Skip to main content
BenchLM
Advertise

Model comparison

Grok 4.20 vs Kimi K3

Data verified

Head-to-head evidence from 7 shared benchmark results across 3 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

54.68/100
Margin
26.3pts
winning →
Kimi K3
Moonshot AI
80.96/100
0 category wins2 category wins

Public leaderboard positions: Grok 4.20 #88 (Estimated); Kimi K3 #4 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Grok 4.20 and Kimi K3 share 7 comparable benchmark results. 2 of 8 categories are comparable. 11 results are unique to Grok 4.20; 50 to Kimi K3.

Updated July 23, 2026
Shared results
7
Grok 4.20 only
11
Kimi K3 only
50
Comparable categories
2 / 8

Pick Kimi K3 if you want the stronger benchmark profile. Grok 4.20 only becomes the better choice if you want the cheaper token bill or you need the larger 2M context window.

Confidence note. This is a partial-evidence comparison with 7 shared benchmark results across 3 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Kimi K3 is clearly ahead on the BenchAlign aggregate, 80.96 to 54.68. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Kimi K3's sharpest advantage is in agentic, where it averages 89.5 against 47.1. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 47.1% to 88.3%.

Kimi K3 is also the more expensive model on tokens at $3.00 input / $15.00 output per 1M tokens, versus $2.00 input / $6.00 output per 1M tokens for Grok 4.20. That is roughly 2.5x on output cost alone. Grok 4.20 gives you the larger context window at 2M, compared with 1.05M for Kimi K3.

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 Grok 4.20 and Kimi K3
CategoryGrok 4.20ΔKimi K3
AgenticGrok 4.2047.1Margin→ 42.4Kimi K389.5
MultimodalGrok 4.2070.1Margin→ 8.4Kimi K378.5
CodingGrok 4.2067.1MarginNo overlapKimi K3Not measured
ReasoningGrok 4.2053.3MarginNo overlapKimi K3Not measured
KnowledgeGrok 4.20Not measuredMarginNo overlapKimi K361.0

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · Grok 4.20B · Kimi K3

  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 47.1%B 88.3%
    Winner: Kimi K3Δ 41.2
    Terminal-Bench 2.0: Grok 4.20 scored 47.1%; Kimi K3 scored 88.3%. Kimi K3 wins this benchmark.

  2. CharXiv

    Multimodal
    Source ↗
    A 60.9%B 91.3%
    Winner: Kimi K3Δ 30.4
    CharXiv: Grok 4.20 scored 60.9%; Kimi K3 scored 91.3%. Kimi K3 wins this benchmark.

  3. MMMU-Pro

    Multimodal
    Source ↗
    A 75.2%B 81.6%
    Winner: Kimi K3Δ 6.4
    MMMU-Pro: Grok 4.20 scored 75.2%; Kimi K3 scored 81.6%. Kimi K3 wins this benchmark.

Operational comparison

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

MetricGrok 4.20Kimi K3Comparison
Input / output priceUSD per 1M tokensGrok 4.20$2 input / $6 outputKimi K3$3 input / $15 outputGrok 4.20 has the lower combined listed price.
Generation speedtokens per secondGrok 4.20233 tok/sKimi K3Not availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGrok 4.2010.33 sKimi K3Not availableA complete latency comparison is not available.
Context windowmaximum listed tokensGrok 4.202MKimi K31.05MGrok 4.20 lists the larger context window.

