Kimi K2.5 · Kimi K2.6

Shared benchmarks

10
Shared benchmarks for Kimi K2.5 and Kimi K2.6
BenchmarkKimi K2.5Kimi K2.6
60.6%
83.2%
Evaluation details for BrowseComp

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Kimi K2.5

Kimi K2.6

77.5%
80.4%
Evaluation details for CharXiv Reasoning — No tools

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Kimi K2.5

Kimi K2.6

87.6%
90.5%
Evaluation details for GPQA Diamond

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Kimi K2.5

Kimi K2.6

30.1%
34.7%
Evaluation details for Humanity's Last Exam Full set — No tools

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Kimi K2.5

Kimi K2.6

50.2%
54.0%
Evaluation details for Humanity's Last Exam Full set — With tools

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Kimi K2.5

Kimi K2.6

78.5%
79.4%
Evaluation details for MMMU-Pro No tools

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Kimi K2.5

Kimi K2.6

73.0%
76.7%
Evaluation details for SWE-bench Multilingual

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Kimi K2.5

Kimi K2.6

76.8%
80.2%
Evaluation details for SWE-bench Verified

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Kimi K2.5

Kimi K2.6

50.7%
58.6%
Evaluation details for SWE-bench Pro Public

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Kimi K2.5

Kimi K2.6

50.8%
66.7%
Evaluation details for Terminal-Bench 2.0

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Kimi K2.5

Kimi K2.6