Explore models.

2,849 models1,624 with prices34 metricsUpdated Oct 22, 2026 ↗

Measured modelsLiveBench Research

Clear benchmark ×

Choose a category in More filters to see relevant price sorts.

49 models · LiveBench Research · newest firstPage 2 / 3

More filters

AnthropicDiscovered 5 days ago

Claude Haiku 4.5

Reasoning

LiveBench ResearchEffort: max · single run42.2%

Price not listed

AnthropicDiscovered 5 days ago

Claude Haiku 5.5

Reasoning

LiveBench ResearchEffort: max · single run73.7%

Price not listed

AnthropicDiscovered 5 days ago

Claude Opus 4.8

Reasoning

LiveBench ResearchEffort: max · single run81.8%

Price not listed

AnthropicDiscovered 5 days ago

Claude Opus 5

Reasoning

LiveBench ResearchEffort: max · single run88.9%

Price not listed

AnthropicDiscovered 5 days ago

Claude Sonnet 4.6

Reasoning

LiveBench ResearchEffort: max · single run63.6%

Price not listed

AnthropicDiscovered 5 days ago

Claude Sonnet 5

Reasoning

LiveBench ResearchEffort: max · single run82.8%

Price not listed

GoogleDiscovered 5 days ago

Gemini 3.1 Pro

Reasoning

LiveBench ResearchEffort: high · single run65.7%

Price not listed

GoogleDiscovered 5 days ago

Gemini 3.7 Flash

Reasoning

LiveBench ResearchEffort: high · single run76.5%

Price not listed

GoogleDiscovered 5 days ago

Gemini 3.8 Flash

Reasoning

LiveBench ResearchEffort: high · single run79.1%

Price not listed

OpenAIDiscovered 5 days ago

GPT-5.5

Reasoning

LiveBench ResearchEffort: xhigh · single run61.6%

Price not listed

OpenAIDiscovered 5 days ago

GPT-5.6 Luna

Reasoning

LiveBench ResearchEffort: max · single run51%

Price not listed

OpenAIDiscovered 5 days ago

GPT-5.6 Sol

Reasoning

LiveBench ResearchEffort: max · single run54.5%

Price not listed

OpenAIDiscovered 5 days ago

GPT-5.6 Terra

Reasoning

LiveBench ResearchEffort: max · single run60.4%

Price not listed

OpenAIDiscovered 5 days ago

GPT-6 Sol

Reasoning

LiveBench ResearchEffort: max · single run69.3%

Price not listed

xAIDiscovered 5 days ago

Grok 4.5

Reasoning

LiveBench ResearchEffort: xhigh · single run85.9%

Price not listed

xAIDiscovered 5 days ago

Grok 4.6

Reasoning

LiveBench ResearchEffort: xhigh · single run84.5%

Price not listed

xAIDiscovered 5 days ago

Grok 4.7

Reasoning

LiveBench ResearchEffort: xhigh · single run86.4%

Price not listed

Thinking MachinesDiscovered 5 days ago

Inkling

Reasoning

LiveBench ResearchEffort: max · single run59.9%

Price not listed

MiniMaxDiscovered 5 days ago

MiniMax M3

ReasoningOpen weights

LiveBench ResearchEffort: max · single run68%

Price not listed

Mistral AIDiscovered 5 days ago

Mistral Large 4

Reasoning

LiveBench ResearchEffort: high · single run28.1%

Price not listed

MetaDiscovered 5 days ago

Muse Spark 1.2

Reasoning

LiveBench ResearchEffort: xhigh · single run67.7%

Price not listed

MetaDiscovered 5 days ago

Muse Spark 1.3

Reasoning

LiveBench ResearchEffort: max · single run68.6%

Price not listed

MetaDiscovered 5 days ago

Muse Wonder 1.0

Reasoning

LiveBench ResearchEffort: max · single run88%

Price not listed

NVIDIADiscovered 5 days ago

Nemotron 3 Ultra

ReasoningOpen weights

LiveBench ResearchEffort: max · single run43.2%

Price not listed