Artificial Analysis Tau3-Banking (AA Tau3 Banking)
An independently evaluated Tau3 banking benchmark from Artificial Analysis.
Top models on AA Tau3 Banking — October 29, 2026
As of October 29, 2026, Grok 4.6 leads the AA Tau3 Banking leaderboard with 50.7% , followed by Muse Spark 1.3 (50.5%) and GLM-5.3 (50.3%).
Grok 4.6
xAI
Muse Spark 1.3
Meta
GLM-5.3
Z.AI
22 modelsAgentic3% of Agentic reference weightCurrentUpdated October 29, 2026
Leaderboard (22 models)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | Grok 4.6xAI | 50.7% | Not reported | Closed |
| 2 | Muse Spark 1.3Meta | 50.5% | Not reported | Closed |
| 3 | GLM-5.3Z.AI | 50.3% | Not reported | Open |
| 4 | Qwen3.8-27BAlibaba | 48.0% | Not reported | Open |
| 5 | Claude Fable 5.1Anthropic | 47.2% | Not reported | Closed |
| 6 | GLM-5.3-FlashZ.AI | 47.2% | Not reported | Open |
| 7 | Kimi K3Moonshot AI | 46.0% | Not reported | Open |
| 8 | Qwen3.8-Flash-NextAlibaba | 45.4% | Not reported | Open |
| 9 | Gemini 3.8 FlashGoogle | 44.9% | Not reported | Closed |
| 10 | GPT-5.6 SolOpenAI | 44.3% | Not reported | Closed |
| 11 | Grok 4.5xAI | 42.1% | Not reported | Closed |
| 12 | GPT-6 AstraOpenAI | 41.4% | Not reported | Closed |
| 13 | GPT-5.6 TerraOpenAI | 40.2% | Not reported | Closed |
| 14 | GPT-5.4OpenAI | 39.6% | Not reported | Closed |
| 15 | DeepSeek V4 Pro 0813DeepSeek | 39.6% | Not reported | Open |
| 16 | DeepSeek V4 Flash 0731DeepSeek | 39.4% | Not reported | Open |
| 17 | GPT-5.5OpenAI | 39.0% | Not reported | Closed |
| 18 | Ling 3.0 Flash FinInclusionAI | 38.6% | Not reported | Closed |
| 19 | Claude Fable 5Anthropic | 38.1% | Not reported | Closed |
| 20 | Claude Sonnet 5Anthropic | 37.3% | Not reported | Closed |
| 21 | InklingThinking Machines Lab | 29.1% | Not reported | Open |
| 22 | Ling 3.0 FlashInclusionAI | 28.0% | Not reported | Open |
According to BenchLM.ai, Grok 4.6 leads the AA Tau3 Banking benchmark with a score of 50.7%, followed by Muse Spark 1.3 (50.5%) and GLM-5.3 (50.3%). The top models are clustered within 0.4 points, suggesting this benchmark is nearing saturation for frontier models.
22 models have been evaluated on AA Tau3 Banking. The benchmark falls in the Agentic category. BenchAlign v5.8 gives AA Tau3 Banking 3% of the Agentic reference weight, so it moves the Agentic leaderboard and the overall ranking. Reference weights are relative weights in the calibrated model, not fixed shares of a score.
About AA Tau3 Banking
Year
2026
Tasks
Banking tool-use workflows
Format
Task success rate
Difficulty
Agentic banking workflows
Stored separately from the broader Tau3-Bench lane.
Freshness and provenance
Version
AA Tau3 Banking 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.
Questions
What does AA Tau3 Banking measure?
An independently evaluated Tau3 banking benchmark from Artificial Analysis.
Which model scores highest on AA Tau3 Banking?
Grok 4.6 by xAI currently leads with a score of 50.7% on AA Tau3 Banking.
How many models are evaluated on AA Tau3 Banking?
22 AI models have published results on AA Tau3 Banking in the BenchLM catalog.
Compare top models on AA Tau3 Banking
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 6,100+ subscribers.
One email each week. Unsubscribe anytime.