Skip to content

Benchmark

tau2-bench v0.1 telecom pass^1

Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.

Models measured
9
Scores recorded
10
Sources
1
IQ weight
0.50

Score distribution

72%
Mean
84.2%
Median
23.8%
Std dev
48.9%
10th percentile
98%
90th percentile
34%
Min
34%98.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.50 for chat models, measured over 9 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Qwen3 Maxsubmission-qwen3-max_qwen_2026-01-23, usersim-gpt-4.1-2025-04-14· Sierra tau-bench Leaderboard data docs98.2%
2Claude Sonnet 4.5submission-claude-sonnet-4-5_anthropic_2025-10-02· Sierra tau-bench Leaderboard data docs98%
3DeepSeek V3.2submission-deepseek-v3.2_deepseek_2025-12-01, usersim-deepseek-v3.2· Sierra tau-bench Leaderboard data docs96.2%
4GPT 5submission-gpt-5_sierra_2025-08-09, usersim-gpt-4.1-2025-04-14· Sierra tau-bench Leaderboard data docs95.8%
5Qwen3 Maxsubmission-qwen3-max_qwen_2024_09_23· Sierra tau-bench Leaderboard data docs84.2%
6Kimi K2submission-kimi-k2_moonshot-ai_2025-07-11· Sierra tau-bench Leaderboard data docs65.8%
7o4 Minisubmission-o4-mini_openai_2024-06-20, usersim-gpt-4.1-2025-04-14· Sierra tau-bench Leaderboard data docs50.2%
8Claude Sonnet 3.7submission-claude-3-7-sonnet_anthropic_2024-06-20, usersim-gpt-4.1-2025-04-14· Sierra tau-bench Leaderboard data docs49%
9GPT-4.1 minisubmission-gpt-4-1-mini_openai_2024-06-20, usersim-gpt-4.1-2025-04-14· Sierra tau-bench Leaderboard data docs48.9%
10GPT 4.1submission-gpt-4-1_openai_2024-06-20, usersim-gpt-4.1-2025-04-14· Sierra tau-bench Leaderboard data docs34%

Data credits: Sierra Research tau2-bench leaderboard submissions (github.com/sierra-research/tau2-bench), MIT (licence)