Compare · ModelsLive · 2 picked · head to head
Kimi K2.7 Code vs Kimi K3.1 Pro
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Kimi K3.1 Pro wins on 6/6 benchmarks
Kimi K3.1 Pro wins 6 of 6 shared benchmarks. Leads in knowledge · math.
Category leads
knowledge·Kimi K3.1 Promath·Kimi K3.1 Pro
Hype vs Reality
Attention vs performance
Kimi K2.7 Code
#78 by perf·#15 by attention
Kimi K3.1 Pro
#29 by perf·#15 by attention
Best value
Kimi K2.7 Code
2.4x better value than Kimi K3.1 Pro
Kimi K2.7 Code
27.4 pts/$
$2.05/M
Kimi K3.1 Pro
11.3 pts/$
$6.00/M
Vendor risk
Who is behind the model
Moonshot AI
$50.0B·Tier 1
Moonshot AI
$50.0B·Tier 1
Head to head
6 benchmarks · 2 models
Kimi K2.7 CodeKimi K3.1 Pro
Chess Puzzles
Kimi K3.1 Pro leads by +32.6
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Kimi K2.7 Code
9.5
Kimi K3.1 Pro
42.1
FrontierMath-Tier-4-v2-Private
Kimi K3.1 Pro leads by +53.6
Kimi K2.7 Code
12.2
Kimi K3.1 Pro
65.8
FrontierMath-Tiers-1-3-v2-Private
Kimi K3.1 Pro leads by +25.5
Kimi K2.7 Code
56.9
Kimi K3.1 Pro
82.4
GPQA diamond
Kimi K3.1 Pro leads by +8.8
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Kimi K2.7 Code
87.3
Kimi K3.1 Pro
96.1
OTIS Mock AIME 2024-2025
Kimi K3.1 Pro leads by +4.5
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Kimi K2.7 Code
95.5
Kimi K3.1 Pro
100.0
SimpleQA Verified
Kimi K3.1 Pro leads by +25.7
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Kimi K2.7 Code
36.5
Kimi K3.1 Pro
62.2
Full benchmark table
| Benchmark | Kimi K2.7 Code | Kimi K3.1 Pro |
|---|---|---|
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 9.5 | 42.1 |
FrontierMath-Tier-4-v2-Private | 12.2 | 65.8 |
FrontierMath-Tiers-1-3-v2-Private | 56.9 | 82.4 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 87.3 | 96.1 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 95.5 | 100.0 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 36.5 | 62.2 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.60 | $3.50 | 262K tokens (~131 books) | $13.25 | |
| $2.00 | $10.00 | 1.0M tokens (~524 books) | $40.00 |