Agentic
Like-for-like- Kimi K2.6
- 46.7
- Supported · #74/152
- Mistral Medium 3.5 128B
- 21.9
- Supported · #150/152
- Basis
- BenchAlign lane · 12 vs 3 public rows
- Reading
- Kimi K2.6 leads
Kimi K2.6 vs Mistral Medium 3.5 128B
Updated September 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Kimi K2.6 has the higher public score, 65.39 versus 30.13, and the 90% score intervals do not overlap.
6 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.
Agentic work
Tool use, computer use, and multi-step task completion
Kimi K2.6
Kimi K2.6 leads on the public agentic lane, 46.7 to 21.9, with Supported evidence for both models and non-overlapping 90% intervals.
Confidence: stronger
Chat turn cost
1K fresh input + 500 output tokens
Kimi K2.6
Kimi K2.6 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Kimi K2.6
Kimi K2.6 has the lower estimated token cost for this stated workload. Kimi K2.6 has no published cached-input rate, so cached tokens use its listed input rate. Mistral Medium 3.5 128B has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
Show secondary and unsupported calls
Repository review cost
50K fresh input + 3K output tokens
Kimi K2.6
Kimi K2.6 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Mistral Medium 3.5 128B is scored on Estimated evidence for coding, 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
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
31 Kimi K2.6 only
6 Shared
1 Mistral Medium 3.5 128B only
- Shared results
- 6
- Kimi K2.6 only
- 31
- Mistral Medium 3.5 128B only
- 1
- Like-for-like categories
- 2 / 8
1 category rests 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.
Knowledge
Like-for-like- Kimi K2.6
- 61.5
- Supported · #32/183
- Mistral Medium 3.5 128B
- 39.0
- Supported · #140/183
- Basis
- BenchAlign lane · 5 vs 2 public rows
- Reading
- Kimi K2.6 leads · intervals overlap
Coding
Directional only- Kimi K2.6
- 50.8
- Supported · #52/151
- Mistral Medium 3.5 128B
- 36.9
- Estimated · #127/151
- Basis
- BenchAlign lane · 10 vs 2 public rows
- Reading
- Directional only
Reasoning
Not comparable- Kimi K2.6
- Not ranked
- Mistral Medium 3.5 128B
- 68.6
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Kimi K2.6
- 71.3
- #1/7
- Mistral Medium 3.5 128B
- Not ranked
- Basis
- Provisional lane · 4 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Kimi K2.6
- Not ranked
- Mistral Medium 3.5 128B
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Kimi K2.6
- 64.0
- #26/48
- Mistral Medium 3.5 128B
- 55.6
- Unranked · 1 rankable row
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Kimi K2.6
- Not ranked
- Mistral Medium 3.5 128B
- 84.0
- #48/123
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Kimi K2.6 | Mistral Medium 3.5 128B | Basis | Reading |
|---|---|---|---|---|
| Agentic | 46.7Supported · #74/152 | 21.9Supported · #150/152 | Like-for-likeBenchAlign lane · 12 vs 3 public rows | Kimi K2.6 leads |
| Knowledge | 61.5Supported · #32/183 | 39.0Supported · #140/183 | Like-for-likeBenchAlign lane · 5 vs 2 public rows | Kimi K2.6 leads · intervals overlap |
| Coding | 50.8Supported · #52/151 | 36.9Estimated · #127/151 | Directional onlyBenchAlign lane · 10 vs 2 public rows | Directional only |
| Reasoning | Not ranked | 68.6Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 71.3#1/7 | Not ranked | Not comparableProvisional lane · 4 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | 64.0#26/48 | 55.6Unranked · 1 rankable row | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | 84.0#48/123 | 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.
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.
