Compare · ModelsLive · 2 picked · head to head
Kimi K2 0711 vs Kimi K3
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Kimi K3 wins on 2/2 benchmarks
Kimi K3 wins 2 of 2 shared benchmarks. Leads in reasoning · coding.
Category leads
reasoning·Kimi K3coding·Kimi K3
Head to head · from the data · data as of 2026-11-22
- Benchmarks · Kimi K2 0711 leads on 0 of 2 shared benchmarks, Kimi K3 on 2 (SimpleBench, WeirdML)
- Price · Kimi K2 0711 input $0.57/M vs Kimi K3 $0.19/M, Kimi K3 is 66% cheaper (OpenRouter list price, as of 2026-11-22)
- Cheapest provider · Kimi K2 0711 at Novita $0.57/M input (1 offer) as of 2026-11-22 · Kimi K3 at Wafer $0.15/M input (of 29 offers) as of 2026-11-22
- Context · Kimi K2 0711 131K tokens vs Kimi K3 1.0M tokens
- Released · Kimi K2 0711 Jul 11, 2025 vs Kimi K3 Jul 16, 2026 · 12 months apart
- Open weights · Kimi K2 0711 has open weights (on Hugging Face as moonshotai/Kimi-K2-Instruct)
- Price history · Kimi K2 0711 OpenRouter input list price had no move of 5% or more in the 90 days to 2026-11-22
Sources · scores from public leaderboards, list prices and provider offers from OpenRouter, price moves from the BenchGecko changelog (5% or more, held in the next daily check), Gecko tests run by BenchGecko.
Hype vs Reality
Attention vs performance
Kimi K2 0711
#84 by perf·#16 by attention
Kimi K3
#72 by perf·#16 by attention
Best value
Kimi K2 0711
5.5x better value than Kimi K3
Kimi K2 0711
39.1 pts/$
$1.43/M
Kimi K3
7.1 pts/$
$8.10/M
Vendor risk
Who is behind the model
Moonshot AI
$50.0B·Tier 1
Moonshot AI
$50.0B·Tier 1
Head to head
2 benchmarks · 2 models
Kimi K2 0711Kimi K3
SimpleBench
Kimi K3 leads by +41.3
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
Kimi K2 0711
11.6
Kimi K3
52.8
WeirdML
Kimi K3 leads by +43.2
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Kimi K2 0711
39.4
Kimi K3
82.6
Full benchmark table
| Benchmark | Kimi K2 0711 | Kimi K3 |
|---|---|---|
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 11.6 | 52.8 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 39.4 | 82.6 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.57 | $2.30 | 131K tokens (~66 books) | $10.03 | |
| $0.19 | $16.00 | 1.0M tokens (~524 books) | $41.44 |
Kimi K2 0711 vs Kimi K3 · questions answered from the data
Kimi K2 0711 leads on 0 of 2 shared benchmarks, Kimi K3 on 2 (SimpleBench, WeirdML)