Capability
65.4/100
field median 56.2
#35 of 232 ranked models
Ornith-1.5-397B
Released Aug 18, 2026 — see all recent releases
Decision reading
Ornith-1.5-397B scores 65.4 out of 100 and ranks #35 of 232. This profile shows 18 source-displayable benchmark rows; its strongest eligible category is Agentic at #18. Published weights can be self-hosted, but infrastructure cost varies and is not a comparable API token rate.
Data as of September 10, 2026 · How the score is built
Share or export
Strongest published evidence
Agentic ranks #18. Particularly useful for coding agents, browser research, and computer-use workflows.
Validate before choosing
18 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.
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.
Price
Self-hosted; infrastructure cost varies
input median $0.97
No comparable first-party hosted token rate
Speed
Not measured
field median 86.5 tok/s
Time to first token not measured
Context
262Ktokens
field median 256,000
Maximum output length is tracked separately
Capability shape
Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.
Ornith-1.5-397B category percentile values
- Agentic89th percentile
- Coding83rd percentile
- ReasoningNot eligible
- Knowledge81st percentile
- MathNot eligible
- MultilingualNot eligible
- MultimodalNot eligible
- Instruction followingNot eligible
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#18/152
- Coding#26/151
- ReasoningNot ranked
- Knowledge#36/183
- MathNot ranked
- MultilingualNot ranked
- MultimodalNot ranked
- Inst. FollowingNot ranked
Top decileTop quartileMid-fieldNot eligible
How 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.
- Agentic7/7 verified
- Coding7/7 verified
- ReasoningNot measured
- Knowledge4/4 verified
- MathNot measured
- MultilingualNot measured
- MultimodalNot measured
- Inst. FollowingNot measured
Verified sourceProvisionalNot measured
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 publishedOrnith-1.5-397B model card
- Context window
- 262KOrnith-1.5-397B 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
- Ornith publishes the MIT-licensed 397B MoE checkpoint for self-hosted use. Its official Hugging Face configuration specifies a 262,144-token context window; no first-party hosted API or token rate is published for this exact 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 recordOrnith-1.5-397B model card
- Self-host
- Open weights available; hardware estimate not sourced
- Rate limits
- Not tracked yet
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.
Published weights are available, but BenchLM does not yet have a sourced parameter and VRAM profile for this exact model. Hardware cost estimates stay unavailable until that sizing record is complete.
Estimate VRAM from known parametersCategory 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 #18 of 152Percentile 89thWeight 22%7 benchmarksVerified | 60.8 | #18 of 152 | 89th | 22% | 7 benchmarks | Verified |
| CodingRank #26 of 151Percentile 83rdWeight 20%7 benchmarksVerified | 58.8 | #26 of 151 | 83rd | 20% | 7 benchmarks | Verified |
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | Not ranked | Not available | 17% | 0 benchmarks | Not measured |
| KnowledgeRank #36 of 183Percentile 81stWeight 12%4 benchmarksVerified | 60.4 | #36 of 183 | 81st | 12% | 4 benchmarks | Verified |
| MathWeight 5%0 benchmarksNot measured | Not measured | Not ranked | Not available | 5% | 0 benchmarks | Not measured |
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | Not ranked | Not available | 7% | 0 benchmarks | Not measured |
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | Not ranked | Not available | 12% | 0 benchmarks | Not measured |
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | Not ranked | Not available | 5% | 0 benchmarks | Not measured |
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.
Coding7 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| SWE-bench Pro | Score65.1% | Versus best verified row Best verified: Claude Fable 5.1 · 81.2% | Gap16.1 behind | WeightWeighted 25% | Provider exact |
| SWE-bench VerifiedSoftware Engineering Benchmark Verified | Score86% | Versus best verified row Best verified: Claude Opus 5 · 96% | Gap10 behind | WeightWeighted 10% | Provider exact |
| SWE Multilingual | Score79.6% | Versus best verified row Best verified: Claude Opus 5 · 89.5% | Gap9.9 behind | WeightWeighted 5% | Provider exact |
| Terminal-Bench 2.1Terminal-Bench 2.1 (provider run) | Score86.1% | Versus best verified row Best verified: SWE-2 · 92.8% | Gap6.7 behind | WeightDisplay only | Provider exact |
| DeepSWE | Score56.0% | Versus best verified row Best verified: Muse Spark 1.3 · 75.4% | Gap19.4 behind | WeightDisplay only | Provider exact |
| frontierBench | Score13.5% | Versus best verified row Best verified: Ornith-1.5-397B · 13.5% | GapBest verified | WeightDisplay only | Provider exact |
| NL2Repo | Score59.5% | Versus best verified row Best verified: DeepSeek V4.1 Flash · 65.4% | Gap5.9 behind | WeightDisplay only | Provider exact |
Agentic7 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| BrowseComp | Score86.6% | Versus best verified row Best verified: GPT-5.6 Sol · 92.2% | Gap5.6 behind | WeightWeighted 25% | Provider exact |
| Terminal-Bench 2.1Terminal-Bench 2.1 (provider run) | Score86.1% | Versus best verified row Best verified: SWE-2 · 92.8% | Gap6.7 behind | WeightDisplay only | Provider exact |
