- Rang
- #206
- Totaal aantal uitvoer-tokens
- 138,946
- Responstijd (gem.)
- 7.74s
- Totale kosten
- $0.034
Mercury 2.5 (medium) vs Qwen3.6 27B
De gemiddelde score is vrijwel gelijk met 6.4 vs 6.3. Mercury 2.5 (medium) heeft lagere benchmarkkosten met $0.034 vs $0.147. Mercury 2.5 (medium) is sneller met 7.74s vs 12.71s, met slagingspercentages van 63.8% vs 47.8%.
Vergeleken modellen
- Rang
- #213
- Totaal aantal uitvoer-tokens
- 20,816
- Responstijd (gem.)
- 12.71s
- Totale kosten
- $0.147
Aanbevolen model
Mercury 2.5 (medium)
Het heeft hier de beste score (6.4) en kost ongeveer 4.4x minder dan Qwen3.6 27B.
Gedetailleerde vergelijking
| Metriek | Mercury 2.5 Mercury 2.5 medium | Qwen3.6 27B Qwen3.6 27B none |
|---|---|---|
| Score | 6.4 | 6.3 |
| Rang | #206 | #213 |
| Betrouwbaarheid | 9.7 | 10.0 |
| Consistentie | 8.3 | 7.7 |
| Pogingen | 69/69 | 69/69 |
| Correcte tests | ||
| Slaagpercentage per poging | 63.8% | 47.8% |
| Instabiele tests | 5 | 6 |
| Totaal runs | 69 | 69 |
| Kosten per resultaat | 0.280 | 1.874 |
| Totale kosten | $0.034 | $0.147 |
| Invoerprijs | $0.040 / 1M | $0.320 / 1M |
| Uitvoerprijs | $0.150 / 1M | $3.200 / 1M |
| Totaal aantal invoer-tokens | 317,982 | 250,919 |
| Uitvoer-tokens | 3,918 | 20,816 |
| Redeneer-tokens | 135,028 | 0 |
| Responstijd (gem.) | 7.74s | 12.71s |
| Responstijd (max) | 107.89s | 156.31s |
| Responstijd (totaal) | 178.07s | 292.29s |
| Parameters | ~100B | 27B |
| Beschikbaarheid | Gesloten broncode | Open-source |
Model generatie-showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#206 Mercury 2.5
medium- Kosten
- $0.001
- Tijd
- 3.8s
- Tokens
- 3,386 tok
#213 Qwen3.6 27B
none- Kosten
- $0.009
- Tijd
- 83.0s
- Tokens
- 4,549 tok
Topmodellen op score
Score vs totale kosten
Responstijd (gem.)
Score vs Responstijd (gem.)
Totaal aantal uitvoer-tokens
Score vs Totaal aantal uitvoer-tokens
Categorie-uitsplitsing
| Agenttaken | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Invoer-tokens | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 | 4.7 | 3.1 | 33.3% | 1 | 107.89s | 226,580 | 780 | 18,037 | |
| Qwen3.6 27B | 10.0 | 10.0 | 100.0% | 0 | 58.61s | 155,114 | 4,660 | 0 |
| Anti-AI-trucs | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Invoer-tokens | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 | 10.0 | 10.0 | 100.0% | 0 | 1.28s | 773 | 192 | 7,122 | |
| Qwen3.6 27B | 3.8 | 3.7 | 41.7% | 3 | 2.83s | 696 | 490 | 0 |
| Programmeren | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Invoer-tokens | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 | 5.0 | 5.1 | 44.5% | 2 | 3.70s | 7,807 | 488 | 21,857 | |
| Qwen3.6 27B | 5.5 | 10.0 | 33.3% | 0 | 4.16s | 7,913 | 539 | 0 |
| Gecombineerd | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Invoer-tokens | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 | 6.5 | 10.0 | 50.0% | 0 | 9.23s | 62,336 | 1,073 | 34,370 | |
| Qwen3.6 27B | 3.2 | 9.1 | 0.0% | 0 | 83.13s | 65,572 | 13,744 | 0 |
| Gegevensparsering en extractie | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Invoer-tokens | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 | 10.0 | 10.0 | 100.0% | 0 | 2.57s | 8,385 | 582 | 9,343 | |
| Qwen3.6 27B | 7.3 | 5.8 | 83.3% | 1 | 2.06s | 7,788 | 248 | 0 |
| Domeinspecifiek | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Invoer-tokens | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 | 3.6 | 7.2 | 22.2% | 1 | 4.39s | 852 | 59 | 19,837 | |
| Qwen3.6 27B | 7.7 | 10.0 | 66.7% | 0 | 2.79s | 798 | 25 | 0 |
| Algemene intelligentie | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Invoer-tokens | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 | 4.4 | 9.9 | 0.0% | 0 | 1.60s | 528 | 98 | 2,364 | |
| Qwen3.6 27B | 5.2 | 9.9 | 0.0% | 0 | 1.07s | 522 | 72 | 0 |
| Instructies opvolgen | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Invoer-tokens | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 | 6.4 | 6.0 | 66.7% | 1 | 1.07s | 520 | 55 | 2,344 | |
| Qwen3.6 27B | 6.2 | 5.8 | 66.7% | 1 | 1.92s | 711 | 49 | 0 |
| Puzzeloplossing | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Invoer-tokens | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 | 10.0 | 10.0 | 100.0% | 0 | 1.93s | 766 | 290 | 7,721 | |
| Qwen3.6 27B | 5.3 | 7.2 | 44.4% | 1 | 5.15s | 714 | 639 | 0 |
| Toolaanroepen | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Invoer-tokens | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 | 10.0 | 10.0 | 100.0% | 0 | 3.35s | 9,203 | 269 | 4,641 | |
| Qwen3.6 27B | 9.5 | 10.0 | 100.0% | 0 | 6.74s | 10,881 | 339 | 0 |
| Algemene kennis | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Invoer-tokens | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 | 3.0 | 10.0 | 0.0% | 0 | 4.30s | 232 | 32 | 7,392 | |
| Qwen3.6 27B | 3.0 | 10.0 | 0.0% | 0 | 4.03s | 210 | 11 | 0 |
Snelle vergelijking
Vergelijkingspaar wisselen
Gemini 3.5 FlashminimalvsMercury 2.5mediumGemini 3.5 Flash LitelowvsQwen3.6 27BnoneDots 3 Note PreviewhighGratis beschikbaarvsMercury 2.5mediumDots 3 Note PreviewlowGratis beschikbaarvsMercury 2.5mediumGemini 3.1 Flash Lite PreviewlowvsQwen3.6 27BnoneDots 3 Note PreviewlowGratis beschikbaarvsQwen3.6 27BnoneDots 3 Note PreviewhighGratis beschikbaarvsQwen3.6 27BnoneGemini 3.1 Flash LitelowvsQwen3.6 27BnoneQwen3.6 27BnonevsSolar Pro 4highMercury 2.5mediumvsLongCat 2.0noneQwen3.6 27BnonevsMiMo-V2.5-PromediumGemini 3.5 FlashminimalvsQwen3.6 27Bnone