AI Battle > Rankings > 𝜏³-Banking: Score

𝜏³-Banking: Score Ranking β€” eval tau3 (2026)

Qwen3.8 Max by Alibaba leads the 𝜏³-Banking: Score ranking with a score of 0.51. The ranking covers 20 evaluated eval tau3 from a public dataset that AI Battle re-checks daily.

Last updated: . Source: public benchmark datasets and provider pricing, aggregated daily; 20 entries shown.

Qwen3.8 Max0.51Grok 4.6 (high)0.51Muse Spark 1.3 (max)0.51GLM-5.3 (max)0.50Qwen3.8 2.4T A95B0.49Qwen3.8 27B (xhigh)0.48Agnes 3.0 Flash0.48Qwen3.8 27B (medium)0.47Claude Fable 5.1 (Adaptive Reasoning, Max Ef0.47Muse Spark 1.3 (xhigh)0.47GLM-5.3-Flash0.47Kimi K3 (max)0.46Claude Fable 5.1 (Adaptive Reasoning, Xhigh 0.46Gemini 3.8 Flash (high)0.45GPT-5.6 Sol (max)0.44Claude Opus 5 (Adaptive Reasoning, Max Effor0.42GPT-6 Astra (max)0.41GPT-5.6 Terra (max)0.40DeepSeek V4 Pro 0813 (Reasoning, Max Effort)0.40Claude Fable 5 (Adaptive Reasoning, Max Effo0.38
Every entry in the dataset, scaled from the smallest to the largest published value.

All 20 entries in this dataset

#EntryCreatorValueΞ” vs #1
1Qwen3.8 MaxAlibaba0.510.0%
2Grok 4.6 (high)SpaceXAI0.51-1.2%
3Muse Spark 1.3 (max)Meta0.51-1.6%
4GLM-5.3 (max)Z AI0.50-2.0%
5Qwen3.8 2.4T A95BAlibaba0.49-4.4%
6Qwen3.8 27B (xhigh)Alibaba0.48-6.4%
7Agnes 3.0 FlashSapiens AI0.48-7.2%
8Qwen3.8 27B (medium)Alibaba0.47-7.6%
9Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)Anthropic0.47-8.0%
10Muse Spark 1.3 (xhigh)Meta0.47-8.0%
11GLM-5.3-FlashZ AI0.47-8.0%
12Kimi K3 (max)Kimi0.46-10.4%
13Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)Anthropic0.46-10.8%
14Gemini 3.8 Flash (high)Google0.45-12.4%
15GPT-5.6 Sol (max)OpenAI0.44-13.7%
16Claude Opus 5 (Adaptive Reasoning, Max Effort)Anthropic0.42-18.1%
17GPT-6 Astra (max)OpenAI0.41-19.3%
18GPT-5.6 Terra (max)OpenAI0.40-21.7%
19DeepSeek V4 Pro 0813 (Reasoning, Max Effort)DeepSeek0.40-22.9%
20Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Anthropic0.38-25.7%

How the values are distributed

Across the 20 numeric entries in this window the median is 0.47 and the mean is 0.46, so the typical entry sits 0.04 below the leader. The window spans 0.38 to 0.51.

21213524
8 equal buckets between the smallest (0.38) and largest (0.51) value; numbers under bars are entry counts.

11 of 20 entries are at or above the median, and the top three hold 17% of the combined value β€” read it against the metric below, since a higher number is not "better" for every dataset.

Creators in this ranking

10 creators appear in this window; the three most-represented hold 55% of the entries.

CreatorEntriesHighest valueTop entry
Alibaba40.51Qwen3.8 Max
Anthropic40.47Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)
OpenAI30.44GPT-5.6 Sol (max)
Meta20.51Muse Spark 1.3 (max)
Z AI20.50GLM-5.3 (max)
SpaceXAI10.51Grok 4.6 (high)
Sapiens AI10.48Agnes 3.0 Flash
Kimi10.46Kimi K3 (max)
Google10.45Gemini 3.8 Flash (high)
DeepSeek10.40DeepSeek V4 Pro 0813 (Reasoning, Max Effort)

Where these models appear in other rankings

The same models are measured across multiple independent datasets. Aggregating the 20 entries above against every other AI Battle dataset gives this cross-section, computed by AI Battle and published nowhere upstream:

