Skip to main content

Model comparison

Gemini 3 Pro vs Kimi K3

Data verified

Head-to-head evidence from 14 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

67.73/100
Margin
13.2pts
winning →
Moonshot AI
80.96/100
1 category wins0 category wins

Public leaderboard positions: Gemini 3 Pro #19 (Supported); Kimi K3 #4 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Gemini 3 Pro and Kimi K3 share 14 comparable benchmark results. 1 of 8 categories are comparable. 13 results are unique to Gemini 3 Pro; 43 to Kimi K3.

Updated July 23, 2026
Shared results
14
Gemini 3 Pro only
13
Kimi K3 only
43
Comparable categories
1 / 8

Pick Kimi K3 if you want the stronger benchmark profile. Gemini 3 Pro only becomes the better choice if multimodal & grounded is the priority or you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 14 shared benchmark results across 5 evidence categories; 1 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 67.73. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Kimi K3 is also the more expensive model on tokens at $3.00 input / $15.00 output per 1M tokens, versus $2.00 input / $12.00 output per 1M tokens for Gemini 3 Pro. Kimi K3 is the reasoning model in the pair, while Gemini 3 Pro is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Gemini 3 Pro 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 Gemini 3 Pro and Kimi K3
CategoryGemini 3 ProΔKimi K3
MultimodalGemini 3 Pro81.1Margin 2.6Kimi K378.5
AgenticGemini 3 ProNot measuredMarginNo overlapKimi K389.5
ReasoningGemini 3 Pro31.1MarginNo overlapKimi K3Not measured
KnowledgeGemini 3 ProNot measuredMarginNo overlapKimi K361.0
MathGemini 3 Pro32.9MarginNo overlapKimi K3Not measured

Decisive benchmark drivers

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

More
A · Gemini 3 ProB · Kimi K3
  1. CharXiv

    Multimodal
    Source ↗
    A 81.4%B 91.3%
    Winner: Kimi K3Δ 9.9
    CharXiv: Gemini 3 Pro scored 81.4%; Kimi K3 scored 91.3%. Kimi K3 wins this benchmark.
  2. MMMU-Pro

    Multimodal
    Source ↗
    A 81%B 81.6%
    Winner: Kimi K3Δ 0.6
    MMMU-Pro: Gemini 3 Pro scored 81%; 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.

MetricGemini 3 ProKimi K3Comparison
Input / output priceUSD per 1M tokensGemini 3 Pro$2 input / $12 outputKimi K3$3 input / $15 outputGemini 3 Pro has the lower combined listed price.
Generation speedtokens per secondGemini 3 Pro109 tok/sKimi K3Not availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGemini 3 Pro32.65 sKimi K3Not availableA complete latency comparison is not available.
Context windowmaximum listed tokensGemini 3 Pro2MKimi K31.05MGemini 3 Pro lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkGemini 3 ProKimi K3Result
τ²-bench resultsSource 87.1%Not comparable
Gert LabsSource 63.23%Not comparable
JobBenchSource 11.4%52.9%Kimi K3 leads
Terminal-Bench 2.0Source 88.3%Not comparable
BrowseCompSource 91.2%Not comparable
DeepSearchQASource 95.0%Not comparable
Toolathlon-VerifiedSource 73.2%Not comparable
MCP AtlasSource 84.2%Not comparable
AutomationBenchSource 30.8%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
BenchmarkGemini 3 ProKimi K3Result
Vibe Code BenchSource 14.30%Not comparable
AA-SciCodeSource 56.1%58.7%Kimi K3 leads
AA LiveCodeBenchSource 91.7%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
Reasoning
BenchmarkGemini 3 ProKimi K3Result
ARC-AGI-2Source 31.1%Not comparable
AA-LCRSource 70.7%74.7%Kimi K3 leads
CritPtSource 9.1%23.4%Kimi K3 leads
Knowledge
BenchmarkGemini 3 ProKimi K3Result
Artificial Analysis Intelligence IndexSource 39.5%57.1%Kimi K3 leads
AA-GPQA DiamondSource 90.8%93.5%Kimi K3 leads
AA-HLESource 37.2%44.3%Kimi K3 leads
AA-Omniscience IndexSource 15.8%18.4%Kimi K3 leads
AA-Omniscience AccuracySource 55.9%46.0%Gemini 3 Pro leads
AA-Omniscience Hallucination RateSource 90.9%50.9%Kimi K3 leads
AA MMLU-ProSource 89.8%Not comparable
GPQASource 93.5%Not comparable
GPQA-DSource 93.5%Not comparable
HLESource 56%Not comparable
HLE w/o toolsSource 43.5%Not comparable
Math
BenchmarkGemini 3 ProKimi K3Result
FrontierMath v2 (Tiers 1-3)Source 37.600%Not comparable
FrontierMath v2 (Tier 4)Source 18.750%Not comparable
Multilingual
BenchmarkGemini 3 ProKimi K3Result
AA Global-MMLU-LiteSource 92.2%Not comparable
MultimodalGemini 3 Pro wins
BenchmarkGemini 3 ProKimi K3Result
MMMU-ProSource 81%81.6%Kimi K3 leads
MathVisionSource 86.6%94.3%Kimi K3 leads
VideoMMMUSource 87.6%Not comparable
ScreenSpot ProSource 72.7%Not comparable
CharXivSource 81.4%91.3%Kimi K3 leads
V*Source 88.0%Not comparable
AA-MMMU-ProSource 80.2%80.5%Kimi K3 leads
OfficeQA ProSource 63.3%Not comparable
MMMU-Pro w/ PythonSource 83.4%Not comparable
CharXiv w/o toolsSource 84.8%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
Design Arena WebsiteSource 1386Not comparable
Inst. Following
BenchmarkGemini 3 ProKimi K3Result
AA-IFBenchSource 70.4%Not comparable
Frequently Asked Questions (2)

Which is better, Gemini 3 Pro or Kimi K3?

Kimi K3 is ahead on BenchLM's BenchAlign leaderboard, 80.96 to 67.73. The biggest single separator in this matchup is CharXiv, where the scores are 81.4% and 91.3%.

Which is better for multimodal and grounded tasks, Gemini 3 Pro or Kimi K3?

Gemini 3 Pro has the edge for multimodal and grounded tasks in this comparison, averaging 81.1 versus 78.5. Inside this category, CharXiv is the benchmark that creates the most daylight between them.

Related Comparisons

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.