BenchLM Benchmarks

165 benchmarks · 22 model scores · Data from Jun 2, 2026

Multilingual6 benchmarks

2 models

1DeepSeek V4 Flash BaseDeepSeek85.7%

2DeepSeek V4 Pro BaseDeepSeek84.4%

10 models

1Qwen3.7 MaxAlibaba87%

2Claude Opus 4.5Anthropic85.7%

3Qwen3.6 PlusAlibaba84.7%

4Qwen3.5 397BAlibaba84.7%

5GLM-5Z.AI83.1%

6 models

1Qwen3.5 397BAlibaba59.1%

2Qwen3.7 MaxAlibaba59.0%

3Qwen3.6 PlusAlibaba57.9%

4Claude Opus 4.5Anthropic56.7%

5Kimi K2.5Moonshot AI56.0%

2 models

1Claude Opus 4.8Anthropic87.6%

2Qwen3.7 MaxAlibaba86.2%

1 models

1Qwen3.7 MaxAlibaba86.5%

1 models

1Qwen3.7 MaxAlibaba89.2%