- Rank
- #295
- Total Output Tokens
- 11,832
- Response Time (avg)
- 22.65s
- Total Cost
- $0.786
Ember-1 vs Kimi K2.5
Ember-1 leads on average score with 5.4 vs 5.3. Kimi K2.5 has the lower benchmark cost at $0.262 vs $0.786. Ember-1 is faster at 22.65s vs 35.86s, with pass rates of 43.5% vs 29.0%.
Compared models
- Rank
- #299
- Total Output Tokens
- 49,389
- Response Time (avg)
- 35.86s
- Total Cost
- $0.262
Recommended model
Kimi K2.5
Its score stays close to the best score here (5.3 vs 5.4), while costing about 3.0x less than Ember-1.
Detailed comparison
| Metric | Ember-1 Ember-1 none | Kimi K2.5 Kimi K2.5 none |
|---|---|---|
| Score | 5.4 | 5.3 |
| Rank | #295 | #299 |
| Reliability | 8.8 | 10.0 |
| Consistency | 8.6 | 8.6 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 43.5% | 29.0% |
| Flaky tests | 4 | 4 |
| Total Runs | 69 | 69 |
| Cost per result | 9.817 | 4.976 |
| Total Cost | $0.786 | $0.262 |
| Input Price | $3.000 / 1M | $0.450 / 1M |
| Output Price | $15.000 / 1M | $2.250 / 1M |
| Cache Read Price | $0.300 / 1M | $0.070 / 1M |
| Cache Write Price | N/A | N/A |
| Total Input Tokens | 202,617 | 275,349 |
| Output Tokens | 11,832 | 49,377 |
| Reasoning Tokens | 0 | 12 |
| Response Time (avg) | 22.65s | 35.86s |
| Response Time (max) | 93.12s | 321.19s |
| Response Time (total) | 520.91s | 609.61s |
| Parameters | ~2.8T total (~104B active) | 1T total (32B active) |
| Availability | Closed | Weights available |
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.
#295 Ember-1
none- Cost
- $0.156
- Time
- 224.6s
- Tokens
- 10,555 tok
#299 MoonshotAI: Kimi K2.5
none- Cost
- $0.015
- Time
- 89.1s
- Tokens
- 5,421 tok
Category Breakdown
Quick Compare
Switch Comparison Pair
Ember-1nonevsStep 3.5 FlashmediumGranite 4.2 8BlowvsKimi K2.5noneEmber-1nonevsHy4 previewlowNorth Mini CodemediumFree AvailablevsEmber-1noneEmber-1nonevsGranite 4.2 8BlowKimi K2.5nonevsStep 3.5 FlashmediumKimi K2.5nonevsHy4 previewlowKimi K2.5nonevsInkling SmalllowFree AvailableNorth Mini CodemediumFree AvailablevsKimi K2.5noneKimi K2.5nonevsNemotron 3.5 LightninghighFree AvailableKAT Coder AIR V2.5highvsKimi K2.5noneEmber-1nonevsInkling SmalllowFree Available