Results

9 results

τ³-bench τ³ — Telecom results
ProviderModelScoreSourceRegistry No.
OpenAIGPT-5.2 (none)57.2%sierra-tau-bench-public.s3.us-west-2.amazonaws.com for GPT-5.2 (none) on τ³-bench τ³ — Telecom (opens in a new tab)Archived copy (opens in a new tab)Task success rateReported Evaluated Benchmark leaderboardSierraIndependentSierra ResearchRecord for GPT-5.2 on τ³-bench τ³ — Telecom10012
Mistral AIMistral Medium 3.5 (high)91.4%huggingface.co for Mistral Medium 3.5 (high) on τ³-bench τ³ — Telecom (opens in a new tab)Task success rateReported Model cardMistral AISelf-reportedRecord for Mistral Medium 3.5 on τ³-bench τ³ — Telecom90005
OpenAIGPT-5.2 (high)89.7%sierra-tau-bench-public.s3.us-west-2.amazonaws.com for GPT-5.2 (high) on τ³-bench τ³ — Telecom (opens in a new tab)Archived copy (opens in a new tab)Task success rateReported Evaluated Benchmark leaderboardSierraIndependentSierra ResearchRecord for GPT-5.2 on τ³-bench τ³ — Telecom10012
AnthropicClaude Opus 4.5 (high)92.3%sierra-tau-bench-public.s3.us-west-2.amazonaws.com for Claude Opus 4.5 (high) on τ³-bench τ³ — Telecom (opens in a new tab)Archived copy (opens in a new tab)Task success rateReported Evaluated Benchmark leaderboardSierraIndependentSierra ResearchRecord for Claude Opus 4.5 on τ³-bench τ³ — Telecom20007
Alibaba (Tongyi)Qwen3.5-397B-A17B (enabled)97.8%sierra-tau-bench-public.s3.us-west-2.amazonaws.com for Qwen3.5-397B-A17B (enabled) on τ³-bench τ³ — Telecom (opens in a new tab)Archived copy (opens in a new tab)Task success rateReported Evaluated Benchmark leaderboardSierraIndependentSierra ResearchRecord for Qwen3.5-397B-A17B on τ³-bench τ³ — Telecom130003
Z.aiGLM-5 (enabled)86.8%sierra-tau-bench-public.s3.us-west-2.amazonaws.com for GLM-5 (enabled) on τ³-bench τ³ — Telecom (opens in a new tab)Archived copy (opens in a new tab)Task success rateReported Evaluated Benchmark leaderboardSierraIndependentSierra ResearchRecord for GLM-5 on τ³-bench τ³ — Telecom150002
Google (DeepMind)Gemini 3 Pro (high)91.0%sierra-tau-bench-public.s3.us-west-2.amazonaws.com for Gemini 3 Pro (high) on τ³-bench τ³ — Telecom (opens in a new tab)Archived copy (opens in a new tab)Task success rateReported Evaluated Benchmark leaderboardSierraIndependentSierra ResearchRecord for Gemini 3 Pro on τ³-bench τ³ — Telecom30008
Google (DeepMind)Gemini 3 Flash (high)91.2%sierra-tau-bench-public.s3.us-west-2.amazonaws.com for Gemini 3 Flash (high) on τ³-bench τ³ — Telecom (opens in a new tab)Archived copy (opens in a new tab)Task success rateReported Evaluated Benchmark leaderboardSierraIndependentSierra ResearchRecord for Gemini 3 Flash on τ³-bench τ³ — Telecom30009
AnthropicClaude Sonnet 4.5 (enabled)84.9%sierra-tau-bench-public.s3.us-west-2.amazonaws.com for Claude Sonnet 4.5 (enabled) on τ³-bench τ³ — Telecom (opens in a new tab)Archived copy (opens in a new tab)Task success rateReported Evaluated Benchmark leaderboardSierraIndependentSierra ResearchRecord for Claude Sonnet 4.5 on τ³-bench τ³ — Telecom20005