Be part of our day by day and weekly newsletters for the most recent updates and unique content material on industry-leading AI protection. Be taught Extra
It began with the announcement of OpenAI’s o1 mannequin in Sept. 2024, however actually took off with the DeepSeek R1 launch in Jan. 2025.
Now, evidently most main AI mannequin suppliers and trainers are in a brand new race to ship higher, sooner, and cheaper “reasoning” AI language fashions — that’s, ones that perhaps take just a little longer to answer a human consumer, however ideally accomplish that with higher, extra complete, extra nicely “reasoned” solutions, which these class of fashions get by performing “chain-of-thought,” reflecting on their very own conclusions and interrogating them for veracity earlier than responding.
ByteDance, the Chinese language net media large dad or mum of TikTok, is the most recent to affix the occasion with the announcement and publication of the technical paper behind Seed-Considering-v1.5, an upcoming massive language mannequin (LLM) designed to advance reasoning efficiency throughout each science, tech, math, and engineering (STEM) fields and general-purpose domains.
The mannequin shouldn’t be but obtainable for obtain or use, and it’s unclear what the licensing phrases might be—whether or not it is going to be proprietary/closed supply, open supply/free for all to make use of and modify at will, or someplace in between. Nevertheless, the technical paper supplies some noteworthy particulars which might be value going over now and prematurely of each time they’re made obtainable.
Constructed atop the more and more standard Combination-of-Consultants (MoE) structure
Like Meta’s new Llama 4 and Mistral’s Mixtral earlier than it, Seed-Considering-v1.5 is constructed utilizing a Combination-of-Consultants (MoE) structure.
This structure is designed to make fashions extra environment friendly. It basically combines the capabilities of a number of fashions into one, every specializing in a unique area.
On this case, the MoE structure signifies that Seed-Considering-v1.5 makes use of solely 20 billion of the 200 billion parameters at a time.
ByteDance says in its technical paper printed to GitHub that Seed-Considering-v1.5 prioritizes structured reasoning and considerate response technology.
The outcomes almost communicate for themselves, with Seed-Considering-v1.5 outperforming DeepSeek R1 and approaching Google’s newly launched Gemini 2.5 Professional and OpenAI’s o3-mini-high reasoner on many third-party benchmark evaluations. It even exceeds these two within the case of the ARC-AGI benchmark, which measures progress in direction of synthetic normal intelligence, seen because the objective or “Holy Grail” of AI. This mannequin outperforms people on most economically precious duties, in keeping with OpenAI’s definition.
Positioned as a compact but succesful various to bigger state-of-the-art fashions, Seed-Considering-v1.5 achieves aggressive benchmark outcomes. It introduces reinforcement studying (RL) improvements, coaching knowledge curation and AI infrastructure.
Efficiency benchmarks and mannequin focus
Seed-Considering-v1.5 reveals robust efficiency on a collection of difficult duties, scoring 86.7% on AIME 2024, 55.0% cross@8 on Codeforces and 77.3% on the GPQA science benchmark. These outcomes place it near or matching fashions like OpenAI’s o3-mini-high and Google’s Gemini 2.5 Professional on particular reasoning metrics.
On non-reasoning duties, the mannequin was evaluated by human choice comparisons and achieved an 8.0% larger win fee over DeepSeek R1, suggesting that its strengths generalize past logic or math-heavy challenges.
To deal with saturation in commonplace benchmarks like AIME, ByteDance launched BeyondAIME, a brand new, tougher math benchmark with curated issues designed to withstand memorization and higher discriminate mannequin efficiency. This and the Codeforces analysis set are anticipated to be publicly launched to help future analysis.
Information technique
Coaching knowledge performed a central function within the mannequin’s growth. For supervised fine-tuning (SFT), the crew curated 400,000 samples, together with 300,000 verifiable (STEM, logic and coding duties) and 100,000 non-verifiable issues like inventive writing and role-playing.
For RL coaching, knowledge was segmented into:
- Verifiable issues: 100,000 rigorously filtered STEM questions and logic puzzles with recognized solutions, sourced from elite competitions and skilled assessment.
- Non-verifiable duties: Human-preference datasets centered on open-ended prompts, evaluated utilizing pairwise reward fashions.
The STEM knowledge leaned closely on superior arithmetic, accounting for over 80% of the issue set. Extra logic knowledge included duties like Sudoku and 24-point puzzles, with adjustable problem to match mannequin progress.
