Skip to main content
ModelScale
OA

Ornith-1.5-397B

Ornith AI · Open Weight · rank 36 · bench-align-v5

Self-hosted
Canonical idornith-1-5-397b
Overall score65.13
Context window262K tokens
Release date2026-08-18
Access typeOpen Weight
Blended $/1MUnavailable75% input / 25% output

Capability shape

Seven axes from the ranking source. A missing axis is drawn as a gap.

Capability evidence

Agentic74.9
Coding63.8
Knowledge66.5
ReasoningUnavailable
Multimodal & GroundedUnavailable
Instruction FollowingUnavailable
MathUnavailable

Runtime service evidence

Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim.

Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.

Evidence key: ObservedUnavailable

Runtime measurements
MeasurementValueObservedLast goodEvidence
Time to first tokenUnavailableUnavailableUnavailable
ThroughputUnavailableUnavailableUnavailable

Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.

Endpoint and price matrix

Every published price component, including cache reads and writes.

Price components
ComponentUSDEvidence
Input / 1M tokensUnavailable
Output / 1M tokensUnavailable
Cache read / 1M tokensUnavailable
Cache write / 1M tokensUnavailable
Blended / 1M (75% input / 25% output)Unavailable
Self-hosted listingOrnith publishes the MIT-licensed Ornith-1.5-397B checkpoint on Hugging Face for self-hosted use. Ornith does not publish a first-party hosted API token price for this exact model, so BenchLM represents it as self-host/free-per-token before infrastructure costs.No hosted token rate was published for this model, so its per-token price is unavailable rather than zero.

Workload-aware monthly cost example

10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. This uses the same calculator as the cost simulator, so an unavailable applicable rate makes the example unavailable too.

Modelled monthly costUnavailableThe applicable input rate is unavailable.
Modelled tokensUnavailable
Open the simulatorChange this workload

Benchmark record

17 matched benchmark rows with their published value, unit, and provenance.

Knowledge

Knowledge benchmarks
BenchmarkValueTasksDifficultyProvenance
GPQA
Graduate-Level Google-Proof Q&A
92.8448 questionsGraduate levelGPQA: A Graduate-Level Google-Proof Q&A Benchmark
GPQA-D
GPQA Diamond
92.8Graduate-level science questionsGraduate levelTrinity-Large-Thinking: Scaling an Open Source Frontier Agent
HLE
Humanity's Last Exam
44.6Expert-level questionsFrontier expert levelHumanity's Last Exam
HLE w/o tools
Humanity's Last Exam without tools
44.6Expert-level questionsFrontier expert levelIntroducing GPT-5.4 mini and nano

Coding

Coding benchmarks
BenchmarkValueTasksDifficultyProvenance
Terminal-Bench 2.1
Terminal-Bench 2.1 (provider run)
86.1Terminal-based software-agent tasksProfessional software engineeringDeepSeek V4 Flash 0731 update
SWE-bench Verified
Software Engineering Benchmark Verified
86500 verified issuesProfessional software engineeringSWE-bench: Can Language Models Resolve Real-World GitHub Issues?
SWE-bench Pro
SWE-bench Pro
65.11,865 repository problemsLong-horizon professional engineeringSWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
SWE Multilingual
SWE Multilingual
79.6Multilingual software-engineering tasksProfessional software engineeringMiniMax M2.7: Early Echoes of Self-Evolution
NL2Repo
NL2Repo
59.5Natural language to repository tasksSystem-level software comprehensionMiniMax M2.7: Early Echoes of Self-Evolution
DeepSWE
DeepSWE
56.0113 software engineering tasks across 91 repositories and 5 languagesLong-horizon software engineeringDeepSWE benchmark blog

Agentic

Agentic benchmarks
BenchmarkValueTasksDifficultyProvenance
Terminal-Bench 2.1
Terminal-Bench 2.1 (provider run)
86.1Terminal-based software-agent tasksProfessional software engineeringDeepSeek V4 Flash 0731 update
BrowseComp
BrowseComp
86.6Research questions requiring browsingHard web researchBrowseComp
HLE w/ tools
Humanity's Last Exam with tools
56.1Expert questions with tool useFrontier tool-augmented reasoningDeepSeek-V4 Technical Report
MCP Atlas
MCP Atlas
80Tool-integrated agent tasksAdvanced tool useIntroducing GPT-5.4 mini and nano
Toolathlon-Verified
Toolathlon-Verified
71.2Verified multi-tool workflowsAdvanced tool useKimi K3: Open Frontier Intelligence
Claw-Eval
Claw-Eval
81.4300 tasks, 2,159 rubricsReal-world general, multi-turn, and native multimodal agent executionClaw-Eval: Towards Trustworthy Evaluation of Autonomous Agents
WideResearch
WideResearch
80.8Open-ended research tasksBroad research-agent workflowsQwen3.6 launch benchmarks

Lifecycle and limitations log

Lifecycle events the source associates with this model, plus what this profile does not claim.

No lifecycle event references this model.

That is not evidence the model has no lifecycle plan — only that this source published none.

What this profile does not claimValues are reproduced exactly as their sources published them, in the units those sources declared; none are converted, interpolated, or averaged across providers. Any field marked unavailable was attempted and not returned — the attempt timestamp is in each badge. Last attempted fetch for this model’s score: 2026-09-17 17:17 UTC.