OpenGPTAI decision intelligenceAverage Pass¹84.76%Cost per successful taskNot publishedPublished result rangeNot published
Agent details →Shared benchmark scope · τ²-bench Core
Same-benchmark agent comparison
The entries below share the same benchmark scope. Their exact scaffolds, model versions, dates, and original source values remain visible.
A higher source value only means better performance on this benchmark and configuration. It is not a cross-benchmark or production-readiness score.
Compare like with like
Decision overview
Only configurations from the same benchmark version and task scope can be placed in one comparison.
Average Pass¹87.91%Cost per successful taskNot publishedPublished result rangeNot published
Agent details →17 identical or entirely unreported fields hidden
| Agent system | τ² standard agent · GPT-5.2 · high | τ² standard agent · Qwen3.5-397B-A17B · thinking |
|---|---|---|
| Configuration | ||
| Base model | GPT-5.2 | Qwen3.5-397B-A17B |
| Source model ID or label | GPT-5.2 · high | Qwen3.5-397B-A17B · thinking |
| Outcome | ||
| Average Pass¹ | 84.76% | 87.91% |
| Trust | ||
| Evaluation date | May 5, 2026 | Feb 27, 2026 |
| Source | ||
| Open source | Open source ↗ | Open source ↗ |
Configuration
τ² standard agent · GPT-5.2 · high
- Base model
- GPT-5.2
- Source model ID or label
- GPT-5.2 · high
τ² standard agent · Qwen3.5-397B-A17B · thinking
- Base model
- Qwen3.5-397B-A17B
- Source model ID or label
- Qwen3.5-397B-A17B · thinking
Outcome
τ² standard agent · GPT-5.2 · high
- Average Pass¹
- 84.76%
τ² standard agent · Qwen3.5-397B-A17B · thinking
- Average Pass¹
- 87.91%
Trust
τ² standard agent · GPT-5.2 · high
- Evaluation date
- May 5, 2026
τ² standard agent · Qwen3.5-397B-A17B · thinking
- Evaluation date
- Feb 27, 2026
Source
τ² standard agent · GPT-5.2 · high
τ² standard agent · Qwen3.5-397B-A17B · thinking
Source-reported data; missing values remain unknown.
Validate before adoption
Public rankings create a shortlist. A small private trial decides whether the configuration fits your work.
- 1
Choose 10–20 representative tasks and define a clear pass condition.
- 2
Lock the agent, model, tools, permissions, and budget before testing.
- 3
Run each important task more than once; record success, cost, time, and takeovers.
- 4
Review failures and data-handling risks before a production decision.