Compare AI Models for Roleplay

Pick any two models to see their Roleplay Index, every category, skill ratings and behaviour checks side by side.

Updated

Every matchup

Ordered by the combined rank of both models.

Kimi-K3 vs GLM-5.3

86.3
85.1

Kimi-K3 vs DeepSeek-V4.1-Flash

86.3
84.4

Kimi-K3 vs GLM-5.3-Flash

86.3
83.3

GLM-5.3 vs DeepSeek-V4.1-Flash

85.1
84.4

Kimi-K3 vs MiMo-V2.6-Pro

86.3
77.4

GLM-5.3 vs GLM-5.3-Flash

85.1
83.3

Kimi-K3 vs Muse-Spark-1.3

86.3
73.1

GLM-5.3 vs MiMo-V2.6-Pro

85.1
77.4

DeepSeek-V4.1-Flash vs GLM-5.3-Flash

84.4
83.3

Kimi-K3 vs GPT-6-Luna

86.3
71.1

GLM-5.3 vs Muse-Spark-1.3

85.1
73.1

DeepSeek-V4.1-Flash vs MiMo-V2.6-Pro

84.4
77.4

Kimi-K3 vs Qwen3.8-Flash-Next

86.3
69.7

GLM-5.3 vs GPT-6-Luna

85.1
71.1

DeepSeek-V4.1-Flash vs Muse-Spark-1.3

84.4
73.1

GLM-5.3-Flash vs MiMo-V2.6-Pro

83.3
77.4

Kimi-K3 vs MiMo-V2.5

86.3
67.1

GLM-5.3 vs Qwen3.8-Flash-Next

85.1
69.7

DeepSeek-V4.1-Flash vs GPT-6-Luna

84.4
71.1

GLM-5.3-Flash vs Muse-Spark-1.3

83.3
73.1

Kimi-K3 vs MiMo-V2.6-Flash-MOPD

86.3
66.8

GLM-5.3 vs MiMo-V2.5

85.1
67.1

DeepSeek-V4.1-Flash vs Qwen3.8-Flash-Next

84.4
69.7

GLM-5.3-Flash vs GPT-6-Luna

83.3
71.1

MiMo-V2.6-Pro vs Muse-Spark-1.3

77.4
73.1

Kimi-K3 vs GLM-4.7

86.3
62.9

GLM-5.3 vs MiMo-V2.6-Flash-MOPD

85.1
66.8

DeepSeek-V4.1-Flash vs MiMo-V2.5

84.4
67.1

GLM-5.3-Flash vs Qwen3.8-Flash-Next

83.3
69.7

MiMo-V2.6-Pro vs GPT-6-Luna

77.4
71.1

Kimi-K3 vs Qwen3.8-27B

86.3
61.8

GLM-5.3 vs GLM-4.7

85.1
62.9

DeepSeek-V4.1-Flash vs MiMo-V2.6-Flash-MOPD

84.4
66.8

GLM-5.3-Flash vs MiMo-V2.5

83.3
67.1

MiMo-V2.6-Pro vs Qwen3.8-Flash-Next

77.4
69.7

Muse-Spark-1.3 vs GPT-6-Luna

73.1
71.1

Kimi-K3 vs Gemma-4-31B-it

86.3
60.6

GLM-5.3 vs Qwen3.8-27B

85.1
61.8

DeepSeek-V4.1-Flash vs GLM-4.7

84.4
62.9

GLM-5.3-Flash vs MiMo-V2.6-Flash-MOPD

83.3
66.8

MiMo-V2.6-Pro vs MiMo-V2.5

77.4
67.1

Muse-Spark-1.3 vs Qwen3.8-Flash-Next

73.1
69.7

Kimi-K3 vs DeepSeek-V4-Flash-0731

86.3
59.0

GLM-5.3 vs Gemma-4-31B-it

85.1
60.6

DeepSeek-V4.1-Flash vs Qwen3.8-27B

84.4
