Model Comparison
Kimi K2 0905
vs. Gemini 3.1 Pro Preview
Comparing 2 AI models · 10 benchmarks · MoonshotAI, Google
Recommended Pick
Go Gemini 3.1 Pro Preview 11 metric wins Strongest on: Throughput, Reasoning, Intelligence
Best Value
Kimi K2 0905
100.0 value score
45.7 reasoning / $1.07/1M
Lowest Price
Kimi K2 0905
$0.60/1M input price
Best Reasoning
Gemini 3.1 Pro Preview
65.3 reasoning score
Blends available reasoning benchmarks
Best for Coding
Gemini 3.1 Pro Preview
55.5 coding index
Composite Indices
Higher is better; speed and price are normalized
Standard Benchmarks
Only benchmarks with data are shown
Differences That Matter
Best value
Kimi K2 0905 has the strongest quality-to-price mix at 100.0 out of 100 value points.
Price gap
Kimi K2 0905 is 3.3x cheaper on input tokens than Gemini 3.1 Pro Preview.
Speed gap
Gemini 3.1 Pro Preview generates about 5.7x as many tokens per second as Kimi K2 0905.
Reasoning gap
Gemini 3.1 Pro Preview leads Kimi K2 0905 by 19.6 points on reasoning.
Coding gap
Gemini 3.1 Pro Preview leads Kimi K2 0905 by 29.6 points on coding.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
Kimi K2 0905
MoonshotAI
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Gemini 3.1 Pro Preview
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Mo Kimi K2 0905 | Top Pick Go Gemini 3.1 Pro Preview |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.60/1M | $2.00/1M |
| Output Cost | $2.50/1M | $12.00/1M |
| Blended (3:1) | $1.07/1M | $4.50/1M |
| Specifications | ||
| Organization | MoonshotAI | |
| Release Date | Sep 5, 2025 | Feb 19, 2026 |
| Performance & Speed | ||
| Throughput | 22.9 tok/s | 131.4 tok/s |
| TTFT | 1573ms | 26995ms |
| Latency | 1573ms | 26995ms |
| Composite Indices | ||
| Value Score | 100.0 | 34.1 |
| Reasoning Score | 45.7 | 65.3 |
| Intelligence | 30.9 | 57.2 |
| Coding | 25.9 | 55.5 |
| Math | 57.3 | — |
| Standard Benchmarks | ||
| GPQA | 76.7% | 94.1% |
| MMLU Pro | 81.9% | — |
| HLE | 6.3% | 44.7% |
| LiveCodeBench | 61.0% | — |
| AIME 2025 | 57.3% | — |
| SciCode | 30.7% | 58.9% |
| LCR | 52.3% | 72.7% |
| IFBench | 41.7% | 77.1% |
| TAU-bench v2 | 73.4% | 95.6% |
| TerminalBench Hard | 23.5% | 53.8% |
Key Takeaways
Kimi K2 0905 offers the best value at $0.60/1M, making it ideal for high-volume applications and cost-conscious projects.
Gemini 3.1 Pro Preview has the strongest reasoning profile with a 65.3 reasoning score, combining the available reasoning-heavy benchmarks.
Gemini 3.1 Pro Preview reaches a 55.5 coding index, making it the top choice for software development and code generation tasks.
All models support context windows of ∞+ tokens, suitable for processing lengthy documents and maintaining extended conversations.
When to Choose Each Model
Kimi K2 0905
- Cost-sensitive applications
- High-volume processing
Gemini 3.1 Pro Preview
- Complex reasoning tasks
- Research & analysis
- Code generation
- Software development
