Skip to content

Benchmark

tau3-bench v1 banking-knowledge pass^4

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

Models measured
25
Scores recorded
26
Sources
1
IQ weight
1.85

Score distribution

15.9%
Mean
13.4%
Median
10.4%
Std dev
4.1%
10th percentile
32%
90th percentile
1%
Min
1%35.1%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.85 for chat models, measured over 25 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Qwen3.8 Maxsubmission-qwen3-8-max_sierra_2026-08-04, usersim-gpt-5.2, effort-xhigh, retrieval-alltools· Sierra tau-bench Leaderboard data docs35.1%
2Claude Opus 5submission-claude-opus-5_sierra_2026-08-04, usersim-gpt-5.2, effort-max, retrieval-alltools· Sierra tau-bench Leaderboard data docs32%
3Grok 4.5submission-grok-4-5_sierra_2026-08-04, usersim-gpt-5.2, effort-high, retrieval-alltools· Sierra tau-bench Leaderboard data docs32%
4GPT 5.5submission-gpt-5-5_sierra_2026-05-05, usersim-gpt-5.2, effort-xhigh, retrieval-alltools· Sierra tau-bench Leaderboard data docs29.9%
5Claude Fable 5submission-claude-fable-5_sierra_2026-08-04, usersim-gpt-5.2, effort-max, retrieval-alltools· Sierra tau-bench Leaderboard data docs28.9%
6GPT-5.6 Solsubmission-gpt-5-6-sol_sierra_2026-08-04, usersim-gpt-5.2, effort-xhigh, retrieval-alltools· Sierra tau-bench Leaderboard data docs27.8%
7Claude Opus 4.7submission-claude-opus-4-7_sierra_2026-05-05, usersim-gpt-5.2, effort-max, retrieval-alltools· Sierra tau-bench Leaderboard data docs24.7%
8Claude Opus 4.8submission-claude-opus-4-8_sierra_2026-08-04, usersim-gpt-5.2, effort-max, retrieval-alltools· Sierra tau-bench Leaderboard data docs22.7%
9GPT 5.4submission-gpt-5-4_sierra_2026-03-25, usersim-gpt-5.2, effort-xhigh, retrieval-alltools· Sierra tau-bench Leaderboard data docs21.7%
10Muse Spark 1.1submission-muse-spark-1-1_sierra_2026-08-04, usersim-gpt-5.2, effort-xhigh, retrieval-alltools· Sierra tau-bench Leaderboard data docs20.6%
11GPT 5.2submission-gpt-5-2_sierra_2026-02-26, usersim-gpt-5.2, effort-high, retrieval-alltools· Sierra tau-bench Leaderboard data docs18.6%
12Kimi K3submission-kimi-k3_sierra_2026-08-04, usersim-gpt-5.2, effort-max, retrieval-alltools· Sierra tau-bench Leaderboard data docs17.5%
13GLM 5.2submission-glm-5-2_sierra_2026-08-04, usersim-gpt-5.2, effort-xhigh, retrieval-alltools· Sierra tau-bench Leaderboard data docs13.4%
14Inkling FP4submission-inkling_sierra_2026-08-04, usersim-gpt-5.2, effort-max, retrieval-alltools· Sierra tau-bench Leaderboard data docs11.3%
15Claude Opus 4.5submission-claude-opus-4-5_sierra_2026-02-26, usersim-gpt-5.2, effort-high, retrieval-alltools· Sierra tau-bench Leaderboard data docs11.3%
16Claude Opus 4.6submission-claude-opus-4-6_sierra_2026-05-05, usersim-gpt-5.2, effort-max, retrieval-alltools· Sierra tau-bench Leaderboard data docs11.3%
17Claude Sonnet 4.5submission-claude-sonnet-4-5_sierra_2026-02-26, usersim-gpt-5.2, effort-enabled, retrieval-terminal· Sierra tau-bench Leaderboard data docs10.3%
18Gemini 3.1 Pro Previewsubmission-gemini-3-1-pro-preview_sierra_2026-05-05, usersim-gpt-5.2, effort-high, retrieval-alltools· Sierra tau-bench Leaderboard data docs9.3%
19Gemini 3 Flashsubmission-gemini-3-flash_sierra_2026-03-02, usersim-gpt-5.2, effort-high, retrieval-terminal· Sierra tau-bench Leaderboard data docs7.2%
20Grok 4.1 Fastsubmission-grok-4-1-fast_sierra_2026-05-05, usersim-gpt-5.2, effort-high, retrieval-alltools· Sierra tau-bench Leaderboard data docs5.2%
21Qwen3.5 397B A17Bsubmission-qwen3.5-397b-a17b-think_sierra_2026-03-02, usersim-gpt-5.2, effort-enabled, retrieval-text-emb-3-large· Sierra tau-bench Leaderboard data docs5.2%
22Gemini 3 Pro Previewsubmission-gemini-3-pro_sierra_2026-03-02, usersim-gpt-5.2, effort-high, retrieval-terminal· Sierra tau-bench Leaderboard data docs4.1%
23GPT 5.2submission-gpt-5-2-none_sierra_2026-02-26, usersim-gpt-5.2, effort-none, retrieval-qwen-embeddings· Sierra tau-bench Leaderboard data docs4.1%
24Grok 4 Fastsubmission-grok-4-fast_sierra_2026-05-05, usersim-gpt-5.2, effort-high, retrieval-alltools· Sierra tau-bench Leaderboard data docs4.1%
25GLM 5submission-glm-5-think_sierra_2026-03-02, usersim-gpt-5.2, effort-enabled, retrieval-text-emb-3-large· Sierra tau-bench Leaderboard data docs3.1%
26Gemini 2.5 Prosubmission-gemini-2-5-pro_sierra_2026-05-05, usersim-gpt-5.2, effort-high, retrieval-alltools· Sierra tau-bench Leaderboard data docs1%

Data credits: Sierra Research tau2-bench leaderboard submissions (github.com/sierra-research/tau2-bench), MIT (licence)