A next-generation tool-use benchmark for complex, long-horizon agent workflows beyond the older tau2 telecom and airline task families.
As of March 2026, Qwen3.6 Plus leads the TAU3-Bench leaderboard with 70.7% , followed by Claude Opus 4.5 (70.2%) and Qwen3.5 397B (68.4%).
Qwen3.6 Plus
Alibaba
Claude Opus 4.5
Anthropic
Qwen3.5 397B
Alibaba
According to BenchLM.ai, Qwen3.6 Plus leads the TAU3-Bench benchmark with a score of 70.7%, followed by Claude Opus 4.5 (70.2%) and Qwen3.5 397B (68.4%). The top models are clustered within 2.3 points, suggesting this benchmark is nearing saturation for frontier models.
5 models have been evaluated on TAU3-Bench. The benchmark falls in the Agentic category. This category carries a 22% weight in BenchLM.ai's overall scoring system. TAU3-Bench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
Year
2026
Tasks
Long-horizon tool workflows
Format
Interactive tool-use evaluation
Difficulty
Advanced tool use
TAU3-Bench appears in the Qwen3.6 launch tables as a broader, more modern tool-use benchmark than the earlier tau2 slices. BenchLM tracks it separately because it is not the same benchmark as Tau2-Telecom or Tau2-Airline.
Qwen3.6 launch benchmarksVersion
TAU3-Bench 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
A next-generation tool-use benchmark for complex, long-horizon agent workflows beyond the older tau2 telecom and airline task families.
Qwen3.6 Plus by Alibaba currently leads with a score of 70.7% on TAU3-Bench.
5 AI models have been evaluated on TAU3-Bench on BenchLM.
Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.
Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.