Agentic
Directional only- Kimi K2.5
- 46.0
- Estimated · #90/151
- Kimi K2.5 (Reasoning)
- 49.9
- Estimated · #67/151
- Basis
- BenchAlign lane · 14 vs 3 public rows
- Reading
- Directional only
Kimi K2.5 vs Kimi K2.5 (Reasoning)
Updated September 4, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload. This is a same-family comparison, so migration details appear when the source data supports them.
Decision reading
Kimi K2.5 (Reasoning) has the higher public score estimate, 58.74 versus 55.62, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
8 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Share or export
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.
No workload recommendation clears the current evidence threshold.
Use the matched evidence, workload costs, and sourced specifications below instead of treating a point score as a universal answer.
Show secondary and unsupported calls
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Kimi K2.5 and Kimi K2.5 (Reasoning) are scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Kimi K2.5 and Kimi K2.5 (Reasoning) are scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limited
Long documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documented
Chat turn cost
1K fresh input + 500 output tokens
No clear pick
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
No clear pick
A complete comparable API-rate estimate is not available for both models.
Confidence: rate-fallback
Repository review cost
50K fresh input + 3K output tokens
No clear pick
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
37 Kimi K2.5 only
8 Shared
1 Kimi K2.5 (Reasoning) only
- Shared results
- 8
- Kimi K2.5 only
- 37
- Kimi K2.5 (Reasoning) only
- 1
- Like-for-like categories
- 0 / 8
3 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign 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.
Coding
Directional only- Kimi K2.5
- 51.5
- Estimated · #64/183
- Kimi K2.5 (Reasoning)
- 52.9
- Estimated · #52/183
- Basis
- BenchAlign lane · 8 vs 2 public rows
- Reading
- Directional only
Knowledge
Directional only- Kimi K2.5
- 53.1
- Estimated · #70/181
- Kimi K2.5 (Reasoning)
- 52.4
- Estimated · #78/181
- Basis
- BenchAlign lane · 6 vs 2 public rows
- Reading
- Directional only
Reasoning
Not comparable- Kimi K2.5
- 53.5
- Unranked · 3 rankable rows
- Kimi K2.5 (Reasoning)
- Not ranked
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Kimi K2.5
- 62.4
- #5/7
- Kimi K2.5 (Reasoning)
- Not ranked
- Basis
- Provisional lane · 4 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Kimi K2.5
- 38.2
- #8/12
- Kimi K2.5 (Reasoning)
- Not ranked
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Kimi K2.5
- 65.7
- #24/48
- Kimi K2.5 (Reasoning)
- 63.2
- Unranked · 1 rankable row
- Basis
- Provisional lane · 1 vs 1 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Kimi K2.5
- 85.6
- #40/120
- Kimi K2.5 (Reasoning)
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Kimi K2.5 | Kimi K2.5 (Reasoning) | Basis | Reading |
|---|---|---|---|---|
| Agentic | 46.0Estimated · #90/151 | 49.9Estimated · #67/151 | Directional onlyBenchAlign lane · 14 vs 3 public rows | Directional only |
| Coding | 51.5Estimated · #64/183 | 52.9Estimated · #52/183 | Directional onlyBenchAlign lane · 8 vs 2 public rows | Directional only |
| Knowledge | 53.1Estimated · #70/181 | 52.4Estimated · #78/181 | Directional onlyBenchAlign lane · 6 vs 2 public rows | Directional only |
| Reasoning | 53.5Unranked · 3 rankable rows | Not ranked | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Math | 62.4#5/7 | Not ranked | Not comparableProvisional lane · 4 vs 0 weighted rows | Not comparable |
| Multilingual | 38.2#8/12 | Not ranked | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Multimodal | 65.7#24/48 | 63.2Unranked · 1 rankable row | Not comparableProvisional lane · 1 vs 1 weighted rows | Not comparable |
| Instruction following | 85.6#40/120 | 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) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
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.
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 K2.5
- $0.0021
- Fits in one request
- Kimi K2.5 (Reasoning)
- $0.0021
- Fits in one request
Modeled costs are equal
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Kimi K2.5
- $0.039
- Fits in one request
- Kimi K2.5 (Reasoning)
- $0.039
- Fits in one request
Modeled costs are equal
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Kimi K2.5
- $0.162
- Fits in one request
- Cached input priced at the published list-input rate
- Kimi K2.5 (Reasoning)
- $0.162
- Fits in one request
- Cached input priced at the published list-input rate
Modeled costs are equal
Kimi K2.5 has no published cached-input rate, so cached tokens use its listed input rate. Kimi K2.5 (Reasoning) has no published cached-input rate, so cached tokens use its listed input rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationKimi K2.5Kimi K2.5 (Reasoning)
Context window
Maximum documented context; output-token limits may be lower.