61.8

GLM-5.3-Flash vs GLM-4.7

83.3
62.9

MiMo-V2.6-Pro vs MiMo-V2.6-Flash-MOPD

77.4
66.8

Muse-Spark-1.3 vs MiMo-V2.5

73.1
67.1

GPT-6-Luna vs Qwen3.8-Flash-Next

71.1
69.7

GLM-5.3 vs DeepSeek-V4-Flash-0731

85.1
59.0

DeepSeek-V4.1-Flash vs Gemma-4-31B-it

84.4
60.6

GLM-5.3-Flash vs Qwen3.8-27B

83.3
61.8

MiMo-V2.6-Pro vs GLM-4.7

77.4
62.9

Muse-Spark-1.3 vs MiMo-V2.6-Flash-MOPD

73.1
66.8

GPT-6-Luna vs MiMo-V2.5

71.1
67.1

DeepSeek-V4.1-Flash vs DeepSeek-V4-Flash-0731

84.4
59.0

GLM-5.3-Flash vs Gemma-4-31B-it

83.3
60.6

MiMo-V2.6-Pro vs Qwen3.8-27B

77.4
61.8

Muse-Spark-1.3 vs GLM-4.7

73.1
62.9

GPT-6-Luna vs MiMo-V2.6-Flash-MOPD

71.1
66.8

Qwen3.8-Flash-Next vs MiMo-V2.5

69.7
67.1

GLM-5.3-Flash vs DeepSeek-V4-Flash-0731

83.3
59.0

MiMo-V2.6-Pro vs Gemma-4-31B-it

77.4
60.6

Muse-Spark-1.3 vs Qwen3.8-27B

73.1
61.8

GPT-6-Luna vs GLM-4.7

71.1
62.9

Qwen3.8-Flash-Next vs MiMo-V2.6-Flash-MOPD

69.7
66.8

MiMo-V2.6-Pro vs DeepSeek-V4-Flash-0731

77.4
59.0

Muse-Spark-1.3 vs Gemma-4-31B-it

73.1
60.6

GPT-6-Luna vs Qwen3.8-27B

71.1
61.8

Qwen3.8-Flash-Next vs GLM-4.7

69.7
62.9

MiMo-V2.5 vs MiMo-V2.6-Flash-MOPD

67.1
66.8

Muse-Spark-1.3 vs DeepSeek-V4-Flash-0731

73.1
59.0

GPT-6-Luna vs Gemma-4-31B-it

71.1
60.6

Qwen3.8-Flash-Next vs Qwen3.8-27B

69.7
61.8

MiMo-V2.5 vs GLM-4.7

67.1
62.9

GPT-6-Luna vs DeepSeek-V4-Flash-0731

71.1
59.0

Qwen3.8-Flash-Next vs Gemma-4-31B-it

69.7
60.6

MiMo-V2.5 vs Qwen3.8-27B

67.1
61.8

MiMo-V2.6-Flash-MOPD vs GLM-4.7

66.8
62.9

Qwen3.8-Flash-Next vs DeepSeek-V4-Flash-0731

69.7
59.0

MiMo-V2.5 vs Gemma-4-31B-it

67.1
60.6

MiMo-V2.6-Flash-MOPD vs Qwen3.8-27B

66.8
61.8

MiMo-V2.5 vs DeepSeek-V4-Flash-0731

67.1
59.0

MiMo-V2.6-Flash-MOPD vs Gemma-4-31B-it

66.8
60.6

GLM-4.7 vs Qwen3.8-27B

62.9
61.8

MiMo-V2.6-Flash-MOPD vs DeepSeek-V4-Flash-0731

66.8
59.0

GLM-4.7 vs Gemma-4-31B-it

62.9
60.6

GLM-4.7 vs DeepSeek-V4-Flash-0731

62.9
59.0

Qwen3.8-27B vs Gemma-4-31B-it

61.8
60.6

Qwen3.8-27B vs DeepSeek-V4-Flash-0731

61.8
59.0

Gemma-4-31B-it vs DeepSeek-V4-Flash-0731

60.6
59.0