Compare · ModelsLive · 2 picked · head to head
Kimi K2 0711 vs Kimi K2.5
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Kimi K2.5 wins on 4/4 benchmarks
Kimi K2.5 wins 4 of 4 shared benchmarks. Leads in knowledge · reasoning · coding.
Category leads
knowledge·Kimi K2.5reasoning·Kimi K2.5coding·Kimi K2.5
Hype vs Reality
Attention vs performance
Kimi K2 0711
#61 by perf·no signal
Kimi K2.5
#85 by perf·no signal
Best value
Kimi K2.5
1.3x better value than Kimi K2 0711
Kimi K2 0711
39.2 pts/$
$1.43/M
Kimi K2.5
49.5 pts/$
$1.05/M
Vendor risk
Who is behind the model
moonshotai
private · undisclosed
moonshotai
private · undisclosed
Head to head
4 benchmarks · 2 models
Kimi K2 0711Kimi K2.5
Fiction.LiveBench
Kimi K2.5 leads by +25.0
Fiction.LiveBench · a continuously updated benchmark using recently published fiction to test reading comprehension and reasoning, preventing data contamination.
Kimi K2 0711
61.1
Kimi K2.5
86.1
SimpleBench
Kimi K2.5 leads by +24.6
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
Kimi K2 0711
11.6
Kimi K2.5
36.2
Terminal Bench
Kimi K2.5 leads by +15.4
Terminal Bench · tests the ability to accomplish real-world tasks using terminal commands, evaluating shell scripting and CLI tool proficiency.
Kimi K2 0711
27.8
Kimi K2.5
43.2
WeirdML
Kimi K2.5 leads by +6.2
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Kimi K2 0711
39.4
Kimi K2.5
45.6
Full benchmark table
| Benchmark | Kimi K2 0711 | Kimi K2.5 |
|---|---|---|
Fiction.LiveBench Fiction.LiveBench · a continuously updated benchmark using recently published fiction to test reading comprehension and reasoning, preventing data contamination. | 61.1 | 86.1 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 11.6 | 36.2 |
Terminal Bench Terminal Bench · tests the ability to accomplish real-world tasks using terminal commands, evaluating shell scripting and CLI tool proficiency. | 27.8 | 43.2 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 39.4 | 45.6 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| Kimi K2 0711 | $0.57 | $2.30 | 131K tokens (~66 books) | $10.03 |
| Kimi K2.5 | $0.38 | $1.72 | 262K tokens (~131 books) | $7.17 |