Results

31 results

Toolathlon Original results
ProviderModelScoreSourceRegistry No.
Google (DeepMind)Gemini 3.5 Flash56.5%deepmind.google for Gemini 3.5 Flash on Toolathlon Original (opens in a new tab)Tasks completedReported Model cardGoogle DeepMindSelf-reportedRecord for Gemini 3.5 Flash on Toolathlon Original30006
DeepSeek AIDeepSeek-V4-Flash (Max)48.2%toolathlon.xyz for DeepSeek-V4-Flash (Max) on Toolathlon Original (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for DeepSeek-V4-Flash on Toolathlon Original110001
DeepSeek AIDeepSeek-V4-Pro (Max)52.8%toolathlon.xyz for DeepSeek-V4-Pro (Max) on Toolathlon Original (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for DeepSeek-V4-Pro on Toolathlon Original110002
AnthropicClaude Opus 4.752.8%toolathlon.xyz for Claude Opus 4.7 on Toolathlon Original (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for Claude Opus 4.7 on Toolathlon Original20010
DeepSeek AIDeepSeek-V4-Flash (max)47.8%huggingface.co for DeepSeek-V4-Flash (max) on Toolathlon Original (opens in a new tab)Tasks completedReported Model cardDeepSeekSelf-reportedDeepSeek AIRecord for DeepSeek-V4-Flash on Toolathlon Original110001
DeepSeek AIDeepSeek-V4-Flash (high)43.5%huggingface.co for DeepSeek-V4-Flash (high) on Toolathlon Original (opens in a new tab)Tasks completedReported Model cardDeepSeekSelf-reportedDeepSeek AIRecord for DeepSeek-V4-Flash on Toolathlon Original110001
DeepSeek AIDeepSeek-V4-Flash (non-thinking)40.7%huggingface.co for DeepSeek-V4-Flash (non-thinking) on Toolathlon Original (opens in a new tab)Tasks completedReported Model cardDeepSeekSelf-reportedDeepSeek AIRecord for DeepSeek-V4-Flash on Toolathlon Original110001
DeepSeek AIDeepSeek-V4-Pro (high)49.0%huggingface.co for DeepSeek-V4-Pro (high) on Toolathlon Original (opens in a new tab)Tasks completedReported Model cardDeepSeekSelf-reportedDeepSeek AIRecord for DeepSeek-V4-Pro on Toolathlon Original110002
DeepSeek AIDeepSeek-V4-Pro (non-thinking)46.3%huggingface.co for DeepSeek-V4-Pro (non-thinking) on Toolathlon Original (opens in a new tab)Tasks completedReported Model cardDeepSeekSelf-reportedDeepSeek AIRecord for DeepSeek-V4-Pro on Toolathlon Original110002
DeepSeek AIDeepSeek-V4-Pro (max)51.8%huggingface.co for DeepSeek-V4-Pro (max) on Toolathlon Original (opens in a new tab)Tasks completedReported Model cardDeepSeekSelf-reportedDeepSeek AIRecord for DeepSeek-V4-Pro on Toolathlon Original110002
Moonshot AIKimi K2.6 (thinking)50.0%huggingface.co for Kimi K2.6 (thinking) on Toolathlon Original (opens in a new tab)Tasks completedReported Model cardMoonshot AISelf-reportedRecord for Kimi K2.6 on Toolathlon Original120002
Google (DeepMind)Gemini 3.1 Pro48.8%toolathlon.xyz for Gemini 3.1 Pro on Toolathlon Original (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for Gemini 3.1 Pro on Toolathlon Original30005
AnthropicClaude Sonnet 4.644.8%toolathlon.xyz for Claude Sonnet 4.6 on Toolathlon Original (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for Claude Sonnet 4.6 on Toolathlon Original20009
Z.aiGLM-539.2%toolathlon.xyz for GLM-5 on Toolathlon Original (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for GLM-5 on Toolathlon Original150002
Moonshot AIKimi K2.527.8%toolathlon.xyz for Kimi K2.5 on Toolathlon Original (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for Kimi K2.5 on Toolathlon Original120001
Z.aiGLM-4.723.8%toolathlon.xyz for GLM-4.7 on Toolathlon Original (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for GLM-4.7 on Toolathlon Original150001
OpenAIGPT-5.2 (xhigh)43.8%toolathlon.xyz for GPT-5.2 (xhigh) on Toolathlon Original (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for GPT-5.2 on Toolathlon Original10012
Google (DeepMind)Gemini 3 Flash49.4%toolathlon.xyz for Gemini 3 Flash on Toolathlon Original (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for Gemini 3 Flash on Toolathlon Original30009
OpenAIGPT-5.2 (high)41.7%toolathlon.xyz for GPT-5.2 (high) on Toolathlon Original (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for GPT-5.2 on Toolathlon Original10012
OpenAIGPT-5 (high)37.7%toolathlon.xyz for GPT-5 (high) on Toolathlon Original (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for GPT-5 on Toolathlon Original10018
OpenAIGPT-5.2 (xhigh)46.3%openai.com for GPT-5.2 (xhigh) on Toolathlon Original (opens in a new tab)Tasks completedReported Launch postOpenAISelf-reportedRecord for GPT-5.2 on Toolathlon Original10012
AnthropicClaude Opus 4.543.5%toolathlon.xyz for Claude Opus 4.5 on Toolathlon Original (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for Claude Opus 4.5 on Toolathlon Original20007
Google (DeepMind)Gemini 3 Pro36.4%toolathlon.xyz for Gemini 3 Pro on Toolathlon Original (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for Gemini 3 Pro on Toolathlon Original30008
OpenAIOpenAI o317.0%toolathlon.xyz for OpenAI o3 on Toolathlon Original (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for OpenAI o3 on Toolathlon Original10003
OpenAIOpenAI o4-mini14.8%toolathlon.xyz for OpenAI o4-mini on Toolathlon Original (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for OpenAI o4-mini on Toolathlon Original10004
OpenAIGPT-5 mini14.5%toolathlon.xyz for GPT-5 mini on Toolathlon Original (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for GPT-5 mini on Toolathlon Original10019
Z.aiGLM-4.618.8%toolathlon.xyz for GLM-4.6 on Toolathlon Original (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for GLM-4.6 on Toolathlon Original150009
AnthropicClaude Sonnet 429.9%toolathlon.xyz for Claude Sonnet 4 on Toolathlon Original (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for Claude Sonnet 4 on Toolathlon Original20003
AnthropicClaude Sonnet 4.538.9%toolathlon.xyz for Claude Sonnet 4.5 on Toolathlon Original (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for Claude Sonnet 4.5 on Toolathlon Original20005
AnthropicClaude Haiku 4.526.2%toolathlon.xyz for Claude Haiku 4.5 on Toolathlon Original (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for Claude Haiku 4.5 on Toolathlon Original20006
SpaceXAIGrok 427.5%toolathlon.xyz for Grok 4 on Toolathlon Original (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for Grok 4 on Toolathlon Original40004