Task success (pass^1): GPT-5.2
1 results · % of tasks, higher is better. Choose a model to highlight it.Clear highlight
- 1 GPT-5.2 (no reasoning)OpenAI 12.6%
Benchmarks / tau2-bench
Share of banking questions answered from a policy knowledge base tasks completed within policy, averaged over trials.
Data older than 90 days: last updated 3 Aug 2026
What it measures. tau2-bench is a third-party benchmark, shown here with credit. Measured here: Share of banking questions answered from a policy knowledge base tasks completed within policy, averaged over trials.
Latest results. , 1 model ranked.
Top 1 on Task success (pass^1) (% of tasks, higher is better):
How to cite. tau2-bench, via Spring Prompt, results dated 26 May 2026. https://springprompt.com/benchmarks/tau2-bench These results belong to tau2-bench, not to us. Licence: MIT License. Credit tau2-bench first.
1 results · % of tasks, higher is better. Choose a model to highlight it.Clear highlight
| # | Model | Task success (pass^1) % of tasks, higher is better | Price $ per million tokens, in / out |
|---|---|---|---|
| 1 | GPT-5.2 (no reasoning)OpenAI |
12.6%
|
$1.75 / $14 |
Swipe the table sideways for more columns.
Source: tau2-bench, via Spring Prompt, springprompt.com/benchmarks/tau2-bench. Test your own prompt on these models →
Ranks follow the score as shown, so equal numbers share a rank. Results as published by tau2-bench; we do not re-run them.
Share of banking questions answered from a policy knowledge base tasks completed within policy, averaged over trials.
Not your policies or customers: the tasks and policies are tau2's own, and the customer is simulated by gpt-5.2.
We rank a result only when we can tie it to a specific model you can use. These are left out:
tau2-bench by Sierra Research and contributors, MIT License.