Head-to-head comparison

Kimi K2.6 vs. Mistral Medium 3.5

Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.

shared result series: 48
distinct benchmarks: 21
latest retrieval: 2026-09-29

First modelSecond model

Specifications

General specifications

Release date, availability, context window, architecture, and published parameter counts at a glance. Undisclosed details remain marked as unavailable.

Specifications for Kimi K2.6 and Mistral Medium 3.5
Attribute	Kimi K2.6	Mistral Medium 3.5
Provider	Moonshot AI	Mistral AI
Released	Apr 20, 2026	Apr 28, 2026
Availability	Active	Active
Model type	Open Weights	Open Weights
Parameters	1T, 32B active	128B
Architecture	Mixture of Experts	Dense
Context window	262,144 tokens	262,144 tokens
Knowledge cutoff	Not published	Not published
Technical sources	Model, Context	Model, Context

Pricing

API pricing compared

The table compares official standard API rates per 1M tokens, including published cache pricing. Batch, fast, priority, regional surcharges, tool calls, and cloud platform pricing are excluded.

API pricing for Kimi K2.6 and Mistral Medium 3.5
Price type	Kimi K2.6	Mistral Medium 3.5
API input	$0.95	$1.5
API output	$4	$7.5
Cache read	$0.16	Not listed
Cache write (5 min.)	Not listed	Not listed
Cache write (1 hr.)	Not listed	Not listed
Price verified	09/22/2026 Source	09/22/2026 Source

Kimi K2.6Mistral Medium 3.5

API inputUSD per 1M tokens, base tier

Kimi K2.6$0.95

Mistral Medium 3.5$1.5

API outputUSD per 1M tokens, base tier

Kimi K2.6$4

Mistral Medium 3.5$7.5

Key to the marks:better valuebetter, but not conclusivetie

Pricing by provider

Direct developer pricing and provider endpoint tariffs routed through OpenRouter are listed separately. Prices are in USD per 1M tokens. Context-dependent direct tiers plus regional, Flex, Priority, and other OpenRouter tariffs remain individually identifiable.

Provider pricing for Kimi K2.6 and Mistral Medium 3.5
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
Kimi K2.6	Moonshot AI	Direct from developerStandard API	$0.95	$4	Source09/22/2026
	AtlasCloud	Via OpenRouteratlas-cloud/int4	$0.95	$4	Source10/02/2026
	Baidu	Via OpenRouterbaidu/fp4	Lowest listed price: $0.4342	Lowest listed price: $1.828	Source10/02/2026
	Chutes	Via OpenRouterchutes/int4	$0.5	$2.85	Source10/02/2026
	Cloudflare	Via OpenRoutercloudflare	$0.95	$4	Source10/02/2026
	CoreWeave	Via OpenRoutercoreweave/fp4	$0.65	$3.41	Source10/02/2026
	Crusoe	Via OpenRoutercrusoe/bf16	$0.7	$3.5	Source10/02/2026
	Decart	Via OpenRouterdecart/fp4	$0.5865	$2.4696	Source10/02/2026
	DeepInfra	Via OpenRouterdeepinfra/fp4	$0.75	$3.5	Source10/02/2026
	DigitalOcean	Via OpenRouterdigitalocean	$0.57	$2.4	Source10/02/2026
	GMICloud	Via OpenRoutergmicloud/fp8	$0.855	$3.6	Source10/02/2026
	Inceptron	Via OpenRouterinceptron/int4	$0.4344	$2.45	Source10/02/2026
	Moonshot AI	Via OpenRoutermoonshotai/int4	$0.95	$4	Source10/02/2026
	Novita	Via OpenRouternovita	$0.8	$3.4	Source10/02/2026
	Parasail	Via OpenRouterparasail/int4	$0.75	$3.5	Source10/02/2026
	Phala	Via OpenRouterphala	$1.09	$4.6	Source10/02/2026
	SiliconFlow	Via OpenRoutersiliconflow/fp8	$0.77	$3.4	Source10/02/2026
	StreamLake	Via OpenRouterstreamlake/fp8	$0.5985	$2.52	Source10/02/2026
Mistral Medium 3.5	Mistral AI	Direct from developerStandard API	Lowest listed price: $1.5	Lowest listed price: $7.5	Source09/22/2026
	Mistral	Via OpenRoutermistral	Lowest listed price: $1.5	Lowest listed price: $7.5	Source10/02/2026
	Mistral	Via OpenRoutermistral/eu	$1.65	$8.25	Source10/02/2026
	Mistral	Via OpenRoutermistral/zdr	Lowest listed price: $1.5	Lowest listed price: $7.5	Source10/02/2026

Performance

Shared benchmarks

Only published results with the same benchmark version, task, metric, and comparison cohort are paired. Different reasoning levels, agents, harnesses, or output limits appear directly in the table.