Kimi K2.5
256K
Kimi K2.5 (Reasoning)
256K
API model ID
Kimi K2.5
Not sourced
Kimi K2.5 (Reasoning)
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Kimi K2.5
Not published
Kimi K2.5 (Reasoning)
Not published
Documented inputs
Kimi K2.5
Not sourced
Kimi K2.5 (Reasoning)
Not sourced
Documented outputs
Kimi K2.5
Not sourced
Kimi K2.5 (Reasoning)
Not sourced
Provider availability
Kimi K2.5
Not sourced
Kimi K2.5 (Reasoning)
Not sourced
Reasoning profile
Kimi K2.5
Non-Reasoning
Kimi K2.5 (Reasoning)
Reasoning
Weight access
Kimi K2.5
Open Weight
Kimi K2.5 (Reasoning)
Proprietary
License
Kimi K2.5
Open Weight
Kimi K2.5 (Reasoning)
Proprietary
Release date
Kimi K2.5
2026-02-01
Kimi K2.5 (Reasoning)
2026-02-01
If you are choosing between sibling variants
- Deployment change
- Both entries list Moonshot AI as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
- Quality signal
- Kimi K2.5 (Reasoning) has the higher public score estimate, 58.74 versus 55.62, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.039 vs $0.039. Cache-heavy agent loop: $0.162 vs $0.162.
- Context tradeoff
- Both models list 256K.
Run the same representative tasks against both endpoints before changing production traffic.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Kimi K2.5
API / mo$2,700
Self-host / mo$5,221
Break-even132M/day
Kimi K2.5 (Reasoning)
API / mo$2,700
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence46 rows
Agentic
Terminal-Bench 2.0
Kimi K2.550.8%SourceKimi K2.5 (Reasoning)50.8%SourceTie
BrowseComp
Shared sourceKimi K2.560.6%Kimi K2.5 (Reasoning)60.6%Tie
Claw-Eval
Kimi K2.552.3%SourceKimi K2.5 (Reasoning)—Not directly comparable
QwenClawBench
Kimi K2.554.3%SourceKimi K2.5 (Reasoning)—Not directly comparable
τ³-bench results
Kimi K2.565.7%SourceKimi K2.5 (Reasoning)—Not directly comparable
DeepSearchQA
Kimi K2.577.1%SourceKimi K2.5 (Reasoning)—Not directly comparable
DeepPlanning
Kimi K2.514.4%SourceKimi K2.5 (Reasoning)—Not directly comparable
Toolathlon
Kimi K2.527.8%SourceKimi K2.5 (Reasoning)—Not directly comparable
MCP Atlas
Kimi K2.529.5%SourceKimi K2.5 (Reasoning)—Not directly comparable
MCP-Tasks
Kimi K2.559.1%SourceKimi K2.5 (Reasoning)—Not directly comparable
WideResearch
Kimi K2.572.7%SourceKimi K2.5 (Reasoning)—Not directly comparable
Gert Labs
Shared sourceKimi K2.545.88%Kimi K2.5 (Reasoning)32.58%Kimi K2.5 leads this result
ResearchClawBench
Kimi K2.514.0%SourceKimi K2.5 (Reasoning)—Not directly comparable
JobBench
Kimi K2.58.7%SourceKimi K2.5 (Reasoning)—Not directly comparable
Coding
SWE-bench Verified
Kimi K2.576.8%SourceKimi K2.5 (Reasoning)76.8%SourceTie
SWE-bench Verified*
Kimi K2.570.8%SourceKimi K2.5 (Reasoning)—Not directly comparable
LiveCodeBench v6
Kimi K2.585.0%SourceKimi K2.5 (Reasoning)—Not directly comparable
SWE-bench Pro
Kimi K2.550.7%SourceKimi K2.5 (Reasoning)—Not directly comparable
SWE Multilingual
Kimi K2.573%SourceKimi K2.5 (Reasoning)—Not directly comparable
SWE-Rebench
Kimi K2.558.5%SourceKimi K2.5 (Reasoning)—Not directly comparable
React Native Evals
Kimi K2.577.2%SourceKimi K2.5 (Reasoning)—Not directly comparable
