Reasoning
Like-for-like- Agents-A1
- 60.2
- Kimi K2.5
- 61.0
- Weighted basis
- 1 vs 1 rows
- Reading
- Kimi K2.5 leads
Agents-A1 vs Kimi K2.5
Updated August 21, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Agents-A1 has the higher public score estimate, 61.25 versus 58.68, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
4 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.
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
Agents-A1
Agents-A1 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
No shared weighted benchmark basis supports a winner.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
The category averages use different weighted benchmark sets, so they are 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: rate-fallback
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
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
2 Agents-A1 only
4 Shared
41 Kimi K2.5 only
- Shared results
- 4
- Agents-A1 only
- 2
- Kimi K2.5 only
- 41
- Like-for-like categories
- 2 / 8
2 categories use different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.
Instruction following
Like-for-like- Agents-A1
- 94.8
- Kimi K2.5
- 93.9
- Weighted basis
- 1 vs 1 rows
- Reading
- Agents-A1 leads
Agentic
Directional only- Agents-A1
- 75.5
- Kimi K2.5
- 55.0
- Weighted basis
- 1 vs 2 rows
- Reading
- Directional only
Knowledge
Directional only- Agents-A1
- 47.6
- Kimi K2.5
- 56.9
- Weighted basis
- 1 vs 4 rows
- Reading
- Directional only
Coding
Not comparable- Agents-A1
- Not measured
- Kimi K2.5
- 59.4
- Weighted basis
- 0 vs 4 rows
- Reading
- Not comparable
Math
Not comparable- Agents-A1
- Not measured
- Kimi K2.5
- 60.6
- Weighted basis
- 0 vs 4 rows
- Reading
- Not comparable
Multilingual
Not comparable- Agents-A1
- Not measured
- Kimi K2.5
- 82.3
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Multimodal
Not comparable- Agents-A1
- Not measured
- Kimi K2.5
- 78.5
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
| Category | Agents-A1 | Kimi K2.5 | Weighted basis | Reading |
|---|---|---|---|---|
| Reasoning | 60.2 | 61.0 | Like-for-like1 vs 1 rows | Kimi K2.5 leads |
| Instruction following | 94.8 | 93.9 | Like-for-like1 vs 1 rows | Agents-A1 leads |
| Agentic | 75.5 | 55.0 | Directional only1 vs 2 rows | Directional only |
| Knowledge | 47.6 | 56.9 | Directional only1 vs 4 rows | Directional only |
| Coding | Not measured | 59.4 | Not comparable0 vs 4 rows | Not comparable |
| Math | Not measured | 60.6 | Not comparable0 vs 4 rows | Not comparable |
| Multilingual | Not measured | 82.3 | Not comparable0 vs 1 rows | Not comparable |
| Multimodal | Not measured | 78.5 | Not comparable0 vs 1 rows | Not comparable |
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.
HLE
Knowledge
BrowseComp
Agentic
IFEval
Instruction following
LongBench v2
Reasoning
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
- Agents-A1
- API rate not published
- Fits in one request
- Kimi K2.5
- $0.0021
- Fits in one request
Agents-A1 has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Agents-A1
- API rate not published
- Fits in one request
- Kimi K2.5
- $0.039
- Fits in one request
Agents-A1 has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Agents-A1
- API rate not published
- Fits in one request
- Cached-input rate unavailable
- Kimi K2.5
- $0.162
- Fits in one request
- Cached input priced at the published list-input rate
Kimi K2.5 has no published cached-input rate, so cached tokens use its listed input rate. Agents-A1 has no comparable published API token rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationAgents-A1Kimi K2.5
Context window
Maximum documented context; output-token limits may be lower.
Agents-A1
262K
Kimi K2.5
256K
API model ID
Agents-A1
Not sourced
Kimi K2.5
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Agents-A1
No comparable hosted API rate
Kimi K2.5
Not published
Documented inputs
Agents-A1
Not sourced
Kimi K2.5
Not sourced
Documented outputs
Agents-A1
Not sourced
Kimi K2.5
Not sourced
Provider availability
Agents-A1
Not sourced
Kimi K2.5
Not sourced
Reasoning profile
Agents-A1
Reasoning
Kimi K2.5
Non-Reasoning
Weight access
Agents-A1
Open Weight
Kimi K2.5
Open Weight
License
Agents-A1
Open Weight
Kimi K2.5
Open Weight
Release date
Agents-A1
2026-06-26
Kimi K2.5
2026-02-01
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
- Agents-A1 has the higher public score estimate, 61.25 versus 58.68, but the 90% score intervals overlap.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- Agents-A1 has the larger documented window (262K).
