Compare · ModelsLive · 2 picked · head to head
Gemini 3 Pro vs Kimi K3
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Kimi K3 wins on 10/12 benchmarks
Kimi K3 wins 10 of 12 shared benchmarks. Leads in speed · agentic · reasoning.
Category leads
speed·Kimi K3agentic·Kimi K3reasoning·Kimi K3knowledge·Kimi K3math·Kimi K3general·Kimi K3coding·Kimi K3
Hype vs Reality
Attention vs performance
Gemini 3 Pro
#71 by perf·#5 by attention
Kimi K3
#51 by perf·#17 by attention
Vendor risk
Who is behind the model
Google DeepMind
$4.20T·Tier 1
Moonshot AI
$18.0B·Tier 1
Head to head
12 benchmarks · 2 models
Gemini 3 ProKimi K3
Artificial Analysis · Quality Index
Kimi K3 leads by +2.3
Gemini 3 Pro
41.3
Kimi K3
43.6
APEX-Agents
Kimi K3 leads by +32.2
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
Gemini 3 Pro
18.4
Kimi K3
50.6
ARC-AGI
Kimi K3 leads by +19.5
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
Gemini 3 Pro
75.0
Kimi K3
94.5
ARC-AGI-2
Kimi K3 leads by +29.3
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
Gemini 3 Pro
31.1
Kimi K3
60.4
Chess Puzzles
Kimi K3 leads by +8.4
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Gemini 3 Pro
27.4
Kimi K3
35.8
GPQA diamond
Kimi K3 leads by +0.7
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Gemini 3 Pro
90.2
Kimi K3
90.8
OTIS Mock AIME 2024-2025
Kimi K3 leads by +5.8
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Gemini 3 Pro
91.4
Kimi K3
97.2
PostTrainBench
Kimi K3 leads by +13.8
Gemini 3 Pro
18.1
Kimi K3
32.0
Proofbench
Kimi K3 leads by +67.0
Gemini 3 Pro
20.0
Kimi K3
87.0
SimpleBench
Gemini 3 Pro leads by +18.8
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
Gemini 3 Pro
71.7
Kimi K3
52.8
SimpleQA Verified
Gemini 3 Pro leads by +22.3
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Gemini 3 Pro
72.9
Kimi K3
50.6
WeirdML
Kimi K3 leads by +12.6
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Gemini 3 Pro
69.9
Kimi K3
82.6
Full benchmark table
| Benchmark | Gemini 3 Pro | Kimi K3 |
|---|---|---|
Artificial Analysis · Quality Index | 41.3 | 43.6 |
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 18.4 | 50.6 |
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 75.0 | 94.5 |
ARC-AGI-2 ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data. | 31.1 | 60.4 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 27.4 | 35.8 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 90.2 | 90.8 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 91.4 | 97.2 |
PostTrainBench | 18.1 | 32.0 |
Proofbench | 20.0 | 87.0 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 71.7 | 52.8 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 72.9 | 50.6 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 69.9 | 82.6 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| — | — | — | — | |
| $0.67 | $14.00 | 1.0M tokens (~524 books) | $40.03 |