Reinforcement studying method
Reinforcement studying in Seed-Considering-v1.5 is powered by customized actor-critic (VAPO) and policy-gradient (DAPO) frameworks, developed to deal with recognized instabilities in RL coaching. These methods cut back reward sign sparsity and improve coaching stability, particularly in lengthy chain-of-thought (CoT) settings.
Reward fashions play a essential function in supervising RL outputs. ByteDance launched two key instruments:
- Seed-Verifier: A rule-based LLM that checks if generated and reference solutions are mathematically equal.
- Seed-Considering-Verifier: A step-by-step reasoning-based choose that improves judgment consistency and resists reward hacking.
This two-tiered reward system allows nuanced analysis for each simple and sophisticated duties.
Infrastructure and scaling
To help environment friendly large-scale coaching, ByteDance constructed a system atop its HybridFlow framework. Execution is dealt with by Ray clusters, and coaching and inference processes are co-located to cut back GPU idle time.
The Streaming Rollout System (SRS) is a notable innovation that separates mannequin evolution from runtime execution. It accelerates iteration velocity by asynchronously managing partially accomplished generations throughout mannequin variations. This structure reportedly delivers as much as 3× sooner RL cycles.
Extra infrastructure methods embrace:
- Blended precision (FP8) for reminiscence financial savings
- Skilled parallelism and kernel auto-tuning for MoE effectivity
- ByteCheckpoint for resilient and versatile checkpointing
- AutoTuner for optimizing parallelism and reminiscence configurations
Human analysis and real-world impression
To judge alignment with human-centric preferences, ByteDance performed human testing throughout a variety of domains, together with inventive writing, humanities data and normal dialog.
Seed-Considering-v1.5 constantly outperformed DeepSeek R1 throughout classes, reinforcing its applicability to real-world consumer wants.
The event crew notes that reasoning fashions educated totally on verifiable duties demonstrated robust generalization to inventive domains—an final result attributed to the construction and rigor embedded in mathematical coaching workflows.
What it means for technical leaders, knowledge engineers and enterprise decision-makers
For technical leads managing the lifecycle of huge language fashions—from knowledge curation to deployment—Seed-Considering-v1.5 presents a possibility to rethink how reasoning capabilities are built-in into enterprise AI stacks.
Its modular coaching course of, which incorporates verifiable reasoning datasets and multi-phase reinforcement studying, notably appeals to groups seeking to scale LLM growth whereas retaining fine-grained management.
ByteDance’s strikes to introduce Seed-Verifier and Seed-Considering-Verifier provide mechanisms for extra reliable reward modeling, which may be essential when deploying fashions into customer-facing or regulated environments.
For groups working beneath tight deadlines and restricted bandwidth, the mannequin’s stability beneath reinforcement studying, enabled by improvements like VAPO and dynamic sampling, may cut back iteration cycles and streamline fine-tuning for particular duties.
From an orchestration and deployment perspective, the mannequin’s hybrid infrastructure method—together with the Streaming Rollout System (SRS) and help for FP8 optimization—suggests vital beneficial properties in coaching throughput and {hardware} utilization.
These options can be precious for engineers answerable for scaling LLM operations throughout cloud and on-prem methods. The truth that Seed-Considering-v1.5 was educated with mechanisms to adapt reward suggestions based mostly on runtime dynamics speaks on to the challenges of managing heterogeneous knowledge pipelines and sustaining consistency throughout domains.
For groups tasked with making certain reliability, reproducibility, and steady integration of latest instruments, Seed-Considering-v1.5’s system-level design may function a blueprint for constructing strong, multi-modal orchestration methods.
For knowledge engineering professionals, the structured method to coaching knowledge—together with rigorous filtering, augmentation and skilled verification—reinforces the significance of knowledge high quality as a multiplier of mannequin efficiency. This might encourage extra deliberate approaches to dataset growth and validation pipelines.
Future outlook
Seed-Considering-v1.5 outcomes from collaboration inside ByteDance’s Seed LLM Programs crew, led by Yonghui Wu and with public illustration by Haibin Lin, a long-time AI contributor.
The undertaking additionally attracts on earlier efforts, reminiscent of Doubao 1.5 Professional, and incorporates shared methods in RLHF and knowledge curation.
The crew plans to proceed refining reinforcement studying methods, specializing in coaching effectivity and reward modeling for non-verifiable duties. The general public launch of inside benchmarks reminiscent of BeyondAIME is meant to foster broader development in reasoning-focused AI analysis.
