Long documents
Prompts that approach the documented context limit
Kimi K3
Kimi K3 has the larger documented context window.
Confidence: documented
Celeris-1 vs Kimi K3
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.
Both of these models will change. Get the price, version and retirement notices for the pair, each with its source. Follow model changes
Share or export
Decision reading
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. Use the documented cost, context, and runtime rows instead. 0 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
- Shared results
- 0
- Celeris-1 only
- 4
- Kimi K3 only
- 48
- Like-for-like categories
- 1 / 8
Estimated: Celeris-1 · Supported: Kimi K3. 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.
Show secondary and unsupported calls
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Celeris-1 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limitedAgentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Celeris-1 is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limitedChat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. Celeris-1 does not fit this workload in one request.
Confidence: listed-ratesCache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. Celeris-1 does not fit this workload in one request. Celeris-1 has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallbackRepository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. Celeris-1 does not fit this workload in one request.
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.
The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.
13.3Celeris-161.4Kimi K3
Directional only · BenchAlign v5.8
Kimi K3 has the higher coding point estimate. Conditional score ranges do not establish rank confidence.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
Same basis rules as the category table below
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
4 Celeris-1 only
48 Kimi K3 only
2 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
A shared-evidence shape is not available.
BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.
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.
Knowledge
Like-for-like- Celeris-1
- 26.5
- Supported · #149/171
- Kimi K3
- 67.9
- Supported · #18/171
- Basis
- BenchAlign v5.8 lane · 1 vs 6 public rows
- Reading
- Kimi K3 leads
Agentic
Directional only- Celeris-1
- 6.5
- Estimated · #115/119
- Kimi K3
- 68.1
- Supported · #8/119
- Basis
- BenchAlign v5.8 lane · 0 vs 12 public rows
- Reading
- Directional only
Coding
Directional only- Celeris-1
- 13.3
- Estimated · #137/144
- Kimi K3
- 61.4
- Supported · #18/144
- Basis
- BenchAlign v5.8 lane · 0 vs 14 public rows
- Reading
- Directional only
Reasoning
Not comparable- Celeris-1
- 48.3
- Unranked · 3 rankable rows
- Kimi K3
- 65.8
- #18/27
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Celeris-1
- Not ranked
- Kimi K3
- 89.4
- #1/49
- Basis
- Provisional lane · 0 vs 3 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Celeris-1
- Not ranked
- Kimi K3
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Celeris-1
- Not ranked
- Kimi K3
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Celeris-1
- Not ranked
- Kimi K3
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Celeris-1 | Kimi K3 | Basis | Reading |
|---|---|---|---|---|
| Knowledge | 26.5Supported · #149/171 | 67.9Supported · #18/171 | Like-for-likeBenchAlign v5.8 lane · 1 vs 6 public rows | Kimi K3 leads |
| Agentic | 6.5Estimated · #115/119 | 68.1Supported · #8/119 | Directional onlyBenchAlign v5.8 lane · 0 vs 12 public rows | Directional only |
| Coding | 13.3Estimated · #137/144 | 61.4Supported · #18/144 | Directional onlyBenchAlign v5.8 lane · 0 vs 14 public rows | Directional only |
| Reasoning | 48.3Unranked · 3 rankable rows | 65.8#18/27 | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Multimodal | Not ranked | 89.4#1/49 | Not comparableProvisional lane · 0 vs 3 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
- Celeris-1
- $0.00055
- Does not fit in one request
- Kimi K3
- $0.0105
- Fits in one request
Celeris-1 does not fit this workload in one request.
Repository review
50K fresh input + 3K output tokens
- Celeris-1
- $0.0121
- Does not fit in one request
- Kimi K3
- $0.195
- Fits in one request
Celeris-1 does not fit this workload in one request.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Celeris-1
- $0.051
- Does not fit in one request
- Cached input priced at the published list-input rate
- Kimi K3
- $0.27
- Fits in one request
Celeris-1 does not fit this workload in one request. Celeris-1 has no published cached-input rate, so cached tokens use its listed input 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.
SpecificationCeleris-1Kimi K3
Context window
Maximum documented context; output-token limits may be lower.
Celeris-1
131,072 tokens
Celeris-1 model guideKimi K3
1.05M
API model ID
Celeris-1
celeris-1
Celeris-1 model guideKimi K3
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Celeris-1
Not published
Celeris API pricingKimi K3
$0.3 per 1M cached input tokens
Documented inputs
Celeris-1
text, image
Celeris-1 model guideKimi K3
Not sourced
Documented outputs
Celeris-1
Kimi K3
Not sourced
Provider availability
Celeris-1
Generally Available · Celeris OpenAI-compatible API (United States)
Celeris availabilityKimi K3
Not sourced
Reasoning profile
Celeris-1
Non-Reasoning
Kimi K3
Reasoning
Weight access
Celeris-1
Proprietary
Kimi K3
Pending
License
Celeris-1
Proprietary
Kimi K3
Pending
Release date
Celeris-1
2026-07-22
Kimi K3
2026-07-16
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
- The public evidence has no benchmark result shared by both models, so it does not support a quality verdict.
- Workload cost
- Repository review: $0.0121 vs $0.195. Cache-heavy agent loop: $0.051 vs $0.27.
- 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, Celeris-1 or Kimi K3?
