- Rank
- #164
- Total Output Tokens
- 121,223
- Response Time (avg)
- 58.14s
- Total Cost
- $2.405
Ember-1 (high) vs Kimi K2.6 (medium)
The average score is effectively tied at 6.9 vs 6.8. Kimi K2.6 (medium) has the lower benchmark cost at $1.323 vs $2.405. Ember-1 (high) is faster at 58.14s vs 121.25s, with pass rates of 71.0% vs 60.9%.
Compared models
- Rank
- #168
- Total Output Tokens
- 396,671
- Response Time (avg)
- 121.25s
- Total Cost
- $1.323
Recommended model
Kimi K2.6 (medium)
It has the best score here (6.8), while costing about 1.8x less than Ember-1 (high).
Detailed comparison
| Metric | Ember-1 Ember-1 high | Kimi K2.6 Kimi K2.6 medium |
|---|---|---|
| Score | 6.9 | 6.8 |
| Rank | #164 | #168 |
| Reliability | 8.6 | 10.0 |
| Consistency | 7.2 | 8.4 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 71.0% | 60.9% |
| Flaky tests | 8 | 4 |
| Total Runs | 69 | 69 |
| Cost per result | 20.041 | 12.282 |
| Total Cost | $2.405 | $1.323 |
| Input Price | $3.000 / 1M | $0.650 / 1M |
| Output Price | $15.000 / 1M | $3.410 / 1M |
| Total Input Tokens | 195,489 | 226,880 |
| Output Tokens | 12,475 | 65,346 |
| Reasoning Tokens | 108,748 | 331,325 |
| Response Time (avg) | 58.14s | 121.25s |
| Response Time (max) | 255.06s | 876.20s |
| Response Time (total) | 1337.19s | 2667.55s |
| Parameters | ~2.8T total (~104B active) | 1T total (32B active) |
| Availability | Closed | Weights available |
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#164 Ember-1
high- Cost
- $0.038
- Time
- 55.1s
- Tokens
- 2,671 tok
#168 MoonshotAI: Kimi K2.6
medium- Cost
- $0.013
- Time
- 103.4s
- Tokens
- 3,620 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
Ember-1highvsGemini 3.1 Flash LitemediumEmber-1highvsGemma 4 31BmediumFree AvailableEmber-1highvsGPT-5.6 LunalowKimi K2.6mediumvsInklinglowFree AvailableClaude Sonnet 5.5lowvsEmber-1highClaude Sonnet 5.5lowvsKimi K2.6mediumKimi K2.6mediumvsGPT-5.6 LunalowKimi K2.6mediumvsGPT-6 SolnoneClaude Opus 4.8nonevsEmber-1highEmber-1highvsQwen3.5-FlashmediumEmber-1highvsInklinglowFree AvailableEmber-1highvsMercury 2.5 Previewmedium