Skip to main content

Model comparison

Kimi K2 vs Mistral Large 2

Data verified

Head-to-head evidence from 11 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Moonshot AI
27.19/100
Margin
14.6pts
winning →
41.77/100
0 category wins0 category wins

Public leaderboard positions: Kimi K2 #189 (Supported); Mistral Large 2 #163 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Kimi K2 and Mistral Large 2 share 11 comparable benchmark results. 0 of 8 categories are comparable. 3 results are unique to Kimi K2; 0 to Mistral Large 2.

Updated July 20, 2026
Shared results
11
Kimi K2 only
3
Mistral Large 2 only
0
Comparable categories
0 / 8

Benchmark data for Kimi K2 and Mistral Large 2 is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 11 shared benchmark results across 5 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Kimi K2 and Mistral Large 2
CategoryKimi K2ΔMistral Large 2
MathKimi K216.1MarginNo overlapMistral Large 2Not measured

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricKimi K2Mistral Large 2Comparison
Input / output priceUSD per 1M tokensKimi K2$0.6 input / $2.5 outputMistral Large 2Not availableA complete price comparison is not available.
Generation speedtokens per secondKimi K243 tok/sMistral Large 238 tok/sKimi K2 has the higher measured throughput.
First-answer latencyseconds to first tokenKimi K21.51 sMistral Large 21.45 sMistral Large 2 reaches the first token sooner.
Context windowmaximum listed tokensKimi K2128KMistral Large 2128KListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkKimi K2Mistral Large 2Result
τ²-bench resultsSource 61.1%30.7%Kimi K2 leads
Coding
BenchmarkKimi K2Mistral Large 2Result
AA-SciCodeSource 34.5%29.2%Kimi K2 leads
Reasoning
BenchmarkKimi K2Mistral Large 2Result
AA-LCRSource 51.0%5.3%Kimi K2 leads
CritPtSource 0.0%0.0%Tie
Knowledge
BenchmarkKimi K2Mistral Large 2Result
Artificial Analysis Intelligence IndexSource 19.4%9.2%Kimi K2 leads
AA-GPQA DiamondSource 76.6%48.6%Kimi K2 leads
AA-HLESource 7.0%4.0%Kimi K2 leads
AA-Omniscience IndexSource -27.5%-34.0%Kimi K2 leads
AA-Omniscience AccuracySource 26.8%20.1%Kimi K2 leads
AA-Omniscience Hallucination RateSource 74.2%67.8%Mistral Large 2 leads
Math
BenchmarkKimi K2Mistral Large 2Result
FrontierMath v2 (Tiers 1-3)Source 21.404%Not comparable
FrontierMath v2 (Tier 4)Source 0.000%Not comparable
Multimodal
BenchmarkKimi K2Mistral Large 2Result
Design Arena WebsiteSource 1083Not comparable
Inst. Following
BenchmarkKimi K2Mistral Large 2Result
AA-IFBenchSource 41.5%31.2%Kimi K2 leads
Frequently Asked Questions (3)

Can I compare Kimi K2 and Mistral Large 2 on BenchLM yet?

Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.

Why does this comparison show “coming soon”?

BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.

What data is available for Kimi K2 and Mistral Large 2 today?

Kimi K2: $0.60 input / $2.50 output per 1M tokens Mistral Large 2: Pricing unavailable Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.

Related Comparisons

Last updated: July 20, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.