How do Gemini 3.8 Flash and Kimi K3 compare on coding benchmarks?

The comparison table shows SWE-bench, SWE-Pro, SWE-Atlas, Terminal-Bench, DeepSWE, and coding agent index scores for both Gemini 3.8 Flash and Kimi K3 when publicly disclosed.

LLM Comparison

Gemini 3.8 Flash vs Kimi K3: benchmark scores, pricing & comparison.

Q: Which is better: Gemini 3.8 Flash or Kimi K3?

AskClash compares Gemini 3.8 Flash and Kimi K3 side by side across SWE-bench, GPQA, HLE, Terminal-Bench, coding agent scores, token pricing, AskClash ACB, and context window so you can see which model wins on each benchmark.

Side-by-side Gemini 3.8 Flash vs Kimi K3 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 Gemini 3.8 Flash model page Kimi K3 model page

Rank #8 vs #9AskClash overall scores 63.3 vs 62.8.

Pricing $1.50/$7.50 vs $3.00/$15.0Input and output token prices per 1M tokens when published.

Proprietary vs Open WeightGoogle vs Moonshot AI.

Gemini 3.8 Flash vs Kimi K3 benchmark comparison

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

Metric	Gemini 3.8 Flash	Kimi K3
Overall Score	63.3	62.8
Leaderboard Rank	#8	#9
ACB	61.1	57.7
RWT	—	8.0
HLE	54.9	43.5
GPQA	—	93.5
Terminal-Bench	89.4	88.3
DeepSWE	73.8	68.5
GDPval-AA	1545.0	1668.0
MCP Atlas	—	84.2
Finance Agent	61.4	54.4
CharXiv	86.2	84.8
MMMU-Pro	—	81.6
Input Price (per 1M tokens)	$1.50	$3.00
Output Price (per 1M tokens)	$7.50	$15.0
Context Window	1M	1M
Benchmarks Published	7	11

Gemini 3.8 Flash vs Kimi K3 head-to-head charts

Gemini 3.8 Flash leads 7 and Kimi K3 leads 1 of 8 shared benchmarks. Gemini 3.8 Flash is cheaper on a defined 1M-input / 200K-output workload. Charts show only benchmarks both models publish.

Gemini 3.8 FlashKimi K3

Overall

63.3Gemini 3.8 Flash

62.8Kimi K3

ACB

61.1Gemini 3.8 Flash

57.7Kimi K3

HLE

54.9Gemini 3.8 Flash

43.5Kimi K3

Terminal-Bench

89.4Gemini 3.8 Flash

88.3Kimi K3

DeepSWE

73.8Gemini 3.8 Flash

68.5Kimi K3

GDPval-AA

1545.0Gemini 3.8 Flash

1668.0Kimi K3

Finance Agent

61.4Gemini 3.8 Flash

54.4Kimi K3

CharXiv

86.2Gemini 3.8 Flash

84.8Kimi K3

Gemini 3.8 Flash

Input$1.50

Output$7.50

Workload$3.00

Context1M

Kimi K3

Input$3.00

Output$15.0

Workload$6.00

Context1M

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

More Gemini 3.8 Flash and Kimi K3 comparisons

Explore how Gemini 3.8 Flash and Kimi K3 stack up against other top-ranked LLMs.

Claude Fable 5.1 vs Gemini 3.8 Flash Claude Fable 5.1 vs Kimi K3 Claude Fable 5 vs Gemini 3.8 Flash Claude Fable 5 vs Kimi K3 GPT-5.6 Sol vs Gemini 3.8 Flash GPT-5.6 Sol vs Kimi K3 Claude Opus 5 vs Gemini 3.8 Flash Claude Opus 5 vs Kimi K3 Grok 4.6 vs Gemini 3.8 Flash Grok 4.6 vs Kimi K3

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.