Data as of October 20, 2026 · How the score is built
Released Oct 16, 2026262K contextOrcaRouter OrcaCyber-Nano-1.0 model card
OrcaCyber-Nano-1.0
Decision readingOrcaCyber-Nano-1.0 is tracked, but not publicly ranked yet. The profile exposes 7 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Released Oct 16, 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 49.9Not eligible for a public rank
Price
Self-hosted; infrastructure cost varies
input median $0.72No comparable first-party hosted token rate
Speed
Not measured
field median 93.5 tok/sTime to first token not measured
Context
262Ktokens
field median 256,000Maximum output length is tracked separately
Strongest published evidence
Instruction Following ranks #134. A well-rounded choice across a range of tasks.
Validate before choosing
7 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.
Source-linked · 7 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 |
|---|---|---|---|---|---|---|
| AgenticWeight 22%1 benchmarkVerified | Score pending | 1 benchmark | Verified | |||
| CodingWeight 20%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| KnowledgeWeight 12%1 benchmarkVerified | Score pending | 1 benchmark | Verified | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingRank #134 of 152Percentile 12thWeight 5%2 benchmarksVerified | 32.4 | 2 benchmarks | Verified | |||
| MathWeight 5%3 benchmarksVerified | Score pending | 3 benchmarks | Verified |
7 of 728 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.
- Agentic1/1 verified
- CodingNot measured
- ReasoningNot measured
- MultimodalNot measured
- Knowledge1/1 verified
- MultilingualNot measured
- Inst. Following2/2 verified
- Math3/3 verified
Benchmark ledger
Agentic 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.
Agentic1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| Terminal-Bench 2.1 | Score72.5% | Versus best verified row Best verified: SWE-2 · 92.8% | Gap20.3 behind | Weight8% ref. weight | Provider exact |
Knowledge1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| GPQA-DGPQA Diamond | Score88.3% | Versus best verified row Best verified: GPT-6 Astra · 96.0% | Gap7.7 behind | WeightDisplay only | Provider exact |
Inst. Following2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| IFBenchInstruction Following Benchmark | Score56.3% | Versus best verified row Best verified: Flint · 89.2% | Gap32.9 behind | WeightWeighted 70% | Provider exact |
| IFEvalInstruction-Following Eval | Score82.8% | Versus best verified row Best verified: LFM2.5-24B-A2B · 96.8% | Gap13.9 behind | WeightDisplay only | Provider exact |
Math3 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| AIME 2025American Invitational Mathematics Examination 2025 | Score96.2% | Versus best verified row Best verified: GPT-5.2 · 100% | Gap3.8 behind | WeightDisplay only | Provider exact |
| MATH-500MATH-500 Problem Set | Score98.6% | Versus best verified row Best verified: Ternary Bonsai 2 27B · 98.8% | Gap0.2 behind | WeightDisplay only | Provider exact |
| GSM8KGrade School Math 8K | Score97.5% | Versus best verified row Best verified: OrcaCyber-Nano-1.0 · 97.5% | GapBest verified | WeightDisplay only | Provider exact |
Bars run 0–100; the dark tick marks the best source-verified value
All 7 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.
Base entry
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
- Not publishedOrcaRouter OrcaCyber-Nano-1.0 model card
- Context window
- 262KOrcaRouter OrcaCyber-Nano-1.0 model card
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not sourced yet
- Availability
- Open GGUF weights on Hugging Face under the Qwen license, behind an automatic-approval gate that requires accepting conditions. Builds are 15.7 GB and 13 GB mixes with an MTP head, a DFlash2 draft file and a vision projector; loads in stock llama.cpp. No hosted endpoint or token price is published for this model.
- Cloud regions
- Not tracked yet
- Lifecycle
- Current
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordOrcaRouter OrcaCyber-Nano-1.0 model card
- Self-host
- OrcaCyber-Nano-1.0 needs ~24GB VRAM (1× NVIDIA RTX 4090 (24GB)).
- 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 OrcaCyber-Nano-1.0, but the public leaderboard excludes this profile until enough non-generated benchmark coverage is available. Only published rows appear above.
OrcaCyber-Nano-1.0 is a open weight model with a 262K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Open GGUF weights on Hugging Face under the Qwen license, behind an automatic-approval gate that requires accepting conditions. Builds are 15.7 GB and 13 GB mixes with an MTP head, a DFlash2 draft file and a vision projector; loads in stock llama.cpp. No hosted endpoint or token price is published for this model.
OrcaRouter, the LLM-gateway company, published OrcaCyber-Nano-1.0 on October 16, 2026 as GGUF builds of a 27B vision-language reasoning model for defensive security work (reverse engineering, vulnerability analysis, secure code review, incident response). It is a quantization of orcarouter/OrcaCyber-Nano-1.0-AI-Defense, runs in llama.cpp, and reads screenshots and diagrams. The card's single-column evaluation table has no comparators, and OrcaRouter says the harness, settings and full tables are still being finalized. BenchLM stores the figures whose benchmark and edition match an existing lane: GPQA Diamond, AIME 2025, MATH-500, GSM8K, IFEval, IFBench and Terminal-Bench 2.1. HumanEval+, MBPP+, BigCodeBench, LiveCodeBench and SWE-bench are reported without a variant or edition and stay unmapped. The card reports no cybersecurity benchmark for this model. The row is display-only and outside rankings.
7 of 728 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Instruction Following at #134. a well-rounded choice across a range of tasks.
Last updated October 20, 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.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Questions
How does OrcaCyber-Nano-1.0 perform overall in AI benchmarks?
OrcaCyber-Nano-1.0 has 7 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 OrcaCyber-Nano-1.0 good for knowledge and understanding?
OrcaCyber-Nano-1.0 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 OrcaCyber-Nano-1.0 good for mathematics?
OrcaCyber-Nano-1.0 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 OrcaCyber-Nano-1.0 good for agentic tool use and computer tasks?
OrcaCyber-Nano-1.0 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.
Is OrcaCyber-Nano-1.0 good for instruction following?
OrcaCyber-Nano-1.0 ranks #134 out of 152 eligible models for instruction following, with a public category score of 32.4/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is OrcaCyber-Nano-1.0 open source?
OrcaCyber-Nano-1.0 is an open-weight model from OrcaRouter. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Does OrcaCyber-Nano-1.0 have full benchmark coverage on BenchLM?
No. OrcaCyber-Nano-1.0 currently has 7 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 OrcaCyber-Nano-1.0?
OrcaCyber-Nano-1.0 has a documented context window of 262K. 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.