wide score. Missing evidence stays blank instead of being estimated from an earlier model.
Is Solar Pro 4 good for knowledge and understanding?
Solar Pro 4 has source-displayable benchmark coverage for knowledge and understanding, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Solar Pro 4 good for coding and programming?
Solar Pro 4 has source-displayable benchmark coverage for coding and programming, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Solar Pro 4 good for mathematics?
Solar Pro 4 has source-displayable benchmark coverage for mathematics, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Solar Pro 4 good for agentic tool use and computer tasks?
Solar Pro 4 has source-displayable benchmark coverage for agentic tool use and computer tasks, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
How does Solar Pro 4 perform on Korean benchmarks?
Solar Pro 4 has 1 source-displayable Korean benchmark score on this profile. Those rows remain separate from the global overall score because regional evaluations use a different comparison set. Use the dedicated Korean tables for side-by-side positions and inspect each source before applying the result elsewhere.
Which sibling models are related to Solar Pro 4?
Solar Pro 4 belongs to the Solar family. Related tracked variants include Solar Pro 2, Solar Pro 3. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does Solar Pro 4 have full benchmark coverage on BenchLM?
No. Solar Pro 4 currently has 22 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Solar Pro 4?
Solar Pro 4 has a documented context window of 512K. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.