@AfterQuery

Applied research lab curating data solutions to accelerate foundation model development.

afterquery.com
Joined February 2025
  • Tweets88
  • Following9
  • Followers3.6K
17Media
Kimi K3 ranks #1 on @AfterQuery's SpreadsheetBench 2, surpassing Claude Fable 5. An open weight model now outperforms all closed-sourced models. Read more in the Kimi K3 blog and SpreadsheetBench 2 paper linked below. Congrats to the @kimi_moonshot team on the incredible model!
38
119
29
1,043
149,296
Replying to @AfterQuery
@AfterQuery is partnering with @NVIDIA to help enterprises post-train Nemotron 3.5 Super VL. The future of enterprise agents is open. 💚
NVIDIA AI
@NVIDIAAIOct 16
Big shoutout to all of our partners for making Nemotron 3.5 Super VL their own through post-training 🙌 Here’s what they’ve built 🧵
2
5
2
25
1,847
@AfterQuery just moved an open model past the cost-accuracy frontier in finance. We post-trained @NVIDIAAI Nemotron 3.5 Super VL on expert credit tasks with @hebbia. Perfect solved: 47% to 74%. That beats Sol 6, and lands within 3 points of Astra 6, at about 1/7 the cost. Link to the full case study in replies.
7
23
11
117
19,969
Learn more: afterquery.com/blog/post-tra…

Post-Training NVIDIA Nemotron 3.5 Super VL for Finance: More Accurate, Cost-Efficient Financial...

AfterQuery and Hebbia post-trained the NVIDIA Nemotron 3.5 Super VL open model on expert-written public credit tasks. Perfect solves on a 100-task held-out set rose from 47% to 74%.

afterquery.com
2
1
10
683
Replying to @AfterQuery
@AfterQuery’s throwing a sftw happy hour with @NVIDIAAI tonight at 6:30pm. reply for an invite.
13
6
5
24
2,708
Not all coding data is created equal. Using only 500 tasks from @AfterQuery's SWE agent dataset, our internal post-training team was able to improve Qwen3.8-27B-Medium by 11.3 points in only 15 steps of GRPO. Read more about our training experiment in the blog post linked in the comments.
22
33
7
211
27,648
Read more about our experiment using SkyRL here: afterquery.com/blog/improvin… To learn more about our tasks and reward design, reach out to us at [email protected]

Improving Qwen3.8-27B-Medium on DeepSWE with GRPO - AfterQuery

GRPO on 500 SWE agent training tasks created by AfterQuery raised Qwen3.8-27B’s DeepSWE pass@1 (avg 3) from 27.8% to 39.1%.

afterquery.com
2
7
3
28
3,966
Working on AI research, post-training, or deployment? Come meet the @AfterQuery Team during SF Tech Week. Wed 10/7: Frontier of Finance with Goldman Sachs Fri 10/9: Rooftop happy hour We'd love to see you there. Details + RSVPs below.
12
11
4
45
9,496
Replying to @AfterQuery
@AfterQuery is hosting a panel with @GoldmanSachs during SF Tech Week to discuss the frontier of finance! RSVP in the replies👇
4
4
2
12
929
People still underestimate how large the data market will become. Better models do not reduce demand for data. They increase the number of useful things models can learn. The frontier keeps moving, so the data has to keep getting harder.
15
18
7
159
14,363
last nights spread for @AfterQuery‘s 3rd poker night now hosting these biweekly♠️
6
7
4
15
1,505
fluffy work trialers at the @AfterQuery office today
9
9
5
69
6,822
If you're free tomorrow night, @AfterQuery is hosting a researcher poker night tmr @ 8:30pm rsvp for deets👇
7
7
4
14
2,827
The @AfterQuery post-training team helped patch a critical LoRA weight-loading bug in SkyRL today. Check out our PR in the replies.
11
14
6
75
8,518
Gemini 3.8 set SOTA on DeepSWE at 9am. Muse Spark 1.3 took it back at 12:30pm. Incredible work from the MSL coding team.
Mark Zuckerberg
@finkdSep 2
Muse Spark 1.3 is rolling out today with frontier performance almost too cheap to meter. This is the biggest jump we've made so far on coding and agentic work. Try it in Muse Code and our API. Next up 🍉 and Muse Spark open weights releases coming soon.
13
9
4
40
4,857
Legal and finance are two of the highest-impact domains to crack. 3.8 Flash now leads both Harvey’s Legal Agent Benchmark and Vals Finance Agent v2. Huge congrats to GDM ⚡️
Logan Kilpatrick
@OfficialLoganKSep 2
Introducing Gemini 3.8 Flash, another jump in Gemini's agentic + coding capabilities, and our 3rd updated Flash model in only 6 weeks... This model has been a ton of fun to work with, excited to see what you all think!
15
14
4
52
6,255
New @nvidia DGX Spark just came in. Hyped to put it to work and eliminate inference costs on a few of my workflows.
12
7
1
65
5,025
Congratulations to the @motif_tech team on the release of Motif 3! AfterQuery is proud to have served as the sole data partner on this model.
9
6
2
43
15,052
This is a historic moment for Korean sovereign AI and the open weights ecosystem writ large. We look forward to supporting Motif and the Korean AI ecosystem as they push the frontier of open intelligence. Motif 3 leads its comparison set on τ³-Banking, and posts 94.7 on τ²-Bench Telecom, 74.9 on Terminal-Bench 2.1, and 76.2 on SWE-bench Verified. It’s also great to see @nvidia's open foundation put to use here - Motif 3's post-training was done via NeMo-RL. In a world where it’s easy to assume that the AI race is already won, the team at Motif is proof that the field is open, and we’re still at the starting line.
1
1
1
11
4,345
Congrats to the @thinkymachines team on the release of Inkling-Small :bufo-yay:
Thinking Machines
@thinkymachinesJul 30
Today, we are releasing Inkling-Small. Inkling-Small achieves comparable performance to Inkling at a quarter of its size. It features 276B total parameters, 12B active. We are making the full weights available. thinkingmachines.ai/news/ink… Fine-tune it on Tinker today, or chat with it in text, image, and audio on Tinker Playground.

Introducing Inkling-Small

An open-weights model that matches Inkling at a quarter of the size: multimodal, Mixture-of-Experts, with controllable reasoning effort. Fine-tune it on Tinker.

thinkingmachines.ai
6
9
1
31
6,699
hosting poker night at the @AfterQuery office this Thursday @ 8:30 pm join us 👇
13
9
3
38
6,744
Load more