How do Kimi K3 and MiniMax-M3 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 K3 and MiniMax-M3 when publicly disclosed.

LLM Comparison

Kimi K3 vs MiniMax-M3: benchmark scores, pricing & comparison.

Q: Which is better: Kimi K3 or MiniMax-M3?

AskClash compares Kimi K3 and MiniMax-M3 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 K3 vs MiniMax-M3 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 K3 model page MiniMax-M3 model page

Rank #3 vs #17AskClash overall scores 82.3 vs 59.0.

Pricing $3.00/$15.0 vs $0.30/$1.20Input and output token prices per 1M tokens when published.

Open Weight vs Open WeightMoonshot AI vs MiniMax.

Kimi K3 vs MiniMax-M3 benchmark comparison

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

Metric	Kimi K3	MiniMax-M3
Overall Score	82.3	59.0
Leaderboard Rank	#3	#17
RWT	—	8.5
HLE	43.5	37.1
GPQA	93.5	92.9
IFEval	—	82.9
SWE-bench	—	80.5
SWE-Pro	—	59.0
Terminal-Bench	88.3	66.0
DeepSWE	67.5	—
OSWorld	—	70.1
MCP Atlas	84.2	74.2
Finance Agent	—	48.3
CharXiv	84.8	—
MMMU-Pro	81.6	78.1
Tau2	—	88.9
Input Price (per 1M tokens)	$3.00	$0.30
Output Price (per 1M tokens)	$15.0	$1.20
Context Window	1M	1M
Benchmarks Published	9	13

Kimi K3 vs MiniMax-M3 head-to-head charts

Kimi K3 leads 6 and MiniMax-M3 leads 0 of 6 shared benchmarks. MiniMax-M3 is cheaper on a defined 1M-input / 200K-output workload. Charts show only benchmarks both models publish.

Kimi K3MiniMax-M3

Overall

82.3Kimi K3

59.0MiniMax-M3

HLE

43.5Kimi K3

37.1MiniMax-M3

GPQA

93.5Kimi K3

92.9MiniMax-M3

Terminal-Bench

88.3Kimi K3

66.0MiniMax-M3

MCP Atlas

84.2Kimi K3

74.2MiniMax-M3

MMMU-Pro

81.6Kimi K3

78.1MiniMax-M3

Kimi K3

Input$3.00

Output$15.0

Workload$6.00

Context1M

MiniMax-M3

Input$0.30

Output$1.20

Workload$0.54

Context1M

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

More Kimi K3 and MiniMax-M3 comparisons

Explore how Kimi K3 and MiniMax-M3 stack up against other top-ranked LLMs.

Claude Fable 5 vs Kimi K3 Claude Fable 5 vs MiniMax-M3 GPT-5.6 Sol vs Kimi K3 GPT-5.6 Sol vs MiniMax-M3 Kimi K3 vs Claude Opus 4.8 Claude Opus 4.8 vs MiniMax-M3 Kimi K3 vs Grok 4.5 Grok 4.5 vs MiniMax-M3 Kimi K3 vs Muse Spark 1.1 Muse Spark 1.1 vs MiniMax-M3

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.