Skip to content

Benchmark

TAU3-Bench

Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.

Models measured
10
Scores recorded
14
Sources
2
IQ weight
1.12

Score distribution

64.9%
Mean
70.6%
Median
14.6%
Std dev
45.8%
10th percentile
72.9%
90th percentile
22.6%
Min
22.6%86.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.12 for chat models, measured over 9 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1GPT-Live 1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86.2%
2MiMo V2.5 ProXiaomi MiMo-V2.5-Pro official launch table · aggregate/domain and harness unspecified· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.72.9%
3MiMo V2.5 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.9%
4Nemotron 3 UltraNeMo Evaluator SDK · TauBench v3 · four-domain average· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.70.9%
5Qwen3.6 PlusQwen official release table · thinking mode unless benchmark requires otherwise · official user model GPT-5.2 low · default BM25 retrieval· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.70.7%
6Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.7%
7GLM 5.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.6%
8GLM 5.1GLM-5.1 official release table· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.70.6%
9Qwen3.6 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim67.2%
10Qwen3.6 FlashQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.67.2%
11Granite 4.2 30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim62%
12Granite 4.2 8B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim58.1%
13Granite 4.2 3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim45.8%
14Nemotron 3 Ultra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim22.6%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats