Kimi K3 vs Ornith-1.5-9B

Updated October 2, 2026. Rank says Kimi K3 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Decision reading

Kimi K3 has the higher public point estimate, 72.14 versus 28.63. Their conditional score ranges do not overlap. These ranges do not establish rank confidence. 8 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A

Kimi K3

Moonshot AI

72.14/100

Supported · Public rank #15

90% interval 68.8–75.5

Model B

Ornith-1.5-9B

Ornith AI

28.63/100

Estimated · Public rank #180

Conditional range 14.3–43.0

Shared results: 8
Kimi K3 only: 40
Ornith-1.5-9B only: 8
Like-for-like categories: 0 / 8

Supported: Kimi K3 · Estimated: Ornith-1.5-9B. Conditional ranges do not establish rank confidence.How the comparison works

Which one for your work

Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.

Long documents
Prompts that approach the documented context limit
Kimi K3
Kimi K3 has the larger documented context window.
Confidence: documented

Show secondary and unsupported calls

Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Ornith-1.5-9B is not ranked on the public lane for coding, so no winner is named for coding.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Ornith-1.5-9B is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limited
Chat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Repository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

Pick the job you would use them for

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

61.4Kimi K3—Ornith-1.5-9B

Not comparable · BenchAlign v5.8

The coding row is not comparable on the public lane: at least one model is not measured or not ranked there.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Open the coding leaderboard Shortlist models for this job

Same basis rules as the category table below

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.

HLEKnowledge
Normalized gap 35.8
Kimi K3:56%
Ornith-1.5-9B:20.2%
Kimi K3 source Ornith-1.5-9B source
BrowseCompAgentic
Normalized gap 34.8
Kimi K3:91.2%
Ornith-1.5-9B:56.4%
Kimi K3 source Ornith-1.5-9B source
HLE w/o toolsKnowledge
Normalized gap 23.3
Kimi K3:43.5%
Ornith-1.5-9B:20.2%
Kimi K3 source Ornith-1.5-9B source
GPQAKnowledge
Normalized gap 7.1
Kimi K3:93.5%
Ornith-1.5-9B:86.4%
Kimi K3 source Ornith-1.5-9B source

Bars run 0–100 on each benchmark’s normalized display scale

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.

Agentic

Directional only

Kimi K3: 68.1; Supported · #8/119
Ornith-1.5-9B: 18.0; Estimated · #101/119
Basis: BenchAlign v5.8 lane · 12 vs 7 public rows
Reading: Directional only

Knowledge

Directional only

Kimi K3: 67.9; Supported · #18/171
Ornith-1.5-9B: 30.6; Estimated · #134/171
Basis: BenchAlign v5.8 lane · 6 vs 4 public rows
Reading: Directional only

Coding

Not comparable

Kimi K3: 61.4; Supported · #18/144
Ornith-1.5-9B: Not ranked
Basis: BenchAlign v5.8 lane · 14 vs 5 public rows
Reading: Not comparable

Reasoning

Not comparable

Kimi K3: 65.8; #18/27
Ornith-1.5-9B: Not ranked
Basis: Provisional lane · 1 vs 0 weighted rows
Reading: Not comparable

Multimodal

Not comparable

Kimi K3: 89.4; #1/49
Ornith-1.5-9B: Not ranked
Basis: Provisional lane · 3 vs 0 weighted rows
Reading: Not comparable

Multilingual

Not comparable

Kimi K3: Not ranked
Ornith-1.5-9B: Not ranked
Basis: Provisional lane · 0 vs 0 weighted rows
Reading: Not comparable

Instruction following

Not comparable

Kimi K3: Not ranked
Ornith-1.5-9B: Not ranked
Basis: Provisional lane · 0 vs 0 weighted rows
Reading: Not comparable

Math

Not comparable

Kimi K3: Not ranked
Ornith-1.5-9B: Not ranked
Basis: Provisional lane · 0 vs 0 weighted rows
Reading: Not comparable

