LLM Comparison
Kimi K2.5 vs Llama 4 Maverick
Side-by-side specs, pricing & capabilities
Add to comparison
2/6 modelsSame tier:
| Organization | ||
| OpenTools Score | 9 22.9 | |
| Family | Kimi | Llama |
| Status | Current | Current |
| Release Date | Jan 2026 | Apr 2025 |
| Context Window | 262K tokens | 1.0M tokens |
| Input Price | $0.38/M tokens | $0.15/M tokens |
| Output Price | $1.72/M tokens | $0.60/M tokens |
| Pricing Notes | Cache read: $0.1913/M tokens | — |
| Capabilities | textvisioncode | textvisioncode |
| Max Output | 66K tokens | 16K tokens |
| API Identifier | moonshotai/kimi-k2.5 | meta-llama/llama-4-maverick |
| Benchmarks | ||
| AIME 2025 | — | 19.3%artificial-analysis |
| Artificial Analysis Intelligence Index v4.3 | — | 9.3 indexartificial-analysis |
| GPQA Diamond | — | 69.8%meta |
| GPQA Diamond | 87.9%artificial-analysis | 67.1%artificial-analysis |
| GPQA Diamond | 87.6%https://huggingface.co/moonshotai/Kimi-K2.5 | — |
| LiveCodeBench (10/01/2024-02/01/2025) | — | 43.4%meta |
| MMLU Pro | — | 80.5%meta |
| MMLU-Pro | 87.1%https://huggingface.co/moonshotai/Kimi-K2.5 | — |
| MMMU | — | 73.4%meta |
| SciCode | — | 31.7%artificial-analysis |
| Terminal-Bench 2.1 | 45.7%artificial-analysis | 7.9%artificial-analysis |
| View Kimi K2.5 | View Llama 4 Maverick | |
Cost Calculator
Enter your expected monthly token usage to compare costs.
| Model | Input | Output | Total / mo | vs Best |
|---|---|---|---|---|
| Llama 4 MaverickCheapest | $0.15 | $0.30 | $0.45 | — |
| Kimi K2.5 | $0.38 | $0.86 | $1.24 | +176% |
Moonshot AI
Kimi K2.5
Kimi K2.5 is a multimodal llm from Moonshot AI. Supports up to 262,144 token context window. Available from $0.38/M input tokens.
Meta
Llama 4 Maverick
Llama 4 Maverick is a multimodal llm from Meta. Supports up to 1,048,576 token context window. Achieves 88.4% on MMLU. Available from $0.15/M input tokens.
More Comparisons
Looking for more AI models?
Browse All LLMs