Benchmark
Open Agent Leaderboard Tau Bench 2 retail
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.
- Models measured
- 5
- Scores recorded
- 25
- Sources
- 1
- IQ weight
- 0.19
Score distribution
- 65.9%
- Mean
- 73%
- Median
- 22.9%
- Std dev
- 19%
- 10th percentile
- 82%
- 90th percentile
- 1%
- Min
This benchmark has a weight of 0.19 for chat models, measured over 5 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.5agent: openai_solo, task: tau2_retail, subset: retail, route: openai/aws· Open Agent Leaderboard results data docs | 85% |
| 2 | Claude Opus 4.5agent: claude_code, task: tau2_retail, subset: retail, route: openai/aws· Open Agent Leaderboard results data docs | 83% |
| 3 | DeepSeek V3.2agent: tool_calling_with_shortlisting, task: tau2_retail, subset: retail, route: openai/azure· Open Agent Leaderboard results data docs | 82% |
| 4 | DeepSeek V3.2agent: tool_calling, task: tau2_retail, subset: retail, route: openai/azure· Open Agent Leaderboard results data docs | 82% |
| 5 | Gemini 3 Pro Previewagent: tool_calling_with_shortlisting, task: tau2_retail, subset: retail, route: openai/gcp· Open Agent Leaderboard results data docs | 82% |
| 6 | Gemini 3 Pro Previewagent: tool_calling, task: tau2_retail, subset: retail, route: openai/gcp· Open Agent Leaderboard results data docs | 82% |
| 7 | Claude Opus 4.5agent: smolagents_code, task: tau2_retail, subset: retail, route: openai/aws· Open Agent Leaderboard results data docs | 78% |
| 8 | Claude Opus 4.5agent: tool_calling_with_shortlisting, task: tau2_retail, subset: retail, route: openai/aws· Open Agent Leaderboard results data docs | 78% |
| 9 | Claude Opus 4.5agent: tool_calling, task: tau2_retail, subset: retail, route: openai/aws· Open Agent Leaderboard results data docs | 78% |
| 10 | DeepSeek V3.2agent: smolagents_code, task: tau2_retail, subset: retail, route: openai/azure· Open Agent Leaderboard results data docs | 77% |
| 11 | Gemini 3 Pro Previewagent: smolagents_code, task: tau2_retail, subset: retail, route: openai/gcp· Open Agent Leaderboard results data docs | 75% |
| 12 | Gemini 3 Pro Previewagent: openai_solo, task: tau2_retail, subset: retail, route: openai/gcp· Open Agent Leaderboard results data docs | 73% |
| 13 | GPT 5.2agent: tool_calling_with_shortlisting, task: tau2_retail, subset: retail, route: openai/azure· Open Agent Leaderboard results data docs | 73% |
| 14 | GPT 5.2agent: tool_calling, task: tau2_retail, subset: retail, route: openai/azure· Open Agent Leaderboard results data docs | 73% |
| 15 | Kimi K2.5agent: smolagents_code, task: tau2_retail, subset: retail, route: openai/azure· Open Agent Leaderboard results data docs | 72.4% |
| 16 | Gemini 3 Pro Previewagent: claude_code, task: tau2_retail, subset: retail, route: openai/gcp· Open Agent Leaderboard results data docs | 71% |
| 17 | GPT 5.2agent: smolagents_code, task: tau2_retail, subset: retail, route: openai/azure· Open Agent Leaderboard results data docs | 68% |
| 18 | DeepSeek V3.2agent: claude_code, task: tau2_retail, subset: retail, route: openai/azure· Open Agent Leaderboard results data docs | 65% |
| 19 | Kimi K2.5agent: tool_calling_with_shortlisting, task: tau2_retail, subset: retail, route: openai/azure· Open Agent Leaderboard results data docs | 64.6% |
| 20 | Kimi K2.5agent: tool_calling, task: tau2_retail, subset: retail, route: openai/azure· Open Agent Leaderboard results data docs | 64.6% |
| 21 | GPT 5.2agent: claude_code, task: tau2_retail, subset: retail, route: openai/azure· Open Agent Leaderboard results data docs | 64% |
| 22 | GPT 5.2agent: openai_solo, task: tau2_retail, subset: retail, route: openai/azure· Open Agent Leaderboard results data docs | 53% |
| 23 | DeepSeek V3.2agent: openai_solo, task: tau2_retail, subset: retail, route: openai/azure· Open Agent Leaderboard results data docs | 19% |
| 24 | Kimi K2.5agent: claude_code, task: tau2_retail, subset: retail, route: openai/azure· Open Agent Leaderboard results data docs | 3% |
| 25 | Kimi K2.5agent: openai_solo, task: tau2_retail, subset: retail, route: openai/azure· Open Agent Leaderboard results data docs | 1% |
Data credits: Open Agent Leaderboard results (Exgentic), CDLA-Permissive-2.0; agreement text at https://cdla.dev/permissive-2-0/. Fractions shown as percentages. (licence)