| HLE w/ toolsHumanity's Last Exam with tools | Score56.1% | Versus best verified row Best verified: Claude Opus 5 · 64.7% | Gap8.6 behind | WeightDisplay only | Provider exact |
| MCP Atlas | Score80% | Versus best verified row Best verified: Muse Spark 1.1 · 88.1% | Gap8.1 behind | WeightDisplay only | Provider exact |
| Toolathlon-Verified | Score71.2% | Versus best verified row Best verified: Claude Opus 5 · 80.6% | Gap9.4 behind | WeightDisplay only | Provider exact |
| WideResearch | Score80.8% | Versus best verified row Best verified: Hy4 preview · 83.9% | Gap3.1 behind | WeightDisplay only | Provider exact |
| Claw-Eval | Score81.4% | Versus best verified row Best verified: Ornith-1.5-397B · 81.4% | GapBest verified | WeightDisplay only | Provider exact |
Knowledge4 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| HLEHumanity's Last Exam | Score44.6% | Versus best verified row Best verified: Claude Fable 5.1 · 65% | Gap20.4 behind | WeightWeighted 35% | Provider exact |
| HLE w/o toolsHumanity's Last Exam without tools | Score44.6% | Versus best verified row Best verified: Claude Fable 5.1 · 60.9% | Gap16.3 behind | WeightWeighted 10% | Provider exact |
| GPQAGraduate-Level Google-Proof Q&A | Score92.8% | Versus best verified row Best verified: GPT-6 Astra · 96% | Gap3.2 behind | WeightWeighted 7% | Provider exact |
| GPQA-DGPQA Diamond | Score92.8% | Versus best verified row Best verified: GPT-6 Astra · 96.0% | Gap3.2 behind | WeightDisplay only | Provider exact |
Lineage
The sequence follows explicit supersedes links. A successor's displayed score stays at least 0.1 points above its predecessor; raw benchmark rows do not move. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
June 2026
Ornith-1.0-397BNot publicly ranked · Price not listed
Aug 18, 2026 · you are here
Ornith-1.5-397BScore 65.4 · Price not listed
397b · 397B
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.
Ornith-1.5-397B ranks #35 of 232 on the public leaderboard with a score of 65.4/100. It does not yet have enough sourced coverage for a verified position.
Ornith-1.5-397B 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.
Ornith publishes the MIT-licensed 397B MoE checkpoint for self-hosted use. Its official Hugging Face configuration specifies a 262,144-token context window; no first-party hosted API or token rate is published for this exact model.
Official exact-value snapshot from Ornith's August 2026 Ornith-1.5 launch page. BenchLM maps the directly comparable provider-reported rows, including the versioned Terminal-Bench 2.1, DeepSWE, and Terminal-Bench 3.0 results as distinct display evidence; the source says all Ornith-1.5 results are averaged over five runs. SWE Atlas QnA and Terminal-Bench Claude Code remain outside the current schema. The family remains unranked while independent benchmark-native coverage is unavailable.
Ornith-1.5-397B sits in the Ornith 1.5 family with Ornith-1.5-35B-A3B, Ornith-1.5-9B. Its explicit predecessor is Ornith-1.0-397B. 18 of 435 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Agentic at #18, while its lowest eligible position is Knowledge at #36. particularly useful for coding agents, browser research, and computer-use workflows.
Radar
Full release historyOrnith-1.5-397B release history
Ornith 1.5 released
Ornith AI · Model release
Source confirmed
Radar confirmed these at the source. Use Ornith-1.5-397B in your work? Explore Radar to follow supported changes and choose your alerts.
Frequently asked questions
How does Ornith-1.5-397B perform overall in AI benchmarks?
Ornith-1.5-397B ranks #35 out of 232 models on the public BenchAlign leaderboard, with a score of 65.4/100. Its evidence status is Estimated, and this profile shows 18 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is Ornith-1.5-397B good for knowledge and understanding?
Ornith-1.5-397B ranks #36 out of 183 eligible models for knowledge and understanding, with a public category score of 60.4/100. 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 Ornith-1.5-397B good for coding and programming?
Ornith-1.5-397B ranks #26 out of 151 eligible models for coding and programming, with a public category score of 58.8/100. 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 Ornith-1.5-397B good for agentic tool use and computer tasks?
Ornith-1.5-397B ranks #18 out of 152 eligible models for agentic tool use and computer tasks, with a public category score of 60.8/100. 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 Ornith-1.5-397B open source?
Ornith-1.5-397B is an open-weight model from Ornith AI. 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.
Which sibling models are related to Ornith-1.5-397B?
Ornith-1.5-397B belongs to the Ornith 1.5 family. Related tracked variants include Ornith-1.5-35B-A3B, Ornith-1.5-9B. 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 Ornith-1.5-397B have full benchmark coverage on BenchLM?
No. Ornith-1.5-397B currently has 18 source-displayable rows across 435 tracked benchmark slots. 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 Ornith-1.5-397B?
Ornith-1.5-397B 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.
Compare Ornith-1.5-397B with every tracked model482 comparisons
Last updated September 10, 2026. Runtime fields remain blank until a sourced snapshot exists.
Watch Ornith-1.5-397B in the weekly brief
Get one weekly email when material rank, price, availability, or benchmark evidence changes are worth revisiting.
Read a sample issueJoin 2,000+ readers.