Category scores with the server-provided evidence basis for Kimi K3 and Ornith-1.5-9B
Category	Kimi K3	Ornith-1.5-9B	Basis	Reading
Agentic	68.1Supported · #8/119	18.0Estimated · #101/119	Directional onlyBenchAlign v5.8 lane · 12 vs 7 public rows	Directional only
Knowledge	67.9Supported · #18/171	30.6Estimated · #134/171	Directional onlyBenchAlign v5.8 lane · 6 vs 4 public rows	Directional only
Coding	61.4Supported · #18/144	Not ranked	Not comparableBenchAlign v5.8 lane · 14 vs 5 public rows	Not comparable
Reasoning	65.8#18/27	Not ranked	Not comparableProvisional lane · 1 vs 0 weighted rows	Not comparable
Multimodal	89.4#1/49	Not ranked	Not comparableProvisional lane · 3 vs 0 weighted rows	Not comparable
Multilingual	Not ranked	Not ranked	Not comparableProvisional lane · 0 vs 0 weighted rows	Not comparable
Instruction following	Not ranked	Not ranked	Not comparableProvisional lane · 0 vs 0 weighted rows	Not comparable
Math	Not ranked	Not ranked	Not comparableProvisional lane · 0 vs 0 weighted rows	Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

Supported evidence per lane · bars run 0–100Methodology

What each workload costs

Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.

Chat turn

1K fresh input + 500 output tokens

Kimi K3: $0.0105; Fits in one request
Ornith-1.5-9B: Self-hosted; infrastructure cost varies; Fits in one request

Ornith-1.5-9B has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Kimi K3: $0.195; Fits in one request
Ornith-1.5-9B: Self-hosted; infrastructure cost varies; Fits in one request

Ornith-1.5-9B has no comparable published API token rate.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

Kimi K3: $0.27; Fits in one request
Ornith-1.5-9B: Self-hosted; infrastructure cost varies; Fits in one request; Cached-input rate unavailable

Ornith-1.5-9B has no comparable published API token rate.

Cached input falls back to the list input rate only where a cached rate is unpublished

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

SpecificationKimi K3Ornith-1.5-9B

Context window

Maximum documented context; output-token limits may be lower.

Kimi K3

1.05M

Ornith-1.5-9B

262K

Ornith-1.5-9B model card

API model ID

Kimi K3

Not sourced

Ornith-1.5-9B

Not sourced

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

Kimi K3

$0.3 per 1M cached input tokens

Ornith-1.5-9B

No comparable hosted API rate

Ornith-1.5-9B model card

Documented inputs

Kimi K3

Not sourced

Ornith-1.5-9B

Not sourced

Documented outputs

Kimi K3

Not sourced

Ornith-1.5-9B

Not sourced

Provider availability

Kimi K3

Not sourced

Ornith-1.5-9B

Not sourced

Reasoning profile

Kimi K3

Reasoning

Ornith-1.5-9B

Reasoning

Weight access

Kimi K3

Pending

Ornith-1.5-9B

Open Weight

License

Kimi K3

Pending

Ornith-1.5-9B

Open Weight

Release date

Kimi K3

2026-07-16

Ornith-1.5-9B

2026-08-18

If you already use one of these models

Deployment change: The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
Quality signal: Kimi K3 has the higher public point estimate, 72.14 versus 28.63. Their conditional score ranges do not overlap. These ranges do not establish rank confidence.
Workload cost: A complete comparable API-rate estimate is not available for both models.
Context tradeoff: Kimi K3 has the larger documented window (1.05M).

Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Kimi K3 or Ornith-1.5-9B?

Kimi K3 has the higher public point estimate, 72.14 versus 28.63. Their conditional score ranges do not overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, Kimi K3 or Ornith-1.5-9B?

Ornith-1.5-9B is not ranked on the public lane for coding, so no winner is named for coding.

Which is better for agentic tasks, Kimi K3 or Ornith-1.5-9B?

Kimi K3 scores higher for agentic tasks on the public lane, 68.1 to 18. Ornith-1.5-9B is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which costs less, Kimi K3 or Ornith-1.5-9B?