Capability profile from matched benchmarks

Each axis averages directly matched benchmark families. A value of 100 means the stronger value within this pair, not a universal quality score.

Kimi K2.6

Mistral Medium 3.5

Coding: 100 / 52.7 (4 benchmark families)

Reasoning: 100 / 68 (2 benchmark families)

Mathematics: 100 / 96.7 (1 benchmark family)

Knowledge: 100 / 91.3 (2 benchmark families)

Finance: 100 / 67.5 (7 benchmark families)

Legal: 100 / 60.3 (3 benchmark families)

Agentic tasks: 100 / 62.8 (1 benchmark family)

Health: 100 / 89.1 (3 benchmark families)

48 matched rows from 20 benchmark families were considered. The radar shows 8 of 11 comparable categories.

Kimi K2.6Mistral Medium 3.5

Code MigrationOverall. Higher is better. No documented setup difference

Kimi K2.627.768 %

Mistral Medium 3.55.127 %

CorpFin v2Overall. Higher is better. No documented setup difference

Kimi K2.666.744 %

Mistral Medium 3.558.78 %

EMBOverall. Higher is better. No documented setup difference

Kimi K2.657.855 %

Mistral Medium 3.511.185 %

Finance Agent (v2)Overall. Higher is better. No documented setup difference

Kimi K2.644.899 %

Mistral Medium 3.532.103 %

GPQA DiamondOverall. Higher is better. No documented setup difference

Kimi K2.689.142 %

Mistral Medium 3.534.848 %

Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference

Kimi K2.61.667 %

Mistral Medium 3.50.417 %

Legal Research BenchOverall · All-pass. Higher is better. No documented setup difference

Kimi K2.615.865 %

Mistral Medium 3.59.135 %

LMArena Text, Style ControlOverall. Higher is better. No documented setup difference

