- Rank
- #59
- Total Output Tokens
- 224,128
- Response Time (avg)
- 142.84s
- Total Cost
- $3.467
Kimi K3 (max) vs Inkling (medium)
The average score is effectively tied at 7.9 vs 8.0. Inkling (medium) has the lower benchmark cost at $0.377 vs $3.467. Inkling (medium) is faster at 15.66s vs 142.84s, with pass rates of 77.3% vs 75.8%.
- Rank
- #57
- Total Output Tokens
- 63,842
- Response Time (avg)
- 15.66s
- Total Cost
- $0.377
Recommended model
Inkling (medium)
It has the best score here (8.0), while costing about 9.2x less than Kimi K3 (max).
Detailed comparison
| Metric | Kimi K3 Kimi K3 max | Inkling Inkling medium |
|---|---|---|
| Score | 7.9 | 8.0 |
| Rank | #59 | #57 |
| Reliability | 9.0 | 10.0 |
| Consistency | 9.2 | 8.5 |
| Attempts | 66/66 | 66/66 |
| Tests Correct | ||
| Attempt pass rate | 77.3% | 75.8% |
| Flaky tests | 2 | 4 |
| Total Runs | 66 | 66 |
| Cost per result | 21.668 | 2.551 |
| Total Cost | $3.467 | $0.377 |
| Input Price | $3.000 / 1M | $0.950 / 1M |
| Output Price | $15.000 / 1M | $4.050 / 1M |
| Total Input Tokens | 34,960 | 124,062 |
| Output Tokens | 2,887 | 12,190 |
| Reasoning Tokens | 221,241 | 51,652 |
| Response Time (avg) | 142.84s | 15.66s |
| Response Time (max) | 766.58s | 85.12s |
| Response Time (total) | 2714.02s | 344.52s |
| Parameters | 2.8T total (104B active) | 975B total (41B active) |
| Availability | Weights available | Open source |
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#59 MoonshotAI: Kimi K3
max- Cost
- $0.281
- Time
- 506.9s
- Tokens
- 18,863 tok
#57 Thinking Machines: Inkling
medium- Cost
- $0.004
- Time
- 11.2s
- Tokens
- 852 tok
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Category Breakdown
Quick Compare
Switch Comparison Pair
GPT-5.6 TerrahighvsInklingmediumKimi K3maxvsGPT-5.2 ChatnoneKimi K3maxvsStep 3.7 FlashmediumKimi K3maxvsQwen3.8 27BlowKimi K3maxvsGPT-5.6 TerrahighInklingmediumvsGLM 5.2highGPT-5.2 ChatnonevsInklingmediumKimi K3maxvsQwen3.7 PlusmediumDeepSeek V4 Flash 0731highvsInklingmediumQwen3.8 27BlowvsInklingmediumDeepSeek V4 Flash 0731lowvsInklingmediumKimi K3maxvsGLM 5.2high