Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
kimi-k2-instruct
fireworksai
Context131072 tokens
Input Price$0.6 / 1M tokens
Output Price$2.5 / 1M tokens
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $0.6 / 1M tokens | $3 / 1M tokens |
| Output Price | $2.5 / 1M tokens | $15 / 1M tokens |
Capabilities | ||
| Context Window | 131072 tokens | 256K tokens |
| Capabilities | tools | tools |
| Input type | text | text |
Category Scores | ||
| Overall Average | 75.1 | 71.3 |
| Science | 75.1 | 87.6 |
| Academia | N/A | 76.4 |
| Finance | N/A | 81.0 |
| Marketing | N/A | 51.5 |
| Maths | N/A | 96.7 |
| Programming | N/A | 63.8 |
| Writing | N/A | 42.2 |
Benchmark Tests | ||
| AIME | _ | 94.3 |
| AA Coding Index | _ | 63.8 |
| AAII | _ | 65.3 |
| AA Math Index | _ | 96.7 |
| GPQA | 75.1 | 87.6 |
| HLE | _ | 23.9 |
| HumanEval | 93.3 | _ |
| LiveCodeBench | _ | 81.9 |
| MATH-500 | _ | 99.0 |
| MMLU | 89.5 | _ |
| MMLU-Pro | 81.1 | 86.6 |
| SciCode | _ | 45.7 |
kimi-k2-instruct Advantages
- • Higher benchmark scores (75.1 vs 71.3)
- • Lower input token cost ($0.6 / 1M tokens vs $3 / 1M tokens)
grok-4 Advantages
- • Larger context window (256K tokens vs 131072 tokens)