Results

8 results

CharXiv Reasoning — Python enabled results
ProviderModelScoreSourceRegistry No.
Moonshot AIKimi K3 (max)91.3%raw.githubusercontent.com for Kimi K3 (max) on CharXiv Reasoning — Python enabled (opens in a new tab)CharXiv AccuracyReported Technical reportMoonshot AISelf-reportedRecord for Kimi K3 on CharXiv Reasoning — Python enabled120003
Thinking Machines LabInkling-Small (effort=0.99)81.3%thinkingmachines.ai for Inkling-Small (effort=0.99) on CharXiv Reasoning — Python enabled (opens in a new tab)CharXiv AccuracyReported Model cardThinking Machines LabSelf-reportedRecord for Inkling-Small on CharXiv Reasoning — Python enabled160002
Thinking Machines LabInkling (effort=0.99)82.0%thinkingmachines.ai for Inkling (effort=0.99) on CharXiv Reasoning — Python enabled (opens in a new tab)CharXiv AccuracyReported Model cardThinking Machines LabSelf-reportedRecord for Inkling on CharXiv Reasoning — Python enabled160001
AnthropicClaude Sonnet 5 (max)88.3%www-cdn.anthropic.com for Claude Sonnet 5 (max) on CharXiv Reasoning — Python enabled (opens in a new tab)CharXiv AccuracyReported System cardAnthropicSelf-reportedRecord for Claude Sonnet 5 on CharXiv Reasoning — Python enabled20013
Moonshot AIKimi K2.6 (thinking)86.7%huggingface.co for Kimi K2.6 (thinking) on CharXiv Reasoning — Python enabled (opens in a new tab)CharXiv AccuracyReported Model cardMoonshot AISelf-reportedRecord for Kimi K2.6 on CharXiv Reasoning — Python enabled120002
AnthropicClaude Opus 4.7 (adaptive thinking, max)91.0%www-cdn.anthropic.com for Claude Opus 4.7 (adaptive thinking, max) on CharXiv Reasoning — Python enabled (opens in a new tab)CharXiv AccuracyReported System cardAnthropicSelf-reportedRecord for Claude Opus 4.7 on CharXiv Reasoning — Python enabled20010
Meta AI (originally Facebook AI Research)Muse Spark (thinking)88.9%ai.meta.com for Muse Spark (thinking) on CharXiv Reasoning — Python enabled (opens in a new tab)CharXiv AccuracyReported Evaluation methodologyMetaSelf-reportedRecord for Muse Spark on CharXiv Reasoning — Python enabled80001
OpenAIGPT-5.2 (xhigh)88.7%openai.com for GPT-5.2 (xhigh) on CharXiv Reasoning — Python enabled (opens in a new tab)CharXiv AccuracyReported Launch postOpenAISelf-reportedRecord for GPT-5.2 on CharXiv Reasoning — Python enabled10012