Navigasi
AI BENCHY
Advertise here

Model yang Dibandingkan

Perbandingan benchmark Muse Spark 1.3 (high) vs Muse Spark 1.2 (high) vs Muse Spark 1.1 (high): Muse Spark 1.3 (high) unggul pada Skor dengan 8.9. Muse Spark 1.3 (high) unggul pada Keandalan dengan 10.0. Muse Spark 1.3 (high) memiliki Total Biaya terendah di $1.653. Muse Spark 1.2 (high) paling cepat di 26.59s.

Benchmark dihasilkan dari suite pengujian AI BENCHY pada: 2026-09-03

Peringkat
#26
Total token output
359,608
Waktu respons (rata-rata)
52.49s
Total Biaya
$1.653
Peringkat
#36
Total token output
382,087
Waktu respons (rata-rata)
26.59s
Total Biaya
$1.771
Peringkat
#60
Total token output
491,916
Waktu respons (rata-rata)
36.85s
Total Biaya
$2.253
Model yang direkomendasikan Muse Spark 1.2 (high)

Its score stays close to the best score here (8.7 vs 8.9), while responding about 1.7x faster than model lain dalam perbandingan ini.

Perbandingan terperinci

Metrik Muse Spark 1.3 Muse Spark 1.3 high Rilis: 2026-09-02 Muse Spark 1.2 Muse Spark 1.2 high Rilis: 2026-08-06 Muse Spark 1.1 Muse Spark 1.1 high Rilis: 2026-07-16
Skor 8.9 8.7 8.0
Peringkat #26 #36 #60
Keandalan 10.0 9.9 10.0
Konsistensi 9.3 8.3 7.9
Percobaan 66/66 66/66 66/66
Tes benar
Tingkat lulus per percobaan 77.3% 74.2% 68.2%
Tes tidak stabil 2 5 6
Total Run 66 66 66
Biaya per hasil 10.327 12.645 18.768
Total Biaya $1.653 $1.771 $2.253
Harga input $1.250 / 1M $1.250 / 1M $1.250 / 1M
Harga output $4.250 / 1M $4.250 / 1M $4.250 / 1M
Total token input 99,143 117,037 129,213
Token output 12,083 6,983 8,356
Token penalaran 347,525 375,104 483,560
Waktu respons (rata-rata) 52.49s 26.59s 36.85s
Waktu respons (maks) 251.53s 192.00s 196.03s
Waktu respons (total) 1154.76s 584.89s 810.72s
Parameter ~1T total (~50B aktif) ~1T total (~50B aktif) ~1T total (~50B aktif)
Ketersediaan Tertutup Tertutup Tertutup

Showcase generasi model

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#26 Muse Spark 1.3

high
Biaya
$0.050
Waktu
203.3s
Token
11,679 tok

#36 Muse Spark 1.2

high
Biaya
$0.057
Waktu
34.7s
Token
13,356 tok

#60 Muse Spark 1.1

high
Biaya
$0.039
Waktu
50.1s
Token
9,423 tok

Model teratas berdasarkan skor

Skor vs Total Biaya

Waktu respons (rata-rata)

Skor vs Waktu respons (rata-rata)

Total token output

Skor vs Total token output

Rincian Kategori

Pemrograman Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token input Token output Token penalaran
Muse Spark 1.3 10.0 10.0 100.0% 0 51.66s 7,275 1,228 64,287
Muse Spark 1.2 10.0 10.0 100.0% 0 22.24s 7,275 351 47,857
Muse Spark 1.1 10.0 10.0 100.0% 0 22.92s 8,562 349 36,039

Perbandingan Cepat

Ganti Pasangan Perbandingan

Muse Spark 1.3highvsGPT-5.3-CodexmediumDeepSeek V4 Flash 0731lowvsMuse Spark 1.1highClaude Fable 5mediumvsMuse Spark 1.2highMuse Spark 1.1highvsGPT-5 MinimediumClaude Opus 4.7mediumvsMuse Spark 1.2highMuse Spark 1.1highvsQwen3.8 2.4T A95BlowMuse Spark 1.2highvsGLM 5.3 FlashmaxGemini 3.6 FlashlowvsMuse Spark 1.2highClaude Opus 5lowvsMuse Spark 1.2highMuse Spark 1.3highvsQwen3.8 MaxmediumMuse Spark 1.3highvsGPT-5.5mediumGemini 3.5 FlashmediumvsMuse Spark 1.3high