Mistral-Medium-3.5-128B vs Kimi-K2.6

Benchmark Performance

Available Benchmarks

BenchmarkMistral-Medium-3.5-128BKimi-K2.6
LMArena Text Arenatext-2026-09-01-011508720696 · arena_rating · leader1,421.1698% of row best · rating · mistral-medium-3.5; 95% CI [1414.62812191, 1427.69573067]; votes 11017; rank 981,455.01100% of row best · rating · kimi-k2.6; 95% CI [1450.48846324, 1459.52803920]; votes 37573; rank 34
LMArena Vision Arenavision-2026-08-27-011508720696 · arena_rating · leader1,222.1895% of row best · rating · mistral-medium-3.5; 95% CI [1212.39755732, 1231.95907443]; votes 5091; rank 671,280.71100% of row best · rating · kimi-k2.6; 95% CI [1273.64165646, 1287.78511818]; votes 15378; rank 27
Overall ResultCounted from the protocol-matched rows above0 benchmark wins2 benchmark winsOverall lead

Third-party benchmark Only like-for-like primary-publisher results are shown; raw scores, relative scores, configuration, and token spend remain visible.

FieldAt a Glance
Mistral AI · activeMistral-Medium-3.5-128BVerified Aug 28, 2026
Moonshot AI · activeKimi-K2.6Verified Aug 28, 2026

Technical Differences

Side-by-Side Facts

Indexable
FieldMistral-Medium-3.5-128BKimi-K2.6
DeveloperMistral AIMoonshot AI
FamilyMistral Medium 3 5 128bKimi K2 6
ModelMistral-Medium-3.5-128BKimi-K2.6
VersionMistral-Medium-3.5-128BKimi-K2.6
Lifecycleactiveactive
ReleasedUnknown2026-04-20
Knowledge cutoffUnknownUnknown
Input modalitiesText, ImageText, Image
Output modalitiesTextText
Context window262,144262,144
Total parameters127,704,210,1761,026,879,376,368
Active parametersUnknown32,000,000,000
Licenseotherother
Open weightsYesYes
API availableUnknownYes
Self-hostableYesYes
Provider accessUnknownDeepinfra (Standard), Fireworks Ai (Standard), Hugging Face (Standard), Openrouter (Standard), Together Ai (Standard)
Capabilitieschat, generation, reasoning, toolschat, generation, reasoning, tools

13 comparable fields · 5 material differences · Pair passes the primary-source comparison gate

Mistral-Medium-3.5-128B Capabilities

chatgenerationreasoningtools
Input price
Output price
Serving providers0
Canonical IDmistralai/Mistral-Medium-3.5-128B

Kimi-K2.6 Capabilities

chatgenerationreasoningtools
Input price$0.75
Output price$3.50
Serving providers5
Canonical IDmoonshotai/Kimi-K2.6

Internal Comparison Graph

Related Comparisons

All image comparisons →
APairBContext
vsfamily variantsimage, text
vsfamily variantsembedding, image, text
vsfamily variantsembedding, image, text
vsfamily variantsimage, text
vsfamily variantsimage, text
vscross-developer peersimage, text
vscross-developer peersimage, text
vscross-developer peersimage, text
vscross-developer peersimage, text
vscross-developer peersimage, text
vscross-developer peersimage, text
vsfamily variantstext

Primary Evidence

Sources and Freshness

Questions

Mistral-Medium-3.5-128B vs Kimi-K2.6 FAQs

Is Mistral-Medium-3.5-128B or Kimi-K2.6 better for coding?+

This comparison does not currently contain a protocol-matched coding benchmark for both Mistral-Medium-3.5-128B and Kimi-K2.6, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.

Which is cheaper, Mistral-Medium-3.5-128B or Kimi-K2.6?+

Only Kimi-K2.6 has a directly sourced input price: $0.75 per million tokens. Only Kimi-K2.6 has a directly sourced output price: $3.50 per million tokens.

Which has a larger context window, Mistral-Medium-3.5-128B or Kimi-K2.6?+

Neither model has a larger sourced context window in this comparison. Mistral-Medium-3.5-128B is 262,144 and Kimi-K2.6 is 262,144.

Which performs better in benchmarks, Mistral-Medium-3.5-128B or Kimi-K2.6?+

There is no overall benchmark winner: An overall winner requires at least two decisive benchmarks from at least two original publishers.

Can Mistral-Medium-3.5-128B or Kimi-K2.6 be self-hosted?+

Both models have the same recorded self-hosting status: supported. Mistral-Medium-3.5-128B is open weight; Kimi-K2.6 is open weight.

Can Mistral-Medium-3.5-128B and Kimi-K2.6 understand images?+

Mistral-Medium-3.5-128B is documented with image input; Kimi-K2.6 is documented with image input. This reflects supported input modalities, not vision quality.

Which can generate longer answers, Mistral-Medium-3.5-128B or Kimi-K2.6?+

Neither has a larger sourced maximum output. Mistral-Medium-3.5-128B is — and Kimi-K2.6 is —.

Do Mistral-Medium-3.5-128B and Kimi-K2.6 support reasoning and tool use?+

Mistral-Medium-3.5-128B: reasoning, tool calling, and image input. Kimi-K2.6: reasoning, tool calling, and image input. Feature support does not establish relative quality.

Which is available from more inference providers, Mistral-Medium-3.5-128B or Kimi-K2.6?+

Mistral-Medium-3.5-128B has 0 sourced provider routes; Kimi-K2.6 has 5, so Kimi-K2.6 has broader tracked availability.

Which offers better value, Mistral-Medium-3.5-128B or Kimi-K2.6?+

There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.

Send Feedback