SciCode
Kimi K2.548.7%SourceKimi K2.5 (Reasoning)—Not directly comparable
Vibe Code Bench
Kimi K2.5—Kimi K2.5 (Reasoning)17.54%SourceNot directly comparable
Reasoning
LongBench v2
Kimi K2.561%SourceKimi K2.5 (Reasoning)—Not directly comparable
Knowledge
GPQA
Shared sourceKimi K2.587.6%Kimi K2.5 (Reasoning)87.6%Tie
GPQA-D
Kimi K2.587.6%SourceKimi K2.5 (Reasoning)—Not directly comparable
SuperGPQA
Kimi K2.569.2%SourceKimi K2.5 (Reasoning)—Not directly comparable
MMLU-Pro
Shared sourceKimi K2.587.1%Kimi K2.5 (Reasoning)87.1%Tie
MMLU-Pro (Arcee)
Kimi K2.587.1%SourceKimi K2.5 (Reasoning)—Not directly comparable
HLE
Kimi K2.530.1%SourceKimi K2.5 (Reasoning)—Not directly comparable
Math
AIME 2025
Shared sourceKimi K2.596.1%Kimi K2.5 (Reasoning)96.1%Tie
AIME26
Kimi K2.595.8%SourceKimi K2.5 (Reasoning)—Not directly comparable
AIME25 (Arcee)
Kimi K2.596.3%SourceKimi K2.5 (Reasoning)—Not directly comparable
HMMT Feb 2025
Kimi K2.595.4%SourceKimi K2.5 (Reasoning)—Not directly comparable
HMMT Nov 2025
Kimi K2.591.1%SourceKimi K2.5 (Reasoning)—Not directly comparable
HMMT Feb 2026
Kimi K2.587.1%SourceKimi K2.5 (Reasoning)—Not directly comparable
MMAnswerBench
Kimi K2.581.8%SourceKimi K2.5 (Reasoning)—Not directly comparable
FrontierMath v2 (Tiers 1-3)
Kimi K2.527.900%SourceKimi K2.5 (Reasoning)—Not directly comparable
FrontierMath v2 (Tier 4)
Kimi K2.54.200%SourceKimi K2.5 (Reasoning)—Not directly comparable
Multilingual
Multimodal
MMMU-Pro
Shared sourceKimi K2.578.5%Kimi K2.5 (Reasoning)78.5%Tie
Video-MME
Kimi K2.587.4%SourceKimi K2.5 (Reasoning)—Not directly comparable
MMVU
Kimi K2.580.4%SourceKimi K2.5 (Reasoning)—Not directly comparable
VideoMMMU
Kimi K2.586.6%SourceKimi K2.5 (Reasoning)—Not directly comparable
Instruction following
IFEval
Kimi K2.593.9%SourceKimi K2.5 (Reasoning)—Not directly comparable
Frequently asked questions
Which is better, Kimi K2.5 or Kimi K2.5 (Reasoning)?
Kimi K2.5 (Reasoning) has the higher public score estimate, 58.74 versus 55.62, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, Kimi K2.5 or Kimi K2.5 (Reasoning)?
Kimi K2.5 (Reasoning) scores higher for coding on the public lane, 52.9 to 51.5. Kimi K2.5 and Kimi K2.5 (Reasoning) are 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, Kimi K2.5 or Kimi K2.5 (Reasoning)?
Kimi K2.5 (Reasoning) scores higher for agentic tasks on the public lane, 49.9 to 46. Kimi K2.5 and Kimi K2.5 (Reasoning) are 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 K2.5 or Kimi K2.5 (Reasoning)?
For the stated presets, chat costs $0.0021 on Kimi K2.5 and $0.0021 on Kimi K2.5 (Reasoning); repository review costs $0.039 and $0.039; the cache-heavy agent loop costs $0.162 and $0.162. Kimi K2.5 has no published cached-input rate, so cached tokens use its listed input rate. Kimi K2.5 (Reasoning) has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Kimi K2.5 or Kimi K2.5 (Reasoning)?
Both models list the same context window, 256K.
Related comparisons
Last updated September 4, 2026
Watch Kimi K2.5 vs Kimi K2.5 (Reasoning)
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.