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.
Agents-A1
API / mo$0
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Kimi K2.5
API / mo$2,700
Self-host / mo$5,221
Break-even132M/day
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence47 rows
Agentic
BrowseComp
Agents-A175.5%SourceKimi K2.560.6%SourceAgents-A1 leads this result
HLE w/ tools
Agents-A147.6%SourceKimi K2.5—Not directly comparable
VITA-Bench
Agents-A138.8%SourceKimi K2.5—Not directly comparable
Terminal-Bench 2.0
Agents-A1—Kimi K2.550.8%SourceNot directly comparable
Claw-Eval
Agents-A1—Kimi K2.552.3%SourceNot directly comparable
QwenClawBench
Agents-A1—Kimi K2.554.3%SourceNot directly comparable
τ³-bench results
Agents-A1—Kimi K2.565.7%SourceNot directly comparable
DeepSearchQA
Agents-A1—Kimi K2.577.1%SourceNot directly comparable
DeepPlanning
Agents-A1—Kimi K2.514.4%SourceNot directly comparable
Toolathlon
Agents-A1—Kimi K2.527.8%SourceNot directly comparable
MCP Atlas
Agents-A1—Kimi K2.529.5%SourceNot directly comparable
MCP-Tasks
Agents-A1—Kimi K2.559.1%SourceNot directly comparable
WideResearch
Agents-A1—Kimi K2.572.7%SourceNot directly comparable
Gert Labs
Agents-A1—Kimi K2.545.88%SourceNot directly comparable
ResearchClawBench
Agents-A1—Kimi K2.514.0%SourceNot directly comparable
JobBench
Agents-A1—Kimi K2.58.7%SourceNot directly comparable
Coding
SWE-bench Verified
Agents-A1—Kimi K2.576.8%SourceNot directly comparable
SWE-bench Verified*
Agents-A1—Kimi K2.570.8%SourceNot directly comparable
LiveCodeBench v6
Agents-A1—Kimi K2.585.0%SourceNot directly comparable
SWE-bench Pro
Agents-A1—Kimi K2.550.7%SourceNot directly comparable
SWE Multilingual
Agents-A1—Kimi K2.573%SourceNot directly comparable
SWE-Rebench
Agents-A1—Kimi K2.558.5%SourceNot directly comparable
React Native Evals
Agents-A1—Kimi K2.577.2%SourceNot directly comparable
SciCode
Agents-A1—Kimi K2.548.7%SourceNot directly comparable
Reasoning
Knowledge
HLE
Agents-A147.6%SourceKimi K2.530.1%SourceAgents-A1 leads this result
GPQA
Agents-A1—Kimi K2.587.6%SourceNot directly comparable
GPQA-D
Agents-A1—Kimi K2.587.6%SourceNot directly comparable
SuperGPQA
Agents-A1—Kimi K2.569.2%SourceNot directly comparable
MMLU-Pro
Agents-A1—Kimi K2.587.1%SourceNot directly comparable
MMLU-Pro (Arcee)
Agents-A1—Kimi K2.587.1%SourceNot directly comparable
Math
AIME 2025
Agents-A1—Kimi K2.596.1%SourceNot directly comparable
AIME26
Agents-A1—Kimi K2.595.8%SourceNot directly comparable
AIME25 (Arcee)
Agents-A1—Kimi K2.596.3%SourceNot directly comparable
HMMT Feb 2025
Agents-A1—Kimi K2.595.4%SourceNot directly comparable
HMMT Nov 2025
Agents-A1—Kimi K2.591.1%SourceNot directly comparable
HMMT Feb 2026
Agents-A1—Kimi K2.587.1%SourceNot directly comparable
MMAnswerBench
Agents-A1—Kimi K2.581.8%SourceNot directly comparable
FrontierMath v2 (Tiers 1-3)
Agents-A1—Kimi K2.527.900%SourceNot directly comparable
FrontierMath v2 (Tier 4)
Agents-A1—Kimi K2.54.200%SourceNot directly comparable
Multilingual
Multimodal
Instruction following
Frequently asked questions
Which is better, Agents-A1 or Kimi K2.5?
Agents-A1 has the higher public score estimate, 61.25 versus 58.68, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, Agents-A1 or Kimi K2.5?
The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.
Which is better for agentic tasks, Agents-A1 or Kimi K2.5?
The current agentic tasks averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.
Which costs less, Agents-A1 or Kimi K2.5?
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, Agents-A1 or Kimi K2.5?
Agents-A1 has the larger documented context window: 262K, compared with 256K.
Related comparisons
Last updated August 21, 2026
Watch Agents-A1 vs Kimi K2.5
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.