ModelDatasetsBest placements elsewhere
Qwen3.8 Max3#10/20 in 𝜏³-Banking: Output Tokens per Task, #20/20 in 𝜏³-Banking: Cost per Task
Grok 4.6 (high)61#5/20 in AA-Briefcase Elo, #5/20 in AA-Omniscience Index, #5/20 in AA-Omniscience Index
Muse Spark 1.3 (max)61#3/20 in AA-Briefcase Elo, #3/20 in Output Speed, #3/20 in GDPval-AA v2 Leaderboard
GLM-5.3 (max)57#3/20 in AA-Briefcase Tool Calls Breakdown, Avg per Task, #4/20 in GDPval-AA v2 Leaderboard, #4/20 in AA-Omniscience Hallucination Rate
Qwen3.8 2.4T A95B43#2/14 in Model Size: Total and Active Parameters, #5/20 in AA-Briefcase Tool Calls Breakdown, Avg per Task, #6/20 in GDPval-AA v2: Average Turns per Task
Qwen3.8 27B (xhigh)43#6/20 in AA-Omniscience Hallucination Rate, #8/20 in AA-LCR v1.1: Cost per Task, #8/19 in MMMU-Pro: Total Cost to Run
Agnes 3.0 Flash3#1/20 in 𝜏³-Banking: Cost per Task, #4/20 in 𝜏³-Banking: Time per Task
Qwen3.8 27B (medium)3#7/20 in 𝜏³-Banking: Output Tokens per Task, #9/20 in 𝜏³-Banking: Cost per Task
Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)36#1/20 in AA-Briefcase Elo, #1/20 in AA-Omniscience Index, #1/20 in Artificial Analysis Intelligence Index by Open Weights / Proprietary
Muse Spark 1.3 (xhigh)12#3/20 in 𝜏³-Banking: Time per Task, #5/20 in SciCode: Score, #7/20 in GDPval-AA v2 Leaderboard
GLM-5.3-Flash54#1/20 in Pricing: Cache Hit, Input, and Output, #1/20 in Pricing: Cache Hit, Input, and Output, #1/20 in AA-Omniscience Index: Cost Breakdown
Kimi K3 (max)60#1/20 in Context Window, #1/20 in AA-LCR v1.1: Score, #1/14 in Model Size: Total and Active Parameters
Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)20#2/20 in Humanity's Last Exam: Score, #2/20 in AA-Omniscience Accuracy, #2/20 in AA-Briefcase Rubric Pass Rate by File Type (Normalized)
Gemini 3.8 Flash (high)60#1/11 in Speed, #1/11 in Speed, #2/20 in Output Speed
GPT-5.6 Sol (max)56#3/20 in SciCode: Output Tokens per Task, #4/20 in 𝜏³-Banking: Output Tokens per Task, #5/20 in AA-LCR v1.1: Output Tokens per Task
Claude Opus 5 (Adaptive Reasoning, Max Effort)44#2/20 in AA-Briefcase Elo, #2/20 in GDPval-AA v2 Leaderboard, #2/20 in AA-Briefcase Elo
GPT-6 Astra (max)51#1/19 in MMMU-Pro: Score, #2/20 in AA-Omniscience Index, #2/20 in Artificial Analysis Intelligence Index by Open Weights / Proprietary
GPT-5.6 Terra (max)52#7/20 in AA-Briefcase Output Tokens per Task, #8/20 in Humanity's Last Exam: Output Tokens per Task, #9/20 in Output Speed
DeepSeek V4 Pro 0813 (Reasoning, Max Effort)59#3/14 in Model Size: Total and Active Parameters, #3/12 in Artificial Analysis Openness Index: Score, #3/11 in Cost per Task
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)40#2/20 in SciCode: Score, #3/20 in AA-Omniscience Index, #3/20 in AA-Omniscience Index

Metric reference

This ranking carries the metric 𝜏³-Banking from the 𝜏³-Banking: Score dataset in the tab::eval-tau3 family. Units and the direction of "better" are not declared by the source dataset, so AI Battle does not invent them: values are shown exactly as published, and the ordering is the source dataset's own.

How this ranking is built

Rebuilt on from the public dataset 𝜏³-Banking: Score (family tab::eval-tau3). The source lists 20 entries and all 20 are shown here. AI Battle requests the dataset's rows, keeps the ordering the source publishes, and computes only the statistics on this page: median, mean, spread, the #1–#2 gap, the creator breakdown and the raw-data file. Nothing on this page is generated text about the entries β€” the numbers come from the source.

Refresh cadence: every deploy re-pulls the dataset, so this page tracks the source's own update cycle. Corrections: see the methodology page.

Limitations

Raw data

Machine-readable copy of this table, with the statistics below and the source provenance: /data/rankings/eval-tau3-3-banking-score.json. Free to reuse with attribution to AI Battle and the source dataset.

FAQ β€” 𝜏³-Banking: Score

What is the best model for 𝜏³-Banking: Score in 2026?

Qwen3.8 Max by Alibaba currently leads the 𝜏³-Banking: Score ranking with a score of 0.51, the highest value in this dataset across eval tau3. AI Battle aggregates the dataset from its public source and re-checks it daily.

How often is the 𝜏³-Banking: Score ranking updated?

The 𝜏³-Banking: Score ranking is rebuilt daily from the upstream public dataset. Scores are the source dataset's own published values, so positions track whatever that source last released β€” each ranking page names the dataset it comes from.

Which models rank in the top 3 for 𝜏³-Banking: Score?

The top 3 are: 1. Qwen3.8 Max (0.51), 2. Grok 4.6 (high) (0.51), 3. Muse Spark 1.3 (max) (0.51).

All AI Battle Rankings

Directories