readable AI benchmarks (simplified)
Kimi
Kimi K2 Thinking
Kimi K2 Thinking has a Quality Score of 36.6, ranking 201st among 551 scored models. Per 1M tokens, pricing is $0.600 input, $2.50 output, and $0.600 cached input. It accepts text input, outputs text, and has a 256k token context window. Its Reliability Score is 39.3, ranking 222nd among 553 scored models, above average (total average: 35.6). Its Value Score is 26.3, low compared with the total Value average of 30.7.
Quality Score36.6coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score26.3
Factual reliability39.3
Cache Discount0%
Model specification
- Reasoning
- reasoning
- Input modalities
- text
- Output modalities
- text
- Context window
- 256k tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.600
- Output
- $2.50
- Cached Input
- $0.600
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 22.0
- Coding
- not available
- Agentic
- not available
- Omniscience
- -21.4
- Correct
- 30.9%
- Blended price
- $0.790
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 83.1%
Correct 30.9%Incorrect 52.3%Partial / not attempted 16.9%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 24%
- GPQA Diamond
- 84%
- CritPt
- 3%
- AA-Omniscience
- 39%
- AA-LCR
- 72%
Similar models
- Kimi K2.5 (Reasoning)KimiQuality Score 41.2Value Score 30.4
- Kimi K2.7 CodeKimiQuality Score 42.3Value Score 30.8
- Kimi K2.6KimiQuality Score 47.1Value Score 34.4
- Kimi K2.5 (Non-reasoning)KimiQuality Score 36.5Value Score 26.1
- Kimi K3 (low)KimiQuality Score 52.5Value Score 33.2
- Kimi K2.6 (Non-reasoning)KimiQuality Score 40.8Value Score 29.8