Both models do not have comparable published API token rates, so this page does not name a universal price winner.

Which has the larger context window, Kimi K3 or Ornith-1.5-9B?

Kimi K3 has the larger documented context window: 1.05M, compared with 262K.

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence56 rows

Agentic

Terminal-Bench 2.1
Kimi K388.3%
Source
Ornith-1.5-9B46.2%
Source
Kimi K3 leads this result
BrowseComp
Kimi K391.2%
Source
Ornith-1.5-9B56.4%
Source
Kimi K3 leads this result
DeepSearchQA
Kimi K395.0%
Source
Ornith-1.5-9B—
Not directly comparable
Toolathlon-Verified
Kimi K373.2%
Source
Ornith-1.5-9B41.2%
Source
Kimi K3 leads this result
MCP Atlas
Kimi K384.2%
Source
Ornith-1.5-9B54.2%
Source
Kimi K3 leads this result
AutomationBench
Kimi K330.8%
Source
Ornith-1.5-9B—
Not directly comparable
JobBench
Kimi K352.9%
Source
Ornith-1.5-9B—
Not directly comparable
APEX-Agents
Kimi K337.6%
Source
Ornith-1.5-9B—
Not directly comparable
SpreadsheetBench 2
Kimi K334.8%
Source
Ornith-1.5-9B—
Not directly comparable
DECK-Bench
Kimi K373.5%
Source
Ornith-1.5-9B—
Not directly comparable
Terminal-Bench 2.1 (Vals)
Kimi K380.9%
Source
Ornith-1.5-9B—
Not directly comparable
ApprenticeBench
Kimi K318%
Source
Ornith-1.5-9B—
Not directly comparable
HLE w/ tools
Kimi K3—
Ornith-1.5-9B30.5%
Source
Not directly comparable
WideResearch
Kimi K3—
Ornith-1.5-9B59.5%
Source
Not directly comparable
Claw-Eval
Kimi K3—
Ornith-1.5-9B66.5%
Source
Not directly comparable

Coding

DeepSWE
Kimi K367.5%
Source
Ornith-1.5-9B—
Not directly comparable
CursorBench 3.2
Kimi K360.8%
Source
Ornith-1.5-9B—
Not directly comparable
FrontierSWE
Kimi K381.2%
Source
Ornith-1.5-9B—
Not directly comparable
ProgramBench
Kimi K377.8%
Source
Ornith-1.5-9B—
Not directly comparable
Kimi Code Bench v2
Kimi K372.9%
Source
Ornith-1.5-9B—
Not directly comparable
sweMarathon
Kimi K342%
Source
Ornith-1.5-9B—
Not directly comparable
PostTrain Bench
Kimi K336.6%
Source
Ornith-1.5-9B—
Not directly comparable
MLS-Bench Lite
Kimi K348.3%
Source
Ornith-1.5-9B—
Not directly comparable
VulcanBench v3
Kimi K373.7%
Source
Ornith-1.5-9B—
Not directly comparable
OpenHarmony Bench
Kimi K357.3%
Source
Ornith-1.5-9B—
Not directly comparable
FrontierSWE v2
Kimi K325.9%
Source
Ornith-1.5-9B—
Not directly comparable
LiveCodeBench (Vals)
Kimi K387.2%
Source
Ornith-1.5-9B—
Not directly comparable
SWE-bench (Vals)
Kimi K393.4%
Source
Ornith-1.5-9B—
Not directly comparable
PostTrainBench v1.1
Kimi K332.0%
Source
Ornith-1.5-9B—
Not directly comparable
Terminal-Bench 2.1
Kimi K3—
Ornith-1.5-9B46.2%
Source
Not directly comparable
SWE-bench Verified
Kimi K3—
Ornith-1.5-9B70.6%
Source
Not directly comparable
SWE-bench Pro
Kimi K3—
Ornith-1.5-9B47.5%
Source
Not directly comparable
SWE Multilingual
Kimi K3—
Ornith-1.5-9B54.4%
Source
Not directly comparable
NL2Repo
Kimi K3—
Ornith-1.5-9B32.4%
Source
Not directly comparable

