τ²-bench evaluates conversational agents completing customer-service tasks in airline, retail, and telecom environments. Agents use tools, follow policies, and coordinate with a simulated user who can also act. Scores here are overall pass@1 from the Standard leaderboard, using GPT-5.2 as the user simulator. Custom, legacy, voice, and banking evaluations are separate.
| Model / creator | Version | Reported score |
|---|---|---|
 Qwen3.5-397B-A17BQwen · Open source / open weights | Standard · Overall | 87.9% |
 Claude Opus 4.5Anthropic · Proprietary | Standard · Overall | 85.3% |
 GPT-5.2OpenAI · Proprietary | Standard · Overall | 84.8% |
 Gemini 3 FlashGoogle · Proprietary | Standard · Overall | 83.5% |
| Gemini 3 ProGoogle · Proprietary | Standard · Overall | 82.5% |
 GLM-5Z.ai · Open source / open weights | Standard · Overall | 81% |
| Claude Sonnet 4.5Anthropic · Proprietary | Standard · Overall | 76.4% |
benchmark: tau2 · domains: retail, airline, telecom · metric: pass^1 · reasoning: enabled · selection: Standard checked; Custom and Legacy unchecked; Overall tab. Do not merge with banking, voice, legacy or custom results. · submitting organization: Sierra · track: Standard · user simulator: gpt-5.2
Sierra ↗benchmark: tau2 · domains: retail, airline, telecom · metric: pass^1 · reasoning: high · selection: Standard checked; Custom and Legacy unchecked; Overall tab. Do not merge with banking, voice, legacy or custom results. · submitting organization: Sierra · track: Standard · user simulator: gpt-5.2
Sierra ↗benchmark: tau2 · domains: retail, airline, telecom · metric: pass^1 · reasoning: high · selection: Standard checked; Custom and Legacy unchecked; Overall tab. Do not merge with banking, voice, legacy or custom results. · submitting organization: Sierra · track: Standard · user simulator: gpt-5.2
Sierra ↗benchmark: tau2 · domains: retail, airline, telecom · metric: pass^1 · reasoning: high · selection: Standard checked; Custom and Legacy unchecked; Overall tab. Do not merge with banking, voice, legacy or custom results. · submitting organization: Sierra · track: Standard · user simulator: gpt-5.2
Sierra ↗benchmark: tau2 · domains: retail, airline, telecom · metric: pass^1 · reasoning: high · selection: Standard checked; Custom and Legacy unchecked; Overall tab. Do not merge with banking, voice, legacy or custom results. · submitting organization: Sierra · track: Standard · user simulator: gpt-5.2
Sierra ↗benchmark: tau2 · domains: retail, airline, telecom · metric: pass^1 · reasoning: enabled · selection: Standard checked; Custom and Legacy unchecked; Overall tab. Do not merge with banking, voice, legacy or custom results. · submitting organization: Sierra · track: Standard · user simulator: gpt-5.2
Sierra ↗benchmark: tau2 · domains: retail, airline, telecom · metric: pass^1 · reasoning: enabled · selection: Standard checked; Custom and Legacy unchecked; Overall tab. Do not merge with banking, voice, legacy or custom results. · submitting organization: Sierra · track: Standard · user simulator: gpt-5.2
Sierra ↗benchmark: tau2 · domains: retail, airline, telecom · metric: pass^1 · reasoning: none · selection: Standard checked; Custom and Legacy unchecked; Overall tab. Do not merge with banking, voice, legacy or custom results. · submitting organization: Sierra · track: Standard · user simulator: gpt-5.2
Sierra ↗GPQA Diamond tests graduate-level scientific knowledge and reasoning with difficult multiple-choice questions in biology, chemistry, and physics.
LiveBench: CodingLiveBench 2.0 coding suite on the October 14, 2026 release.
GDPval-AAGDPval-AA evaluates models on professional knowledge-work tasks from OpenAI’s GDPval dataset, including creating documents, spreadsheets, slides, and other work products.
