Compare · ModelsLive · 2 picked · head to head
Kimi K2 Thinking vs Kimi K3
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Kimi K3 wins on 7/7 benchmarks
Kimi K3 wins 7 of 7 shared benchmarks. Leads in agentic · knowledge · math.
Category leads
agentic·Kimi K3knowledge·Kimi K3math·Kimi K3coding·Kimi K3
Hype vs Reality
Attention vs performance
Kimi K2 Thinking
#103 by perf·#17 by attention
Kimi K3
#51 by perf·#17 by attention
Best value
Kimi K2 Thinking
4.2x better value than Kimi K3
Kimi K2 Thinking
34.0 pts/$
$1.55/M
Kimi K3
8.1 pts/$
$7.33/M
Vendor risk
Who is behind the model
Moonshot AI
$18.0B·Tier 1
Moonshot AI
$18.0B·Tier 1
Head to head
7 benchmarks · 2 models
Kimi K2 ThinkingKimi K3
APEX-Agents
Kimi K3 leads by +46.6
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
Kimi K2 Thinking
4.0
Kimi K3
50.6
Chess Puzzles
Kimi K3 leads by +20.0
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Kimi K2 Thinking
15.8
Kimi K3
35.8
GPQA diamond
Kimi K3 leads by +11.9
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Kimi K2 Thinking
79.0
Kimi K3
90.8
OTIS Mock AIME 2024-2025
Kimi K3 leads by +14.2
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Kimi K2 Thinking
83.0
Kimi K3
97.2
PostTrainBench
Kimi K3 leads by +24.7
Kimi K2 Thinking
7.3
Kimi K3
32.0
SimpleQA Verified
Kimi K3 leads by +19.0
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Kimi K2 Thinking
31.6
Kimi K3
50.6
WeirdML
Kimi K3 leads by +39.8
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Kimi K2 Thinking
42.8
Kimi K3
82.6
Full benchmark table
| Benchmark | Kimi K2 Thinking | Kimi K3 |
|---|---|---|
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 4.0 | 50.6 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 15.8 | 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. | 79.0 | 90.8 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 83.0 | 97.2 |
PostTrainBench | 7.3 | 32.0 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 31.6 | 50.6 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 42.8 | 82.6 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.60 | $2.50 | 262K tokens (~131 books) | $10.75 | |
| $0.67 | $14.00 | 1.0M tokens (~524 books) | $40.03 |