AI BENCHY Compare
Inception: Mercury 2 vs MoonshotAI: Kimi K2.5
Vergelijken:
Benchmarks gegenereerd uit AI BENCHY-testsuites op: 2026-03-05
| Metriek | Inception: Mercury 2 none Releasedatum: 2026-02-24 | MoonshotAI: Kimi K2.5 medium Releasedatum: 2026-01-27 |
|---|---|---|
| Rang | #50 | #29 |
| Gem. score | 3.4 | 6.4 |
| Correcte tests | ||
| Consistentie | 8.9 | 7.8 |
| Kosten per resultaat | 0.147 | 2.082 |
| Totale kosten | $0.006 | $0.188 |
| Slaagpercentage per poging | 33.3% | 73.3% |
| Instabiele tests | 2 | 4 |
| common.totalAttempts | 45 (15 x 3) | 45 (15 x 3) |
| Uitvoer-tokens | 1,144 | 34,638 |
| Redeneer-tokens | 0 | 68,234 |
| Responstijd (gem.) | 594ms | 69.84s |
| Responstijd (max) | 1.27s | 137.29s |
| Responstijd (totaal) | 8.91s | 558.72s |
Responstijd (gem.)
Score vs totale kosten
Gem. score vs Responstijd (gem.)
Categorie-uitsplitsing
| Anti-AI-trucs | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|
| Inception: Mercury 2 | 10.0 | 10.0 | 0.0% | 0 | 466ms | 274 | 0 | |
| MoonshotAI: Kimi K2.5 | 7.0 | 7.2 | 88.9% | 1 | 85.28s | 335 | 6,255 |
| Gecombineerd | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|
| Inception: Mercury 2 | 10.0 | 10.0 | 0.0% | 0 | 606ms | 131 | 0 | |
| MoonshotAI: Kimi K2.5 | 10.0 | 10.0 | 100.0% | 0 | 71.37s | 703 | 3,713 |
| Gegevensparsering en extractie | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|
| Inception: Mercury 2 | 5.5 | 5.9 | 83.3% | 1 | 667ms | 180 | 0 | |
| MoonshotAI: Kimi K2.5 | 9.9 | 10.0 | 100.0% | 0 | 49.78s | 563 | 7,940 |
| Domeinspecifiek | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|
| Inception: Mercury 2 | 4.0 | 7.2 | 44.4% | 1 | 534ms | 46 | 0 | |
| MoonshotAI: Kimi K2.5 | 10.0 | 4.4 | 33.3% | 2 | 137.29s | 20,753 | 30,564 |
| Instructies opvolgen | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|
| Inception: Mercury 2 | 5.5 | 10.0 | 50.0% | 0 | 551ms | 82 | 0 | |
| MoonshotAI: Kimi K2.5 | 10.0 | 10.0 | 100.0% | 0 | 92.47s | 5,371 | 6,547 |
| Puzzle Solving | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|
| Inception: Mercury 2 | 10.0 | 10.0 | 0.0% | 0 | 533ms | 234 | 0 | |
| MoonshotAI: Kimi K2.5 | 4.0 | 7.3 | 44.4% | 1 | 45.40s | 6,671 | 12,403 |
| Toolaanroepen | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|
| Inception: Mercury 2 | 10.0 | 10.0 | 100.0% | 0 | 1.27s | 197 | 0 | |
| MoonshotAI: Kimi K2.5 | 10.0 | 10.0 | 100.0% | 0 | 31.74s | 242 | 812 |
Snelle vergelijking
Vergelijkingspaar wisselen
Kimi K2.5mediumvsQwen3.5 Plus 2026-02-15noneMercury 2nonevsQwen3 Coder NextmediumMercury 2nonevsGLM 4.7 FlashmediumClaude Sonnet 4.6nonevsKimi K2.5mediumGemini 3 Flash PreviewnonevsKimi K2.5mediumKimi K2.5mediumvsGLM 5noneGemini 3.1 Flash Lite PreviewnonevsKimi K2.5mediumKimi K2.5mediumvsGPT-5.3 ChatnoneGemini 3.1 Flash Lite PreviewlowvsKimi K2.5mediumGemini 2.5 FlashnonevsKimi K2.5mediumDeepSeek V3.2nonevsKimi K2.5mediumKimi K2.5mediumvsGPT-5.2 Chatnone