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, Celeris-1 or Kimi K3?
Kimi K3 scores higher for coding on the public lane, 61.4 to 13.3. Celeris-1 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which is better for agentic tasks, Celeris-1 or Kimi K3?
Kimi K3 scores higher for agentic tasks on the public lane, 68.1 to 6.5. Celeris-1 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, Celeris-1 or Kimi K3?
For the stated presets, chat costs $0.00055 on Celeris-1 and $0.0105 on Kimi K3; repository review costs $0.0121 and $0.195; the cache-heavy agent loop costs $0.051 and $0.27. Celeris-1 does not fit this workload in one request. Celeris-1 has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Celeris-1 or Kimi K3?
Kimi K3 has the larger documented context window: 1.05M, compared with 131,072 tokens.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence52 rows
Agentic
Terminal-Bench 2.1
Celeris-1—Kimi K388.3%SourceNot directly comparable
BrowseComp
Celeris-1—Kimi K391.2%SourceNot directly comparable
DeepSearchQA
Celeris-1—Kimi K395.0%SourceNot directly comparable
Toolathlon-Verified
Celeris-1—Kimi K373.2%SourceNot directly comparable
MCP Atlas
Celeris-1—Kimi K384.2%SourceNot directly comparable
AutomationBench
Celeris-1—Kimi K330.8%SourceNot directly comparable
JobBench
Celeris-1—Kimi K352.9%SourceNot directly comparable
APEX-Agents
Celeris-1—Kimi K337.6%SourceNot directly comparable
SpreadsheetBench 2
Celeris-1—Kimi K334.8%SourceNot directly comparable
DECK-Bench
Celeris-1—Kimi K373.5%SourceNot directly comparable
Terminal-Bench 2.1 (Vals)
Celeris-1—Kimi K380.9%SourceNot directly comparable
ApprenticeBench
Celeris-1—Kimi K318%SourceNot directly comparable
Coding
DeepSWE
Celeris-1—Kimi K367.5%SourceNot directly comparable
CursorBench 3.2
Celeris-1—Kimi K360.8%SourceNot directly comparable
FrontierSWE
Celeris-1—Kimi K381.2%SourceNot directly comparable
ProgramBench
Celeris-1—Kimi K377.8%SourceNot directly comparable
Kimi Code Bench v2
Celeris-1—Kimi K372.9%SourceNot directly comparable
sweMarathon
Celeris-1—Kimi K342%SourceNot directly comparable
PostTrain Bench
Celeris-1—Kimi K336.6%SourceNot directly comparable
MLS-Bench Lite
Celeris-1—Kimi K348.3%SourceNot directly comparable
VulcanBench v3
Celeris-1—Kimi K373.7%SourceNot directly comparable
OpenHarmony Bench
Celeris-1—Kimi K357.3%SourceNot directly comparable
FrontierSWE v2
Celeris-1—Kimi K325.9%SourceNot directly comparable
LiveCodeBench (Vals)
Celeris-1—Kimi K387.2%SourceNot directly comparable
SWE-bench (Vals)
Celeris-1—Kimi K393.4%SourceNot directly comparable
PostTrainBench v1.1
Celeris-1—Kimi K332.0%SourceNot directly comparable
Reasoning
Multimodal
OfficeQA Pro
Celeris-1—Kimi K363.3%SourceNot directly comparable
MMMU-Pro
Celeris-1—Kimi K381.6%SourceNot directly comparable
MMMU-Pro w/ Python
Celeris-1—Kimi K383.4%SourceNot directly comparable
CharXiv w/o tools
Celeris-1—Kimi K384.8%SourceNot directly comparable
CharXiv
Celeris-1—Kimi K391.3%SourceNot directly comparable
MathVision
Celeris-1—Kimi K394.3%SourceNot directly comparable
MathVision w/ Python
Celeris-1—Kimi K397.8%SourceNot directly comparable
BabyVision w/ Python
Celeris-1—Kimi K385.7%SourceNot directly comparable
ZeroBench
Celeris-1—Kimi K323.0%SourceNot directly comparable
ZeroBench w/ Python
Celeris-1—Kimi K341.0%SourceNot directly comparable
WorldVQA ForceAnswer
Celeris-1—Kimi K351.0%SourceNot directly comparable
OmniDocBench
Celeris-1—Kimi K391.1%SourceNot directly comparable
PerceptionBench
Celeris-1—Kimi K358.5%SourceNot directly comparable
Knowledge
MMLU-Pro
Celeris-175.9%SourceKimi K3—Not directly comparable
GPQA
Celeris-1—Kimi K393.5%SourceNot directly comparable
GPQA-D
Celeris-1—Kimi K393.5%SourceNot directly comparable
HLE
Celeris-1—Kimi K356%SourceNot directly comparable
HLE w/o tools
Celeris-1—Kimi K343.5%SourceNot directly comparable
GPQA Diamond (Vals)
Celeris-1—Kimi K392.9%SourceNot directly comparable
MMLU-Pro (Vals)
Celeris-1—Kimi K388.0%SourceNot directly comparable
Instruction following
Math
GSM8K
Celeris-193.7%SourceKimi K3—Not directly comparable
52 public results · 0 shared
Watch Celeris-1 vs Kimi K3
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.
Last updated October 2, 2026