Kimi K2.61,460.921

Mistral Medium 3.51,426.128

MedCodeOverall. Higher is better. No documented setup difference

Kimi K2.640.142 %

Mistral Medium 3.533.752 %

MedScribeOverall. Higher is better. No documented setup difference

Kimi K2.678.149 %

Mistral Medium 3.567.728 %

MMLU-ProOverall. Higher is better. No documented setup difference

Kimi K2.687.572 %

Mistral Medium 3.575.335 %

MortgageTaxOverall. Higher is better. No documented setup difference

Kimi K2.665.818 %

Mistral Medium 3.528.895 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Kimi K2.6 and Mistral Medium 3.5
Benchmark and task	Kimi K2.6	Mistral Medium 3.5	Source
Code MigrationOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner27.768 %	5.127 %	Vals AI Source details Data as of: 09/27/2026
CorpFin v2Overall Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better	Winner66.744 %	58.78 %	Vals AI Source details Data as of: 08/12/2026
EMBOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner57.855 %	11.185 %	Vals AI Source details Data as of: 09/27/2026
Finance Agent (v2)Overall Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better	Winner44.899 %	32.103 %	Vals AI Source details Data as of: 09/27/2026
GPQA DiamondOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner89.142 %	34.848 %	Vals AI Source details Data as of: 09/01/2026
Harvey's Legal Agent BenchmarkOverall · Task fully resolved Test details No documented difference in the test setupVersion: 1Metric: task resolution rateScoring: Higher is better	Winner1.667 %	0.417 %	Vals AI Source details Data as of: 09/27/2026
Legal Research BenchOverall · All-pass Test details No documented difference in the test setupVersion: 1Metric: all-pass rateScoring: Higher is better	Winner15.865 %	9.135 %	Vals AI Source details Data as of: 09/27/2026
LMArena Text, Style ControlOverall Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 39,971 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 11,693 anonymous pairwise votes.	Winner1,460.921 95% confidence interval: ±4.435The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,426.128 95% confidence interval: ±6.42The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
MedCodeOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner40.142 %	33.752 %	Vals AI Source details Data as of: 09/26/2026
MedScribeOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner78.149 %	67.728 %	Vals AI Source details Data as of: 09/26/2026
MMLU-ProOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner87.572 %	75.335 %	Vals AI Source details Data as of: 09/01/2026
MortgageTaxOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner65.818 %	28.895 %	Vals AI Source details Data as of: 09/01/2026
SAGEOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner50.224 %	37.613 %	Vals AI Source details Data as of: 09/26/2026
SWE-bench VerifiedOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner76.2 %	66.4 %	Vals AI Source details Data as of: 09/01/2026
Tax Agent BenchOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner45.135 %	27.291 %	Vals AI Source details Data as of: 09/27/2026
TaxEval v2Overall Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better	Winner74.652 %	67.988 %	Vals AI Source details Data as of: 09/01/2026
Terminal-Bench 2.0Overall Test details No documented difference in the test setupVersion: 2.0Metric: accuracyScoring: Higher is better	Winner57.303 %	30.337 %	Vals AI Source details Data as of: 06/04/2026
Terminal-Bench 2.1Overall Test details No documented difference in the test setupVersion: 2.1Metric: accuracyScoring: Higher is better	Winner53.558 %	38.951 %	Vals AI Source details Data as of: 09/27/2026
Vals IndexOverall Test details No documented difference in the test setupVersion: 2Metric: weighted index scoreScoring: Higher is better	Winner43.465 %	17.947 %	Vals AI Source details Data as of: 09/27/2026
Vals Multimodal IndexOverall Test details No documented difference in the test setupVersion: 1.2Metric: weighted index scoreScoring: Higher is better	Winner56.434 %	34.768 %	Vals AI Source details Data as of: 08/11/2026
Vibe Code Bench v1.1Overall Test details No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is betterSettings: Harness: OpenHands	Winner37.891 %	2.888 %	Vals AI Source details Data as of: 09/27/2026
LMArena Text, Style ControlBusiness, management and finance Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 7,948 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 2,256 anonymous pairwise votes.	Winner1,454.77 95% confidence interval: ±7.55The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,430.173 95% confidence interval: ±12.827The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlChinese Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 2,343 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 621 anonymous pairwise votes.	Winner1,517.112 95% confidence interval: ±12.799The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,446.524 95% confidence interval: ±23.931The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlCoding Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 11,092 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 3,282 anonymous pairwise votes.	Winner1,515.582 95% confidence interval: ±6.896The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,477.898 95% confidence interval: ±10.854The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlCreative writing Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 6,305 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,999 anonymous pairwise votes.	Winner1,432.89 95% confidence interval: ±8.246The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,397.828 95% confidence interval: ±13.94The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlEnglish Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 18,087 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 5,562 anonymous pairwise votes.	Winner1,469.203 95% confidence interval: ±5.649The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,442.84 95% confidence interval: ±8.53The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlEntertainment, sports and media Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 8,265 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 2,618 anonymous pairwise votes.	Winner1,428.923 95% confidence interval: ±7.544The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,394.24 95% confidence interval: ±12.151The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlExcluding ties Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 29,598 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 8,856 anonymous pairwise votes.	Winner1,464.783 95% confidence interval: ±5.815The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,419.562 95% confidence interval: ±8.482The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlExpert prompts Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 3,841 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,205 anonymous pairwise votes.	Winner1,502.88 95% confidence interval: ±9.953The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,433.7 95% confidence interval: ±17.235The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlFrench Test details No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 1,575 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 453 anonymous pairwise votes.	No clear lead1,477.486 95% confidence interval: ±16.574The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,435.855 95% confidence interval: ±29.943The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlGerman Test details No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 746 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 173 anonymous pairwise votes.	No clear lead1,457.617 95% confidence interval: ±21.288The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,447.96 95% confidence interval: ±43.885The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlHard prompts Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 26,094 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 7,627 anonymous pairwise votes.	Winner1,485.462 95% confidence interval: ±5.188The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,444.677 95% confidence interval: ±7.686The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlHard prompts, English Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 12,459 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 3,821 anonymous pairwise votes.	Winner1,488.176 95% confidence interval: ±6.532The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,455.806 95% confidence interval: ±10.148The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlInstruction following Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 13,226 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 3,827 anonymous pairwise votes.	Winner1,455.711 95% confidence interval: ±6.32The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,420.763 95% confidence interval: ±10.011The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlKorean Test details No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 730 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 188 anonymous pairwise votes.	No clear lead1,423.745 95% confidence interval: ±22.737The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,392.677 95% confidence interval: ±43.291The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlLegal and government Test details No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 3,028 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 893 anonymous pairwise votes.	No clear lead1,464.097 95% confidence interval: ±11.113The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,437.755 95% confidence interval: ±20.721The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlLife, physical and social science Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 6,726 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,939 anonymous pairwise votes.	Winner1,478.057 95% confidence interval: ±7.876The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,435.825 95% confidence interval: ±13.971The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlLonger queries Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 16,975 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 5,065 anonymous pairwise votes.	Winner1,477.914 95% confidence interval: ±6.084The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,428.117 95% confidence interval: ±9.119The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlMath Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 2,076 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 565 anonymous pairwise votes.	Winner1,479.908 95% confidence interval: ±13.073The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,428.606 95% confidence interval: ±24.143The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlMathematical professions Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 2,216 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 653 anonymous pairwise votes.	Winner1,485.541 95% confidence interval: ±12.814The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,438.481 95% confidence interval: ±22.896The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlMedicine and healthcare Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 2,934 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 844 anonymous pairwise votes.	Winner1,473.129 95% confidence interval: ±11.438The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,421.161 95% confidence interval: ±21.257The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlMulti-turn Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 6,946 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,925 anonymous pairwise votes.	Winner1,460.669 95% confidence interval: ±7.98The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,432.256 95% confidence interval: ±14.007The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlNon-English Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 21,884 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 6,131 anonymous pairwise votes.	Winner1,448.57 95% confidence interval: ±5.333The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,406.139 95% confidence interval: ±8.159The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlPolish Test details No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 761 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 235 anonymous pairwise votes.	No clear lead1,443.087 95% confidence interval: ±20.906The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,415.979 95% confidence interval: ±38.135The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlRussian Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 4,254 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,242 anonymous pairwise votes.	Winner1,453.596 95% confidence interval: ±9.384The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,410.34 95% confidence interval: ±17.157The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlSoftware and IT services Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 16,059 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 4,587 anonymous pairwise votes.	Winner1,502.848 95% confidence interval: ±5.972The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,468.806 95% confidence interval: ±9.304The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlSpanish Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 1,379 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 393 anonymous pairwise votes.	Winner1,458.419 95% confidence interval: ±16.701The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,392.394 95% confidence interval: ±31.573The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlWriting, literature and language Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterKimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlKimi K2.6: Style-controlled Arena rating from 9,562 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 2,919 anonymous pairwise votes.	Winner1,440.989 95% confidence interval: ±7.079The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,403.766 95% confidence interval: ±11.409The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
Key to the marks:better valuebetter, but not conclusivetie