MMLU-Pro (Vals)
Knowledge
Kimi K2.6: 87.6%Mistral Medium 3.5 128B: 75.3%Normalized gap 12.3Kimi K2.6 source Mistral Medium 3.5 128B sourceSWE-bench Verified
Coding
Kimi K2.6: 80.2%Mistral Medium 3.5 128B: 77.6%Normalized gap 2.6Kimi K2.6 source Mistral Medium 3.5 128B source
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 K2.6
- $0.00295
- Fits in one request
- Mistral Medium 3.5 128B
- $0.00525
- Fits in one request
Kimi K2.6 has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Kimi K2.6
- $0.0595
- Fits in one request
- Mistral Medium 3.5 128B
- $0.0975
- Fits in one request
Kimi K2.6 has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Kimi K2.6
- $0.249
- Fits in one request
- Cached input priced at the published list-input rate
- Mistral Medium 3.5 128B
- $0.405
- Fits in one request
- Cached input priced at the published list-input rate
Kimi K2.6 has the lower modeled cost
Kimi K2.6 has no published cached-input rate, so cached tokens use its listed input rate. Mistral Medium 3.5 128B 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 K2.6Mistral Medium 3.5 128B
Context window
Maximum documented context; output-token limits may be lower.
Kimi K2.6
256K
Mistral Medium 3.5 128B
256K
API model ID
Kimi K2.6
Not sourced
Mistral Medium 3.5 128B
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Kimi K2.6
Not published
Mistral Medium 3.5 128B
Not published
Documented inputs
Kimi K2.6
Not sourced
Mistral Medium 3.5 128B
Not sourced
Documented outputs
Kimi K2.6
Not sourced
Mistral Medium 3.5 128B
Not sourced
Provider availability
Kimi K2.6
Not sourced
Mistral Medium 3.5 128B
Not sourced
Reasoning profile
Kimi K2.6
Reasoning
Mistral Medium 3.5 128B
Reasoning
Weight access
Kimi K2.6
Open Weight
Mistral Medium 3.5 128B
Open Weight
License
Kimi K2.6
Open Weight
Mistral Medium 3.5 128B
Open Weight
Release date
Kimi K2.6
2026-04-20
Mistral Medium 3.5 128B
2026-04-29
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 K2.6 has the higher public score, 65.39 versus 30.13, and the 90% score intervals do not overlap.
- Workload cost
- Repository review: $0.0595 vs $0.0975. Cache-heavy agent loop: $0.249 vs $0.405.
- 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 K2.6
API / mo$3,713
Self-host / mo$18,221
Break-even326M/day
Mistral Medium 3.5 128B
API / mo$6,750
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 evidence38 rows
Agentic
Terminal-Bench 2.0
Kimi K2.666.7%SourceMistral Medium 3.5 128B—Not directly comparable
BrowseComp
Kimi K2.683.2%SourceMistral Medium 3.5 128B—Not directly comparable
OSWorld-Verified
Kimi K2.673.1%SourceMistral Medium 3.5 128B—Not directly comparable
Toolathlon
Kimi K2.650%SourceMistral Medium 3.5 128B—Not directly comparable
MCP Atlas
Kimi K2.655.9%SourceMistral Medium 3.5 128B—Not directly comparable
Claw-Eval
Kimi K2.662.3%SourceMistral Medium 3.5 128B—Not directly comparable
DeepSearchQA
Kimi K2.692.5%SourceMistral Medium 3.5 128B—Not directly comparable
WideResearch
Kimi K2.680.8%SourceMistral Medium 3.5 128B—Not directly comparable
Gert Labs
Shared sourceKimi K2.656.82%Mistral Medium 3.5 128B39.10%Kimi K2.6 leads this result
ResearchClawBench
Kimi K2.618.0%SourceMistral Medium 3.5 128B—Not directly comparable
OSWorld 2.0
Kimi K2.64.6%SourceMistral Medium 3.5 128B—Not directly comparable
Terminal-Bench 2.1 (Vals)
Kimi K2.653.6%SourceMistral Medium 3.5 128B39.0%SourceKimi K2.6 leads this result
τ³-bench results
