Microsoft
Fara-7B is a open-weight Microsoft specialized model.
Running this yourself: consumer gpu should be enough.
40.7
Quality Score
---
Arena ELO
7B
Parameters
---
Context
Sign in to join the discussion
15.2K
Downloads
586
Likes
Oct 2025
Released
Launches
2
Benchmarks
3
Research
2
General
3
Recent launch, pricing, benchmark, and API signals linked to this model or its provider.
Avg: 27.0 | IFEval: 40.2 | BBH: 46.6 | MATH: 17.8 | GPQA: 7.4 | MMLU-PRO: 39.6
MAI‑Transcribe‑1 makes speech‑to‑text clearer, faster, and more reliable even in noisy audio. Ranked #1 on the industry-standard FLEURS word error rate benchmark. Now in public preview. Learn more: https://t.co/Gr4Q8jgCwL https://t.co/L6hndn3D34
View sourceAvg: 27.0 | IFEval: 40.2 | BBH: 46.6 | MATH: 17.8 | GPQA: 7.4 | MMLU-PRO: 39.6
View sourceMAI-Voice-1 exports flawless audio in record speed. Can you tell the difference between the real recording and our model? Drop your best guess. Try it today. https://t.co/r6cQjv2Lng https://t.co/l9S0HCoQQL
Big on quality. Light on compute. Meet MAI‑Image‑2‑Efficient, our production model built for rapid iteration—delivering 4× the efficiency of MAI‑Image‑2. Learn more here: https://t.co/d3SF9gAmqG https://t.co/vGH1wotBuh
The most accurate model across 25 languages, faster transcription speeds, and stronger performance in real‑world noise. MAI‑Transcribe‑1 sets a new bar for speech recognition. Learn more + try it today: https://t.co/zBY6ZuqWMN https://t.co/yC3o4slXiW
MAI‑Transcribe‑1 makes speech‑to‑text clearer, faster, and more reliable even in noisy audio. Ranked #1 on the industry-standard FLEURS word error rate benchmark. Now in public preview. Learn more: https://t.co/Gr4Q8jgCwL https://t.co/L6hndn3D34
Evaluation of software engineering (SWE) agents is dominated by a binary signal: whether the final patch passes the tests. This outcome-only view treats a principled solution and a chaotic trial-and-error process as equivalent. We show that this equivalence is empirically false. We evaluate 2,614 OpenHands trajectories from eight model backends on 60 SWE-bench Verified tasks. Of these, 47 have enough passing trajectories to construct task-level process references, yielding a 1,815-trajectory evaluation subset. Among passing trajectories in this subset, 10.7% exhibit behavior we call a Lucky Pass: regression cycles, blind retries, missing verification, or temporally disordered exploration, implementation, and verification. We introduce AgentLens, a framework for process-level assessment of SWE-agent trajectories, and release AgentLens-Bench, a dataset of 1,815 trajectories annotated with quality scores, waste signals, divergence points, and 47 task-level Prefix Tree Acceptor (PTA) references. AgentLens builds PTA references by merging multiple passing solutions for the same task, and uses a context-sensitive intent labeler to assign actions to Exploration, Implementation, Verification, or Orchestration based on trajectory history rather than tool identity alone. On AgentLens-Bench, the quality score separates passing trajectories into Lucky, Solid, and Ideal tiers and further decomposes Lucky Passes into five recurring mechanisms. Across the eight model backends, Lucky rates range from 0.5% to 23.2%, and some models move by as many as five rank positions when ranked by quality score instead of pass rate. We release the anonymized project repository, including the AgentLens-Bench dataset and AgentLens SDK, at https://github.com/microsoft/code-agent-state-trajectories/.
Contextual bandits are incredibly useful in many practical problems. We go one step further by devising a more realistic problem that combines: (1) contextual bandits with dense arm features, (2) non-linear reward functions, and (3) a generalization of correlated bandits where reward distributions change over time but the degree of correlation maintains. This formulation lends itself to a wider set of applications such as recommendation tasks. To solve this problem, we introduce conditionally coupled contextual C3 Thompson sampling for Bernoulli bandits. It combines an improved Nadaraya-Watson estimator on an embedding space with Thompson sampling that allows online learning without retraining. Empirical results show that C3 outperforms the next best algorithm by 5.7% lower average cumulative regret on four OpenML tabular datasets as well as demonstrating a 12.4% click lift on Microsoft News Dataset (MIND) compared to other algorithms.