AI Paper Atlas

Research map / Benchmarks / Minerva

Minerva leaderboard

34 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Minerva. Best pass@1: 55 (PADD, ICML 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

Minerva · pass@1

19 papers, each with its best reported number for its own method; higher is better.

#pass@1 ↑MethodPaperTopic
155PADD
Qwen3-30B-A3B student
PADD: Path-Aligned Decompression Distillation for Non-Router Teacher to Guide MoE Student Learning
ICML 2026 · Table 1
Reasoning and chain of thought
251.84MACoT
Qwen2.5-7B-Instruct
MACoT: Synthesizing Chains of Thought for Small Models via Multi-Agent Collaboration
AAAI 2026 · Table 1
LLM agents
347.21GRPO w/ MAPR
Qwen3-8B-Base
Verifying Meta-Awareness via Predictive Rewards in Reasoning Models
ICML 2026 · Table 1
Reasoning and chain of thought
445.95GVPO
Qwen2.5-Math-7B
GVPO: Group Variance Policy Optimization for Large Language Model Post-Training
NeurIPS 2025 · Algorithm Performance Comparis
RL from feedback
545.5VSRM-PPO
DS-Distill-7B
Promoting Efficient Reasoning with Verifiable Stepwise Reward
AAAI 2026 · Table 1
Reasoning and chain of thought
643.1CRAFT
Qwen3-4B-Thinking
Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations
ICML 2026 · Table 2
Reasoning and chain of thought
741.2LUFFY†
Qwen2.5-Math-7B
Learning to Reason under Off-Policy Guidance
NeurIPS 2025 · Table 1
RL from feedback
841DisCO (log-L)
DeepSeek-R1-Distill-Qwen-7B
DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization
NeurIPS 2025 · Table 2
RL from feedback
940.3AttnRL
DS-R1-Distill-Qwen-1.5B
Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models
ICLR 2026 · Table 1
Reasoning and chain of thought
1040DeepSearch-1.5B
Nemotron-Research-Reasoning-Qwen-1.5B v2
DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search
ICLR 2026 · Table 1
Reasoning and chain of thought
9 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Minerva · accuracy

15 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
145.82DAPO w/ Forking Tokens
Qwen3-32B
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
NeurIPS 2025 · Table: comparison between vani
Reasoning and chain of thought
244.9CPMöbius
Qwen2.5-Math-7B-Instruct
CPMöbius: Iterative Coach–Player Reasoning for Data-Free Reinforcement Learning
ICML 2026 · Table 1
Reasoning and chain of thought
344.1ShorterBetter-7B (α=2)
DeepSeek-R1-Distill-Qwen-7B
ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning
NeurIPS 2025 · 7B results table
Reasoning and chain of thought
442.8Seirênes
Qwen3-4B-Instruct
Seirênes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning
NeurIPS 2026 · Table 1
Reasoning and chain of thought
542.6ERA
Qwen2.5-Math-7B
Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraints
ICLR 2026 · Table 2
RL from feedback
641.5TRAPO
Qwen2.5-Math-7B
Trust-Region Adaptive Policy Optimization
ICLR 2026 · Table 1
RL from feedback
741.4OmniAgent
Qwen2.5-Omni-7B
Native Active Perception as Reasoning for Omni-Modal Understanding
ICML 2026 · Table 1
Video-language understanding
840.8+ NFT
Qwen2.5-Math-7B
NFT: Bridging Supervised Learning and Reinforcement Learning in Math Reasoning
ICLR 2026 · Table 1
Reasoning and chain of thought
939.7SRFT
Qwen2.5-Math-7B
SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning
ICLR 2026 · Table 2
Instruction and fine-tuning
1038.7VSR+GRPO
Qwen2.5-7B-Instruct
Variance-Optimal State Resampling for Reinforcement Learning with Verifiable Rewards
NeurIPS 2026 · Table 1
RL from feedback
5 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.