Our model tests

Our tests

Compare how the models respond to the same prompt. Each test shows the first attempt, with no subsequent fixes to the generated code. These results do not contribute to an overall score.

Pelican on a bicycle

A community classic for free-form SVG drawing.

Kimi K2.6

API access was unavailable for this run. The model was not evaluated.

Reasoning (requested): high

First attempt

Run date: 7 Sept 2026
API provider: openrouter
Requested API model: moonshotai/kimi-k2.6
Reasoning setting: high
Pinned endpoint: Moonshot AI | moonshotai/kimi-k2.6-20260420
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Not run

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Mistral Medium 3.5

API access was unavailable for this run. The model was not evaluated.

Reasoning (requested): high

First attempt

Run date: 7 Sept 2026
API provider: openrouter
Requested API model: mistralai/mistral-medium-3-5
Reasoning setting: high
Pinned endpoint: Mistral | mistralai/mistral-medium-3.5-20260430
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Not run

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Prompt and test conditions

Generate an SVG of a pelican riding a bicycle

Token limit including reasoning: 8,192 tokens

Task origin (Simon Willison)

How to read this comparison

Winning one benchmark is not an overall verdict

Your workload, budget, and required context length matter most. A coding benchmark says little about visual understanding or agent performance.

The standard price table uses direct developer rates. The provider comparison labels OpenRouter endpoints, regions, and special tariffs separately.

Every result links to its measurement source and retrieval date. Labels distinguish vendor reports, official benchmark leaderboards, and independent evaluations. Disputed or archived results are excluded.

More matchups

Compare Kimi K2.6 and Mistral Medium 3.5 with other leading models using the same data and benchmark logic.

View the complete LLM comparison