Reasoning

ARC-AGI-1
Kimi K394.50%
Source
Ornith-1.5-9B—
Not directly comparable
ARC-AGI-2
Kimi K360.4%
Source
Ornith-1.5-9B—
Not directly comparable

Multimodal

OfficeQA Pro
Kimi K363.3%
Source
Ornith-1.5-9B—
Not directly comparable
MMMU-Pro
Kimi K381.6%
Source
Ornith-1.5-9B—
Not directly comparable
MMMU-Pro w/ Python
Kimi K383.4%
Source
Ornith-1.5-9B—
Not directly comparable
CharXiv w/o tools
Kimi K384.8%
Source
Ornith-1.5-9B—
Not directly comparable
CharXiv
Kimi K391.3%
Source
Ornith-1.5-9B—
Not directly comparable
MathVision
Kimi K394.3%
Source
Ornith-1.5-9B—
Not directly comparable
MathVision w/ Python
Kimi K397.8%
Source
Ornith-1.5-9B—
Not directly comparable
BabyVision w/ Python
Kimi K385.7%
Source
Ornith-1.5-9B—
Not directly comparable
ZeroBench
Kimi K323.0%
Source
Ornith-1.5-9B—
Not directly comparable
ZeroBench w/ Python
Kimi K341.0%
Source
Ornith-1.5-9B—
Not directly comparable
WorldVQA ForceAnswer
Kimi K351.0%
Source
Ornith-1.5-9B—
Not directly comparable
OmniDocBench
Kimi K391.1%
Source
Ornith-1.5-9B—
Not directly comparable
PerceptionBench
Kimi K358.5%
Source
Ornith-1.5-9B—
Not directly comparable

Knowledge

GPQA
Kimi K393.5%
Source
Ornith-1.5-9B86.4%
Source
Kimi K3 leads this result
GPQA-D
Kimi K393.5%
Source
Ornith-1.5-9B86.4%
Source
Kimi K3 leads this result
HLE
Kimi K356%
Source
Ornith-1.5-9B20.2%
Source
Kimi K3 leads this result
HLE w/o tools
Kimi K343.5%
Source
Ornith-1.5-9B20.2%
Source
Kimi K3 leads this result
GPQA Diamond (Vals)
Kimi K392.9%
Source
Ornith-1.5-9B—
Not directly comparable
MMLU-Pro (Vals)
Kimi K388.0%
Source
Ornith-1.5-9B—
Not directly comparable

Instruction following

Gray Swan IPI (15 attempts)
Kimi K352.7%
Source
Ornith-1.5-9B—
Not directly comparable

56 public results · 8 shared

Related comparisons

Compare API pricing Read the methodology Open the model selector

Watch Kimi K3 vs Ornith-1.5-9B

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 2,000+ readers.

Last updated October 2, 2026

Kimi K3 vs Ornith-1.5-9B

Decision reading

Which one for your work

Long documents

Coding work

Agentic work

Chat turn cost

Cache-heavy agent loop cost

Repository review cost

Which one for a specific job

What is actually comparable

Shape of the matched evidence

Category results, on a stated basis

Agentic

Knowledge

Coding

Reasoning

Multimodal

Multilingual

Instruction following

Math

What each workload costs

Chat turn

Repository review

Cache-heavy agent loop

Specification differences

Context window

API model ID

Cached-input rate

Documented inputs

Documented outputs

Provider availability

Reasoning profile

Weight access

License

Release date

If you already use one of these models

Questions

Which is better, Kimi K3 or Ornith-1.5-9B?

Which is better for coding, Kimi K3 or Ornith-1.5-9B?

Which is better for agentic tasks, Kimi K3 or Ornith-1.5-9B?

Which costs less, Kimi K3 or Ornith-1.5-9B?

Which has the larger context window, Kimi K3 or Ornith-1.5-9B?

Benchmark evidence

Agentic

Coding

Reasoning

Multimodal

Knowledge

Instruction following

Related comparisons

Watch Kimi K3 vs Ornith-1.5-9B