Banking77
PulseAugur coverage of Banking77 — every cluster mentioning Banking77 across labs, papers, and developer communities, ranked by signal.
- instance of Jevíčko 90%
- instance of Clef-flash 90%
- instance of System One 90%
- competes with Jevíčko 70%
- used by CLINC150 70%
- used by Laya 70%
- competes with Lightbend Inc. 70%
- instance of Conference and Labs of the Evaluation Forum 70%
- competes with Claude Haiku 5.5 70%
- instance of CLINC150+OOS 70%
- used by Jevíčko 60%
- instance of CLINC150 60%
11 day(s) with sentiment data
-
GPT-6.1 Terra leads cost-effective LLMs for banking intent classification
A recent analysis compared ten LLMs on the Banking77 intent classification task, finding GPT-6.1 Terra to be the most cost-effective model that meets a 70% success threshold. While GPT-6.1 Terra achieved an 84% pass rat…
-
GLiNER2 extraction model tested against Claude Haiku 5.5
A recent comparison evaluated the performance of GLiNER2, an open-source extraction model, against Anthropic's Claude Haiku 5.5 for JSON extraction tasks. GLiNER2, which runs on a CPU and uses a schema for extraction, p…
-
LLM research explores data selection, TCS evaluation, and RAG vs. fine-tuning strategies
Researchers are exploring new methods for fine-tuning Large Language Models (LLMs) and evaluating their capabilities. One study suggests prioritizing data coverage over difficulty for more effective fine-tuning, outperf…
-
New framework evaluates machine unlearning for probabilistic decisions
Researchers have introduced DecisionUnlearn-Bench, a new empirical framework designed to evaluate machine unlearning for probabilistic decision models. This framework assesses how well models can forget specific data wh…
-
System One models offer faster, cheaper AI decisions than LLMs
A new class of AI models, termed "System One" models, are designed for fast, structured decisions rather than text generation. In a comparison, a System One model named Jev demonstrated significantly lower latency and c…
-
DeepOpen framework achieves high accuracy on banking and intent classification tasks
Researchers have introduced DeepOpen, a framework for decision-oriented intent classification tailored for specific datasets like BANKING77 and CLINC150. The system achieved a high accuracy of 94.12% on BANKING77 using …
-
ELMDE system slashes LLM decision latency to milliseconds
A new system called the Equilibrium Latent-MoE Decision Engine (ELMDE) has been developed to significantly speed up decision-making processes in language models. Unlike traditional token-by-token decoding, ELMDE process…
-
Vektor's Desk AI agent boosts message routing accuracy to 90%
Vektor has released an update to its AI agent, Desk, version 2.0.1, significantly improving its automatic routing capabilities. The new version can now correctly route about 90% of messages to the appropriate mode, a su…
-
Jev, Drex, and Laya: System-One Decision Models Compared for Medical and General Use
A comparative study published on arXiv highlights the reliability of Jev, a system-one decision model, in medical contexts, finding it rivals leading models on text-driven tasks but struggles with numerical ones. The re…
-
HotKV cuts Claude token use by 70% via semantic caching
HotKV, a semantic caching system, has demonstrated a significant reduction in LLM operational costs by serving repeated and similar customer support queries from memory. In tests using Anthropic's Claude models, HotKV d…
-
AutoTrust-JEV-27B v1.1 model evaluated on Decision Index 0.3
The autotrust/AutoTrust-JEV-27B-v1.1 model has been evaluated on the Decision Index 0.3 benchmark suite, achieving a public index score of 67.31 across 37 benchmarks and over 140,000 requests. The model demonstrates par…
-
20+ Jev Decision Model Alternatives Emerge, Challenging TypeSafe's Offering
In response to TypeSafe's Jev decision model, over 20 alternatives have emerged since its launch in September 2026. These alternatives, developed by companies like Cloudflare, OpenAI, and Perplexity, as well as independ…
-
SemTree introduces inspectable, repairable semantic decision trees
Researchers have developed SemTree, a novel framework that represents rule decisions as semantic decision trees. Each node in the tree poses a natural-language question, and a semantic judge answers it, with the tree's …
-
Jev decision model shows significant option-set dependence in tests
A new study published on arXiv investigates the option-set dependence of hosted decision models, specifically testing the Jev model. The research found that adding irrelevant alternatives to classification tasks signifi…
-
Cloudflare releases Clef-omni multimodal decision model
Cloudflare has released Clef-omni, a 30B multimodal mixture-of-experts model, on Hugging Face under an Apache 2.0 license. Unlike traditional LLMs, Clef-omni is designed for decision-making tasks, accepting text, images…
-
Cloudflare launches Clef-Flash, a 9B decision model for rapid classification
Cloudflare has released Clef-Flash, a 9 billion parameter decision model designed for speed and efficiency, built upon Qwen3.5-9B. Unlike traditional chat models, Clef-Flash processes input states and typed questions in…
-
New Lexical Confidence Method Enhances AI Intent Routing Reliability
Researchers have developed a new method called Signed Lexical Confidence (SLC) to improve the reliability of AI intent routing. This technique combines a classifier's confidence score with evidence from a lexical model,…
-
Cloudflare releases Clef decision models for typed probability outputs
Cloudflare has introduced Clef and Clef-flash, two open-weight decision models designed for specific question answering rather than general text generation. These models, built upon Qwen backbones and compatible with th…
-
Local AI model laya-triage boosted to 90.5% accuracy on support tickets
A developer has successfully fine-tuned a local AI model, laya-triage, to improve its accuracy in classifying support tickets from 51% to 90.5%. This was achieved by training on 10,003 BANKING77 support tickets using Ka…
-
yoDEV Decisions tool compares LLM performance on user data
yoDEV Decisions is a new free tool for yoDEV members that allows users to compare the performance of various Large Language Models (LLMs) against their own data. The tool runs the same query across selected LLMs and a m…