Results

13 results

Terminal-Bench 2.1 results
ProviderModelScoreSourceRegistry No.
Google (DeepMind)Gemini 3.8 Flash89.4%deepmind.google for Gemini 3.8 Flash on Terminal-Bench 2.1 (opens in a new tab)Terminal-Bench AccuracyReported Model cardGoogle DeepMindSelf-reportedRecord for Gemini 3.8 Flash on Terminal-Bench 2.130004
Meta AI (originally Facebook AI Research)Muse Spark 1.3 (max)88.8%dev.meta.ai for Muse Spark 1.3 (max) on Terminal-Bench 2.1 (opens in a new tab)Terminal-Bench AccuracyReported Model pageMetaSelf-reportedRecord for Muse Spark 1.3 on Terminal-Bench 2.180005
Google (DeepMind)Gemini 3.7 Flash85.8%deepmind.google for Gemini 3.7 Flash on Terminal-Bench 2.1 (opens in a new tab)Terminal-Bench AccuracyReported Model cardGoogle DeepMindSelf-reportedRecord for Gemini 3.7 Flash on Terminal-Bench 2.130010
Alibaba (Tongyi)Qwen3.8-Max86.6%huggingface.co for Qwen3.8-Max on Terminal-Bench 2.1 (opens in a new tab)Terminal-Bench AccuracyReported Model cardQwenSelf-reportedQwen TeamRecord for Qwen3.8-Max on Terminal-Bench 2.1130008
Google (DeepMind)Gemini 3.6 Flash78.0%deepmind.google for Gemini 3.6 Flash on Terminal-Bench 2.1 (opens in a new tab)Terminal-Bench AccuracyReported Model cardGoogle DeepMindSelf-reportedRecord for Gemini 3.6 Flash on Terminal-Bench 2.130007
Moonshot AIKimi K3 (max)88.3%huggingface.co for Kimi K3 (max) on Terminal-Bench 2.1 (opens in a new tab)Terminal-Bench AccuracyReported Model cardMoonshot AISelf-reportedRecord for Kimi K3 on Terminal-Bench 2.1120003
SpaceXAIGrok 4.583.3%x.ai for Grok 4.5 on Terminal-Bench 2.1 (opens in a new tab)Terminal-Bench AccuracyReported Launch postSpaceXAISelf-reportedRecord for Grok 4.5 on Terminal-Bench 2.140001
OpenAIGPT-5.6 Luna84.7%openai.com for GPT-5.6 Luna on Terminal-Bench 2.1 (opens in a new tab)Terminal-Bench AccuracyReported Launch postOpenAISelf-reportedRecord for GPT-5.6 Luna on Terminal-Bench 2.110009
OpenAIGPT-5.6 Sol88.8%openai.com for GPT-5.6 Sol on Terminal-Bench 2.1 (opens in a new tab)Terminal-Bench AccuracyReported Launch postOpenAISelf-reportedRecord for GPT-5.6 Sol on Terminal-Bench 2.110010
OpenAIGPT-5.6 Terra87.4%openai.com for GPT-5.6 Terra on Terminal-Bench 2.1 (opens in a new tab)Terminal-Bench AccuracyReported Launch postOpenAISelf-reportedRecord for GPT-5.6 Terra on Terminal-Bench 2.110011
NVIDIANVIDIA Nemotron 3 Ultra 550B-A55B56.4%huggingface.co for NVIDIA Nemotron 3 Ultra 550B-A55B on Terminal-Bench 2.1 (opens in a new tab)Terminal-Bench AccuracyReported Model cardNVIDIASelf-reportedRecord for NVIDIA Nemotron 3 Ultra 550B-A55B on Terminal-Bench 2.160003
AnthropicClaude Opus 4.8 (adaptive thinking, max)74.6%www-cdn.anthropic.com for Claude Opus 4.8 (adaptive thinking, max) on Terminal-Bench 2.1 (opens in a new tab)Terminal-Bench AccuracyReported System cardAnthropicSelf-reportedRecord for Claude Opus 4.8 on Terminal-Bench 2.120011
Google (DeepMind)Gemini 3.5 Flash76.2%deepmind.google for Gemini 3.5 Flash on Terminal-Bench 2.1 (opens in a new tab)Terminal-Bench AccuracyReported Model cardGoogle DeepMindSelf-reportedRecord for Gemini 3.5 Flash on Terminal-Bench 2.130006