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 8 of 8 shared benchmarks. Leads in agentic · knowledge · math.

Category leads
agentic·Kimi K3knowledge·Kimi K3math·Kimi K3reasoning·Kimi K3coding·Kimi K3

Head to head · from the data · data as of 2026-11-22

  • Benchmarks · Kimi K2 Thinking leads on 0 of 8 shared benchmarks, Kimi K3 on 8 (APEX-Agents, Chess Puzzles, GPQA diamond, OTIS Mock AIME 2024-2025, 4 more)
  • Price · Kimi K2 Thinking input $0.60/M vs Kimi K3 $0.19/M, Kimi K3 is 68% cheaper (OpenRouter list price, as of 2026-11-22)
  • Cheapest provider · Kimi K2 Thinking at Novita $0.60/M input (1 offer) as of 2026-11-22 · Kimi K3 at Wafer $0.15/M input (of 29 offers) as of 2026-11-22
  • Context · Kimi K2 Thinking 262K tokens vs Kimi K3 1.0M tokens
  • Released · Kimi K2 Thinking Nov 6, 2025 vs Kimi K3 Jul 16, 2026 · 8 months apart
  • Open weights · Kimi K2 Thinking has open weights (on Hugging Face as moonshotai/Kimi-K2-Thinking)
  • Price history · Kimi K2 Thinking OpenRouter input list price had no move of 5% or more in the 90 days to 2026-11-22

Sources · scores from public leaderboards, list prices and provider offers from OpenRouter, price moves from the BenchGecko changelog (5% or more, held in the next daily check), Gecko tests run by BenchGecko.

Hype vs Reality
Kimi K2 Thinking
#125 by perf·#16 by attention
UNDERRATED
Kimi K3
#72 by perf·#16 by attention
UNDERRATED
Best value
4.7x better value than Kimi K3
Kimi K2 Thinking
33.1 pts/$
$1.55/M
Kimi K3
7.1 pts/$
$8.10/M
Vendor risk
moonshotai logo
Moonshot AI
$50.0B·Tier 1
Medium risk
moonshotai logo
Moonshot AI
$50.0B·Tier 1
Medium risk
Head to head
Kimi K2 ThinkingKimi K3
APEX-Agents
Kimi K3 leads by +43.8
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
47.8
Chess Puzzles
Kimi K3 leads by +13.7
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Kimi K2 Thinking
20.0
Kimi K3
33.7
GPQA diamond
Kimi K3 leads by +15.7
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
94.6
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 +24.2
Kimi K2 Thinking
7.3
Kimi K3
31.5
SimpleBench
Kimi K3 leads by +25.3
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
Kimi K2 Thinking
27.5
Kimi K3
52.8
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
BenchmarkKimi K2 ThinkingKimi K3
APEX-Agents
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
4.047.8
Chess Puzzles
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
20.033.7
GPQA diamond
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
79.094.6
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
83.097.2
PostTrainBench
7.331.5
SimpleBench
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
27.552.8
SimpleQA Verified
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
31.650.6
WeirdML
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
42.882.6
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
moonshotai logoKimi K2 Thinking$0.60$2.50262K tokens (~131 books)$10.75
moonshotai logoKimi K3$0.19$16.001.0M tokens (~524 books)$41.44
Kimi K2 Thinking leads on 0 of 8 shared benchmarks, Kimi K3 on 8 (APEX-Agents, Chess Puzzles, GPQA diamond, OTIS Mock AIME 2024-2025, 4 more)