Compare · ModelsLive · 2 picked · head to head
o1 vs Kimi K2.5
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Kimi K2.5 wins on 7/7 benchmarks
Kimi K2.5 wins 7 of 7 shared benchmarks. Leads in reasoning · knowledge · math.
Category leads
reasoning·Kimi K2.5knowledge·Kimi K2.5math·Kimi K2.5coding·Kimi K2.5
Hype vs Reality
Attention vs performance
o1
#59 by perf·no signal
Kimi K2.5
#87 by perf·no signal
Best value
Kimi K2.5
28.3x better value than o1
o1
1.5 pts/$
$37.50/M
Kimi K2.5
42.6 pts/$
$1.22/M
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
moonshotai
private · undisclosed
Head to head
7 benchmarks · 2 models
o1Kimi K2.5
ARC-AGI
Kimi K2.5 leads by +34.6
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
o1
30.7
Kimi K2.5
65.3
Fiction.LiveBench
Kimi K2.5 leads by +2.8
Fiction.LiveBench · a continuously updated benchmark using recently published fiction to test reading comprehension and reasoning, preventing data contamination.
o1
83.3
Kimi K2.5
86.1
FrontierMath-2025-02-28-Private
Kimi K2.5 leads by +18.6
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
o1
9.3
Kimi K2.5
27.9
GPQA diamond
Kimi K2.5 leads by +14.5
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
o1
69.0
Kimi K2.5
83.5
OTIS Mock AIME 2024-2025
Kimi K2.5 leads by +18.9
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
o1
73.3
Kimi K2.5
92.2
SimpleBench
Kimi K2.5 leads by +8.0
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
o1
28.1
Kimi K2.5
36.2
WeirdML
Kimi K2.5 leads by +1.8
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
o1
43.8
Kimi K2.5
45.6
Full benchmark table
| Benchmark | o1 | Kimi K2.5 |
|---|---|---|
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 30.7 | 65.3 |
Fiction.LiveBench Fiction.LiveBench · a continuously updated benchmark using recently published fiction to test reading comprehension and reasoning, preventing data contamination. | 83.3 | 86.1 |
FrontierMath-2025-02-28-Private FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning. | 9.3 | 27.9 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 69.0 | 83.5 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 73.3 | 92.2 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 28.1 | 36.2 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 43.8 | 45.6 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
People also compared