Benchmark Deep Dive

AgenticKimi K3 wins
BenchmarkGrok 4.20Kimi K3Result
Terminal-Bench 2.0Source 47.1%88.3%Kimi K3 leads
DeepSearchQASource 62.8%95.0%Kimi K3 leads
Gert LabsSource 38.36%—Not comparable
BrowseCompSource —91.2%Not comparable
Toolathlon-VerifiedSource —73.2%Not comparable
MCP AtlasSource —84.2%Not comparable
AutomationBenchSource —30.8%Not comparable
JobBenchSource —52.9%Not comparable
APEX-AgentsSource —37.6%Not comparable
SpreadsheetBench 2Source —34.8%Not comparable
DECK-BenchSource —73.5%Not comparable
AA Agentic IndexSource —50.1%Not comparable
GDPval-AASource —59.0%Not comparable
GDPval-AASource —1679Not comparable
AA BriefcaseSource —1543Not comparable
AA AutomationBenchSource —52.7%Not comparable
AA EnterpriseOps-GymSource —45.3%Not comparable
AA Harvey LABSource —94.6%Not comparable
AA Tau3 BankingSource —33.4%Not comparable
aaTerminalBench21Source —85%Not comparable
APEX-Agents-AASource —41.3%Not comparable
AA ITBenchSource —47.7%Not comparable
Coding
BenchmarkGrok 4.20Kimi K3Result
LiveCodeBench ProSource 74.2%—Not comparable
SWE-bench VerifiedSource 76.7%—Not comparable
SWE-bench ProSource 51.8%—Not comparable
Vibe Code BenchSource 4.06%—Not comparable
deepSweSource —67.5%Not comparable
FrontierSWESource —81.2%Not comparable
ProgramBenchSource —77.8%Not comparable
Kimi Code Bench v2Source —72.9%Not comparable
sweMarathonSource —42%Not comparable
PostTrain BenchSource —36.6%Not comparable
MLS-Bench LiteSource —48.3%Not comparable
AA Coding IndexSource —76.2%Not comparable
AA-SciCodeSource —58.7%Not comparable
Reasoning
BenchmarkGrok 4.20Kimi K3Result
ARC-AGI-2Source 53.3%—Not comparable
AA-LCRSource —74.7%Not comparable
CritPtSource —23.4%Not comparable
Knowledge
BenchmarkGrok 4.20Kimi K3Result
GPQA-DSource 88.5%93.5%Kimi K3 leads
HLE w/o toolsSource 31.6%43.5%Kimi K3 leads
HealthBench HardSource 20.3%—Not comparable
MedXpertQA (Text)Source 50.2%—Not comparable
GPQASource —93.5%Not comparable
HLESource —56%Not comparable
Artificial Analysis Intelligence IndexSource —57.1%Not comparable
AA-GPQA DiamondSource —93.5%Not comparable
AA-HLESource —44.3%Not comparable
AA-Omniscience IndexSource —18.4%Not comparable
AA-Omniscience AccuracySource —46.0%Not comparable
AA-Omniscience Hallucination RateSource —50.9%Not comparable
MultimodalKimi K3 wins
BenchmarkGrok 4.20Kimi K3Result
MMMU-ProSource 75.2%81.6%Kimi K3 leads
CharXivSource 60.9%91.3%Kimi K3 leads
ERQASource 54.1%—Not comparable
SimpleVQASource 57.4%—Not comparable
MedXpertQA (MM)Source 65.8%—Not comparable
Design Arena WebsiteSource 12571386Kimi K3 leads
OfficeQA ProSource —63.3%Not comparable
MMMU-Pro w/ PythonSource —83.4%Not comparable
CharXiv w/o toolsSource —84.8%Not comparable
MathVisionSource —94.3%Not comparable
MathVision w/ PythonSource —97.8%Not comparable
BabyVision w/ PythonSource —85.7%Not comparable
ZeroBenchSource —23.0%Not comparable
ZeroBench w/ PythonSource —41.0%Not comparable
WorldVQA ForceAnswerSource —51.0%Not comparable
OmniDocBenchSource —91.1%Not comparable
PerceptionBenchSource —58.5%Not comparable
AA-MMMU-ProSource —80.5%Not comparable
Frequently Asked Questions (3)

Which is better, Grok 4.20 or Kimi K3?

Kimi K3 is ahead on BenchLM's BenchAlign leaderboard, 80.96 to 54.68. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 47.1% and 88.3%.

Which is better for agentic tasks, Grok 4.20 or Kimi K3?

Kimi K3 has the edge for agentic tasks in this comparison, averaging 89.5 versus 47.1. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Grok 4.20 or Kimi K3?

Kimi K3 has the edge for multimodal and grounded tasks in this comparison, averaging 78.5 versus 70.1. Inside this category, Design Arena Website is the benchmark that creates the most daylight between them.

Related Comparisons

Explore More

xAI Compare Pricing Methodology Find Your Best LLM Overall Rankings
Last updated: July 23, 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.