- Rank
- #128
- Total Output Tokens
- 233,327
- Response Time (avg)
- 139.41s
- Total Cost
- $3.409
Kimi K3 (max) vs Grok 4.5 (high)
Kimi K3 (max) leads on average score with 8.3 vs 8.2. Grok 4.5 (high) has the lower benchmark cost at $2.687 vs $3.409. Grok 4.5 (high) is faster at 72.50s vs 139.41s, with pass rates of 78.3% vs 82.6%.
Compared models
- Rank
- #134
- Total Output Tokens
- 333,632
- Response Time (avg)
- 72.50s
- Total Cost
- $2.687
Recommended model
Grok 4.5 (high)
Its score stays close to the best score here (8.2 vs 8.3), while responding about 1.9x faster than Kimi K3 (max).
Detailed comparison
| Metric | Kimi K3 Kimi K3 max | Grok 4.5 Grok 4.5 high |
|---|---|---|
| Score | 8.3 | 8.2 |
| Rank | #128 | #134 |
| Reliability | 9.3 | 10.0 |
| Consistency | 9.3 | 8.9 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 78.3% | 82.6% |
| Flaky tests | 2 | 3 |
| Total Runs | 69 | 69 |
| Cost per result | 23.601 | 15.123 |
| Total Cost | $3.409 | $2.687 |
| Input Price | $0.830 / 1M | $2.000 / 1M |
| Output Price | $14.000 / 1M | $6.000 / 1M |
| Cache Read Price | $0.270 / 1M | $0.300 / 1M |
| Cache Write Price | N/A | N/A |
| Total Input Tokens | 170,700 | 342,124 |
| Output Tokens | 7,719 | 7,135 |
| Reasoning Tokens | 225,608 | 326,497 |
| Response Time (avg) | 139.41s | 72.50s |
| Response Time (max) | 766.58s | 676.83s |
| Response Time (total) | 2788.26s | 1667.51s |
| Parameters | 2.8T total (104B active) | ~1.7T total (~170B active) |
| Availability | Weights available | Closed |
Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#128 MoonshotAI: Kimi K3
max- Cost
- $0.281
- Time
- 506.9s
- Tokens
- 18,863 tok
#134 SpaceXAI: Grok 4.5
high- Cost
- $0.015
- Time
- 29.7s
- Tokens
- 2,737 tok
Category Breakdown
Quick Compare
Switch Comparison Pair
DeepSeek V4.1 Flash 1017maxvsGrok 4.5highGemini 3.5 FlashhighvsKimi K3maxGrok 4.5highvsGLM 5.2mediumQwen3.7 PlusmediumvsGrok 4.5highLing 3.1 FlashmediumvsGrok 4.5highClaude Haiku 5.5highvsKimi K3maxGPT-5.6 TerramediumvsGrok 4.5highClaude Opus 4.8mediumvsGrok 4.5highGPT-6 LunamediumvsGrok 4.5highKimi K3maxvsGPT-5.6 TerrahighKimi K3maxvsGPT-6 LunamediumClaude Opus 4.8mediumvsKimi K3max