Kimi K2.6—Mistral Medium 3.5 128B91.4%SourceNot directly comparable
Coding
SWE-bench Verified
Kimi K2.680.2%SourceMistral Medium 3.5 128B77.6%SourceKimi K2.6 leads this result
LiveCodeBench v6
Kimi K2.689.6%SourceMistral Medium 3.5 128B—Not directly comparable
SWE-bench Pro
Kimi K2.658.6%SourceMistral Medium 3.5 128B—Not directly comparable
SWE Multilingual
Kimi K2.676.7%SourceMistral Medium 3.5 128B—Not directly comparable
SciCode
Kimi K2.652.2%SourceMistral Medium 3.5 128B—Not directly comparable
Terminal-Bench 2.0
Kimi K2.666.7%SourceMistral Medium 3.5 128B—Not directly comparable
Vibe Code Bench
Kimi K2.637.89%SourceMistral Medium 3.5 128B—Not directly comparable
cursorBench31
Kimi K2.647.6%SourceMistral Medium 3.5 128B—Not directly comparable
LiveCodeBench (Vals)
Kimi K2.686.8%SourceMistral Medium 3.5 128B—Not directly comparable
SWE-bench (Vals)
Kimi K2.676.2%SourceMistral Medium 3.5 128B66.4%SourceKimi K2.6 leads this result
Knowledge
GPQA
Kimi K2.690.5%SourceMistral Medium 3.5 128B—Not directly comparable
GPQA-D
Kimi K2.690.5%SourceMistral Medium 3.5 128B—Not directly comparable
HLE
Kimi K2.634.7%SourceMistral Medium 3.5 128B—Not directly comparable
GPQA Diamond (Vals)
Kimi K2.689.1%SourceMistral Medium 3.5 128B34.8%SourceKimi K2.6 leads this result
MMLU-Pro (Vals)
Kimi K2.687.6%SourceMistral Medium 3.5 128B75.3%SourceKimi K2.6 leads this result
Math
AIME26
Kimi K2.696.4%SourceMistral Medium 3.5 128B—Not directly comparable
HMMT Feb 2026
Kimi K2.692.7%SourceMistral Medium 3.5 128B—Not directly comparable
MMAnswerBench
Kimi K2.686.0%SourceMistral Medium 3.5 128B—Not directly comparable
FrontierMath v2 (Tiers 1-3)
Kimi K2.638.966%SourceMistral Medium 3.5 128B—Not directly comparable
FrontierMath v2 (Tier 4)
Kimi K2.614.580%SourceMistral Medium 3.5 128B—Not directly comparable
Multimodal
MMMU-Pro
Kimi K2.679.4%SourceMistral Medium 3.5 128B—Not directly comparable
MMMU-Pro w/ Python
Kimi K2.680.1%SourceMistral Medium 3.5 128B—Not directly comparable
CharXiv
Kimi K2.680.4%SourceMistral Medium 3.5 128B—Not directly comparable
MathVision
Kimi K2.687.4%SourceMistral Medium 3.5 128B—Not directly comparable
V*
Kimi K2.696.9%SourceMistral Medium 3.5 128B—Not directly comparable
Frequently asked questions
Which is better, Kimi K2.6 or Mistral Medium 3.5 128B?
Kimi K2.6 has the higher public score, 65.39 versus 30.13, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.
Which is better for coding, Kimi K2.6 or Mistral Medium 3.5 128B?
Kimi K2.6 scores higher for coding on the public lane, 50.8 to 36.9. Mistral Medium 3.5 128B 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, Kimi K2.6 or Mistral Medium 3.5 128B?
Kimi K2.6 leads the public agentic tasks lane, 46.7 to 21.9, with Supported evidence for both models and non-overlapping 90% intervals.
Which costs less, Kimi K2.6 or Mistral Medium 3.5 128B?
For the stated presets, chat costs $0.00295 on Kimi K2.6 and $0.00525 on Mistral Medium 3.5 128B; repository review costs $0.0595 and $0.0975; the cache-heavy agent loop costs $0.249 and $0.405. Kimi K2.6 has no published cached-input rate, so cached tokens use its listed input rate. Mistral Medium 3.5 128B has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Kimi K2.6 or Mistral Medium 3.5 128B?
Both models list the same context window, 256K.
Related comparisons
Last updated September 10, 2026
Watch Kimi K2.6 vs Mistral Medium 3.5 128B
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.