How do Kimi K2.7 and SWE-1.7 compare on coding benchmarks?

The comparison table shows SWE-bench, SWE-Pro, SWE-Atlas, Terminal-Bench, DeepSWE, and coding agent index scores for both Kimi K2.7 and SWE-1.7 when publicly disclosed.

LLM Comparison

Kimi K2.7 vs SWE-1.7: benchmark scores, pricing & comparison.

Q: Which is better: Kimi K2.7 or SWE-1.7?

AskClash compares Kimi K2.7 and SWE-1.7 side by side across SWE-bench, GPQA, HLE, Terminal-Bench, coding agent scores, token pricing, and context window so you can see which model wins on each benchmark.

Side-by-side Kimi K2.7 vs SWE-1.7 comparison across SWE-bench, GPQA, HLE, Terminal-Bench, coding agent scores, token pricing, context window, and AskClash RWT. Green marks the winner on each benchmark.

Open live leaderboard Kimi K2.7 model page SWE-1.7 model page

Rank #19 vs #46AskClash overall scores 56.8 vs 26.4.

Pricing $0.95/$4.00 vs $0/$0Input and output token prices per 1M tokens when published.

Open Weight vs ProprietaryMoonshot AI vs Cognition.

Kimi K2.7 vs SWE-1.7 benchmark comparison

Green cells highlight the winning model for each metric. Scores are cached from the AskClash LLM leaderboard snapshot.

Metric	Kimi K2.7	SWE-1.7
Overall Score	56.8	26.4
Leaderboard Rank	#19	#46
RWT	7.5	8.5
HLE	54.0	—
GPQA	90.5	—
SWE-bench	80.2	—
SWE-Pro	58.6	—
Terminal-Bench	66.7	81.5
DeepSWE	30.5	—
OSWorld	73.1	—
MCP Atlas	76.0	—
Finance Agent	44.9	—
CharXiv	80.4	—
MMMU-Pro	79.4	—
Tau2	90.1	—
Input Price (per 1M tokens)	$0.95	$0
Output Price (per 1M tokens)	$4.00	$0
Context Window	256K	256K
Benchmarks Published	13	1

Kimi K2.7 vs SWE-1.7 head-to-head charts

Kimi K2.7 leads 1 and SWE-1.7 leads 2 of 3 shared benchmarks. SWE-1.7 is cheaper on a defined 1M-input / 200K-output workload. Charts show only benchmarks both models publish.

Kimi K2.7SWE-1.7

Overall

56.8Kimi K2.7

26.4SWE-1.7

RWT

7.5Kimi K2.7

8.5SWE-1.7

Terminal-Bench

66.7Kimi K2.7

81.5SWE-1.7

Kimi K2.7

Input$0.95

Output$4.00

Workload$1.75

Context256K

SWE-1.7

Input$0

Output$0

Workload$0.00

Context256K

Workload = published cost of 1M input + 200K output tokens. Open the live leaderboard for interactive compare charts.

More Kimi K2.7 and SWE-1.7 comparisons

Explore how Kimi K2.7 and SWE-1.7 stack up against other top-ranked LLMs.

Claude Fable 5 vs Kimi K2.7 Claude Fable 5 vs SWE-1.7 GPT-5.6 Sol vs Kimi K2.7 GPT-5.6 Sol vs SWE-1.7 Kimi K3 vs Kimi K2.7 Kimi K3 vs SWE-1.7 Claude Opus 4.8 vs Kimi K2.7 Claude Opus 4.8 vs SWE-1.7 Grok 4.5 vs Kimi K2.7 Grok 4.5 vs SWE-1.7

How to read this comparison

Benchmark scores

Higher is better for all benchmark scores (SWE-bench, GPQA, HLE, Terminal-Bench, etc.). Green marks the model with the higher score.

Token pricing

Lower is better for input and output prices. Green marks the cheaper model per 1M tokens.

Coverage matters

Models with fewer disclosed benchmark cells may have inflated percentile scores. Check the benchmark cell count for context.

This comparison page is generated from the AskClash LLM leaderboard cache. Open the live leaderboard for real-time scores and interactive filtering.