Compare · ModelsLive · 2 picked · head to head
Kimi K2.6 vs Kimi K2.7 Code
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Kimi K2.6 wins on 6/9 benchmarks
Kimi K2.6 wins 6 of 9 shared benchmarks. Leads in speed · knowledge · math.
Category leads
speed·Kimi K2.6knowledge·Kimi K2.6math·Kimi K2.6
Hype vs Reality
Attention vs performance
Kimi K2.6
#106 by perf·no signal
Kimi K2.7 Code
#42 by perf·no signal
Best value
Kimi K2.7 Code
1.3x better value than Kimi K2.6
Kimi K2.6
25.4 pts/$
$2.04/M
Kimi K2.7 Code
34.3 pts/$
$1.84/M
Vendor risk
Who is behind the model
moonshotai
private · undisclosed
moonshotai
private · undisclosed
Head to head
9 benchmarks · 2 models
Kimi K2.6Kimi K2.7 Code
Artificial Analysis · Agentic Index
Kimi K2.6 leads by +0.7
Artificial Analysis Agentic Index · a composite score measuring how well a model performs in agentic workflows · multi-step tool use, planning, error recovery, and autonomous task completion. Aggregates results from multiple agentic benchmarks including SWE-bench, tool-use tests, and planning evaluations. The canonical single-number metric for "how good is this model as an agent?"
Kimi K2.6
30.3
Kimi K2.7 Code
29.6
Artificial Analysis · Coding Index
Kimi K2.7 Code leads by +4.7
Artificial Analysis Coding Index · a composite score that aggregates performance across multiple coding benchmarks into a single index. Tracks code generation quality, debugging ability, multi-language competence, and real-world software engineering tasks. Used by Artificial Analysis to rank model coding capability in a normalized, comparable format. Useful for developers choosing between models for coding-heavy workloads.
Kimi K2.6
56.0
Kimi K2.7 Code
60.8
Artificial Analysis · Quality Index
Kimi K2.6 leads by +0.9
Kimi K2.6
42.8
Kimi K2.7 Code
42.0
Chess Puzzles
Kimi K2.6 leads by +5.0
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Kimi K2.6
26.0
Kimi K2.7 Code
21.0
FrontierMath-Tier-4-v2-Private
Kimi K2.6 leads by +13.4
Kimi K2.6
25.6
Kimi K2.7 Code
12.2
FrontierMath-Tiers-1-3-v2-Private
Kimi K2.6 leads by +3.1
Kimi K2.6
57.2
Kimi K2.7 Code
54.0
GPQA diamond
Kimi K2.6 leads by +1.7
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Kimi K2.6
87.7
Kimi K2.7 Code
86.0
OTIS Mock AIME 2024-2025
Kimi K2.7 Code leads by +0.3
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Kimi K2.6
96.1
Kimi K2.7 Code
96.4
SimpleQA Verified
Kimi K2.7 Code leads by +0.5
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Kimi K2.6
38.7
Kimi K2.7 Code
39.2
Full benchmark table
| Benchmark | Kimi K2.6 | Kimi K2.7 Code |
|---|---|---|
Artificial Analysis · Agentic Index Artificial Analysis Agentic Index · a composite score measuring how well a model performs in agentic workflows · multi-step tool use, planning, error recovery, and autonomous task completion. Aggregates results from multiple agentic benchmarks including SWE-bench, tool-use tests, and planning evaluations. The canonical single-number metric for "how good is this model as an agent?" | 30.3 | 29.6 |
Artificial Analysis · Coding Index Artificial Analysis Coding Index · a composite score that aggregates performance across multiple coding benchmarks into a single index. Tracks code generation quality, debugging ability, multi-language competence, and real-world software engineering tasks. Used by Artificial Analysis to rank model coding capability in a normalized, comparable format. Useful for developers choosing between models for coding-heavy workloads. | 56.0 | 60.8 |
Artificial Analysis · Quality Index | 42.8 | 42.0 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 26.0 | 21.0 |
FrontierMath-Tier-4-v2-Private | 25.6 | 12.2 |
FrontierMath-Tiers-1-3-v2-Private | 57.2 | 54.0 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 87.7 | 86.0 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 96.1 | 96.4 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 38.7 | 39.2 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.66 | $3.41 | 262K tokens (~131 books) | $13.48 | |
| $0.61 | $3.07 | 262K tokens (~131 books) | $12.26 |