Updated October 10, 2026. Rank says Kimi K2.6 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
Kimi K2.6 has the higher public point estimate, 58.74 versus 48.62. Their conditional score ranges overlap. These ranges do not establish rank confidence. 17 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
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.
Code generation, repair, and software-engineering tasks
Kimi K2.6
Kimi K2.6 has the higher public coding point estimate, 43.9 to 35.3, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Tool use, computer use, and multi-step task completion
Kimi K2.6
Kimi K2.6 has the higher public agentic point estimate, 43.7 to 31.4, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Prompts that approach the documented context limit
Kimi K2.6
Kimi K2.6 has the larger documented context window.
1K fresh input + 500 output tokens
MiniMax M2.7
MiniMax M2.7 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
50K fresh input + 3K output tokens
MiniMax M2.7
MiniMax M2.7 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
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. MiniMax M2.7 does not fit this workload in one request. MiniMax M2.7 has no published cached-input rate, so cached tokens use its listed input rate.
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.
Like-for-like · BenchAlign v5.8
Kimi K2.6 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.
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
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.
HMMT Feb 2026Math
Normalized gap 20.0Terminal-Bench 2.0Agentic
Normalized gap 9.7MMLU-Pro (Vals)Knowledge
Normalized gap 7.2LiveCodeBench (Vals)Coding
Normalized gap 6.9HLEKnowledge
Normalized gap 6.7Each 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.
| Category | Kimi K2.6 | MiniMax M2.7 | Basis | Reading |
|---|---|---|---|---|
| Agentic | 43.7Supported · #57/123 | 31.4Supported · #84/123 | Like-for-likeBenchAlign v5.8 lane · 12 vs 8 public rows | Kimi K2.6 leads · intervals overlap |
| Coding | 43.9Supported · #54/146 | 35.3Supported · #76/146 | Like-for-likeBenchAlign v5.8 lane · 10 vs 12 public rows | Kimi K2.6 leads · intervals overlap |
| Knowledge | 59.8Supported · #45/177 | 46.1Supported · #90/177 | Like-for-likeBenchAlign v5.8 lane · 5 vs 5 public rows | Kimi K2.6 leads · intervals overlap |
| Reasoning | Not ranked | 79.9Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | 73.8#27/54 | Not ranked | Not comparableProvisional lane · 2 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 | 93.0#13/127 | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 72.2#1/7 | 63.8Unranked · 4 rankable rows | Not comparableProvisional lane · 4 vs 2 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.
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.
1K fresh input + 500 output tokens
MiniMax M2.7 has the lower modeled cost
Costs use the listed standard API rates.
50K fresh input + 3K output tokens
MiniMax M2.7 has the lower modeled cost
Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
MiniMax M2.7 does not fit this workload in one request. MiniMax M2.7 has no published cached-input rate, so cached tokens use its listed input rate.
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
Maximum documented context; output-token limits may be lower.
Kimi K2.6
256K
MiniMax M2.7
200K
Kimi K2.6
Not sourced
MiniMax M2.7
Not sourced
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Kimi K2.6
$0.16 per 1M cached input tokens
MiniMax M2.7
Not published
Kimi K2.6
Not sourced
MiniMax M2.7
Not sourced
Kimi K2.6
Not sourced
MiniMax M2.7
Not sourced
Kimi K2.6
Not sourced
MiniMax M2.7
Not sourced
Kimi K2.6
Reasoning
MiniMax M2.7
Non-Reasoning
Kimi K2.6
Open Weight
MiniMax M2.7
Open Weight
Kimi K2.6
Open Weight
MiniMax M2.7
Open Weight
Kimi K2.6
2026-04-20
MiniMax M2.7
2026-03-18
Kimi K2.6 has the higher public point estimate, 58.74 versus 48.62. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.
Kimi K2.6 has the higher public coding point estimate, 43.9 to 35.3, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Kimi K2.6 has the higher public agentic tasks point estimate, 43.7 to 31.4, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
For the stated presets, chat costs $0.00295 on Kimi K2.6 and $0.0009 on MiniMax M2.7; repository review costs $0.0595 and $0.0186; the cache-heavy agent loop costs $0.091 and $0.078. MiniMax M2.7 does not fit this workload in one request. MiniMax M2.7 has no published cached-input rate, so cached tokens use its listed input rate.
Kimi K2.6 has the larger documented context window: 256K, compared with 200K.
Estimates at 50,000 req/day · 1000 tokens/req average.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Terminal-Bench 2.0
Kimi K2.6 leads this result
BrowseComp
Not directly comparable
OSWorld-Verified
Not directly comparable
Toolathlon
Kimi K2.6 leads this result
MCP Atlas
Not directly comparable
Claw-Eval
Shared sourceKimi K2.6 leads this result
DeepSearchQA
Not directly comparable
WideResearch
Not directly comparable
Gert Labs
Shared sourceKimi K2.6 leads this result
ResearchClawBench
Not directly comparable
OSWorld 2.0
Not directly comparable
Terminal-Bench 2.1 (Vals)
Kimi K2.6 leads this result
τ³-bench results
Not directly comparable
MLE-Bench Lite
Not directly comparable
MM-ClawBench
Not directly comparable
SWE-bench Verified
Not directly comparable
LiveCodeBench v6
Not directly comparable
SWE-bench Pro
Kimi K2.6 leads this result
SWE Multilingual
Kimi K2.6 leads this result
SciCode
Not directly comparable
Terminal-Bench 2.0
Kimi K2.6 leads this result
Vibe Code Bench
Shared sourceKimi K2.6 leads this result
cursorBench31
Not directly comparable
LiveCodeBench (Vals)
Kimi K2.6 leads this result
SWE-bench (Vals)
Kimi K2.6 leads this result
SWE-bench Verified*
Not directly comparable
SWE-Rebench
Not directly comparable
Multi-SWE Bench
Not directly comparable
VIBE-Pro
Not directly comparable
NL2Repo
Not directly comparable
React Native Evals
Not directly comparable
MMMU-Pro
Not directly comparable
MMMU-Pro w/ Python
Not directly comparable
CharXiv
Not directly comparable
MathVision
Not directly comparable
V*
Not directly comparable
GPQA
Not directly comparable
GPQA-D
Kimi K2.6 leads this result
HLE
Kimi K2.6 leads this result
GPQA Diamond (Vals)
Kimi K2.6 leads this result
MMLU-Pro (Vals)
Kimi K2.6 leads this result
MMLU-Pro (Arcee)
Not directly comparable
AIME26
Kimi K2.6 leads this result
HMMT Feb 2026
Kimi K2.6 leads this result
MMAnswerBench
Not directly comparable
FrontierMath v2 (Tiers 1-3)
Not directly comparable
FrontierMath v2 (Tier 4)
Not directly comparable
AIME25 (Arcee)
Not directly comparable
HMMT Nov 2025
Not directly comparable
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 5,500+ readers.
Last updated October 10, 2026
