Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/MAC

MAC

Reported on 37 benchmarks across 8 tasks · 5 papers · 11 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Playing Games12 results

Atari GamesonAtari 2600 Pong
Score· 2017-09-01
10.6
best: 21 (Duel noop)
Mean Actor Critic arXiv:1709.00503
Atari GamesonAtari 2600 Breakout
Score· 2017-09-01
372.7
best: 864 (GDI-H3(200M frames))
Mean Actor Critic arXiv:1709.00503
Atari GamesonAtari 2600 Space Invaders
Score· 2017-09-01
1173.1
best: 154380 (GDI-H3(200M frames))
Mean Actor Critic arXiv:1709.00503
Atari GamesonAtari 2600 Beam Rider
Score· 2017-09-01
6072
best: 454993.53 (MuZero)
Mean Actor Critic arXiv:1709.00503
Atari GamesonAtari 2600 Seaquest
Score· 2017-09-01
1703.4
best: 1000000 (GDI-H3(200M frames))
Mean Actor Critic arXiv:1709.00503
Atari GamesonAtari 2600 Q*Bert
Score· 2017-09-01
243.4
best: 580328.14 (Agent57)
Mean Actor Critic arXiv:1709.00503
Video GamesonAtari 2600 Pong
Score· 2017-09-01
10.6
best: 21 (Duel noop)
Mean Actor Critic arXiv:1709.00503
Video GamesonAtari 2600 Breakout
Score· 2017-09-01
372.7
best: 864 (GDI-H3(200M frames))
Mean Actor Critic arXiv:1709.00503
Video GamesonAtari 2600 Space Invaders
Score· 2017-09-01
1173.1
best: 154380 (GDI-H3(200M frames))
Mean Actor Critic arXiv:1709.00503
Video GamesonAtari 2600 Beam Rider
Score· 2017-09-01
6072
best: 454993.53 (MuZero)
Mean Actor Critic arXiv:1709.00503
Video GamesonAtari 2600 Seaquest
Score· 2017-09-01
1703.4
best: 1000000 (GDI-H3(200M frames))
Mean Actor Critic arXiv:1709.00503
Video GamesonAtari 2600 Q*Bert
Score· 2017-09-01
243.4
best: 580328.14 (Agent57)
Mean Actor Critic arXiv:1709.00503

Natural Language Processing11 results

Visual Question Answering (VQA)onQLEVR
Overall Accuracy· 2022-05-06
66.5
SOTA
QLEVR: A Diagnostic Dataset for Quantificational Language and Elementary Visual Reasoning arXiv:2205.03075
Visual Question Answering (VQA)onGQA Test2019
Accuracy· 2019-02-25
54.06
best: 89.3 (human)
SOTA
GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering arXiv:1902.09506
Visual Question Answering (VQA)onGQA test-std
Accuracy· 2019-02-25
54.06
best: 65.14 (ProTo)
SOTA
GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering arXiv:1902.09506
Visual Question Answering (VQA)onCLEVR
Accuracy· 2018-03-08
98.9
best: 99.8 (NS-VQA (1K programs))
SOTA
Compositional Attention Networks for Machine Reasoning arXiv:1803.03067
Visual Question Answering (VQA)onCLEVR-Humans
Accuracy· 2018-03-08
81.5
best: 81.7 (MDETR)
SOTA
Compositional Attention Networks for Machine Reasoning arXiv:1803.03067
Visual Question Answering (VQA)onGQA Test2019
Binary
71.23
best: 91.2 (human)
Visual Question Answering (VQA)onGQA Test2019
Consistency
81.59
best: 98.4 (human)
Visual Question Answering (VQA)onGQA Test2019
Distribution
5.34
best: 93.08 (GlobalPrior)
Visual Question Answering (VQA)onGQA Test2019
Open
38.91
best: 87.4 (human)
Visual Question Answering (VQA)onGQA Test2019
Plausibility
84.48
best: 97.2 (human)
Visual Question Answering (VQA)onGQA Test2019
Validity
96.16
best: 98.9 (human)

Computer Vision8 results

VideoonMSR-VTT-1kA
text-to-video Median Rank· uses extra data· 2022-12-02
3
best: 13 (JSFusion)
Masked Contrastive Pre-Training for Efficient Video-Text Retrieval arXiv:2212.00986
VideoonMSR-VTT-1kA
text-to-video R@1· uses extra data· 2022-12-02
38.9
best: 62.9 (HunYuan_tvr (huge))
Masked Contrastive Pre-Training for Efficient Video-Text Retrieval arXiv:2212.00986
VideoonMSR-VTT-1kA
text-to-video R@10· uses extra data· 2022-12-02
73.9
best: 90.8 (HunYuan_tvr (huge))
Masked Contrastive Pre-Training for Efficient Video-Text Retrieval arXiv:2212.00986
VideoonMSR-VTT-1kA
text-to-video R@5· uses extra data· 2022-12-02
63.1
best: 84.5 (HunYuan_tvr (huge))
Masked Contrastive Pre-Training for Efficient Video-Text Retrieval arXiv:2212.00986
Video RetrievalonMSR-VTT-1kA
text-to-video Median Rank· uses extra data· 2022-12-02
3
best: 13 (JSFusion)
Masked Contrastive Pre-Training for Efficient Video-Text Retrieval arXiv:2212.00986
Video RetrievalonMSR-VTT-1kA
text-to-video R@1· uses extra data· 2022-12-02
38.9
best: 62.9 (HunYuan_tvr (huge))
Masked Contrastive Pre-Training for Efficient Video-Text Retrieval arXiv:2212.00986
Video RetrievalonMSR-VTT-1kA
text-to-video R@10· uses extra data· 2022-12-02
73.9
best: 90.8 (HunYuan_tvr (huge))
Masked Contrastive Pre-Training for Efficient Video-Text Retrieval arXiv:2212.00986
Video RetrievalonMSR-VTT-1kA
text-to-video R@5· uses extra data· 2022-12-02
63.1
best: 84.5 (HunYuan_tvr (huge))
Masked Contrastive Pre-Training for Efficient Video-Text Retrieval arXiv:2212.00986

Robots2 results

Continuous ControlonCart Pole (OpenAI Gym)
Score· 2017-09-01
178.3
SOTA
Mean Actor Critic arXiv:1709.00503
Continuous ControlonLunar Lander (OpenAI Gym)
Score· 2017-09-01
163.5
SOTA
Mean Actor Critic arXiv:1709.00503

Methodology2 results

3DonCart Pole (OpenAI Gym)
Score· 2017-09-01
178.3
SOTA
Mean Actor Critic arXiv:1709.00503
3DonLunar Lander (OpenAI Gym)
Score· 2017-09-01
163.5
SOTA
Mean Actor Critic arXiv:1709.00503

Medical2 results

3D Face ModellingonCart Pole (OpenAI Gym)
Score· 2017-09-01
178.3
SOTA
Mean Actor Critic arXiv:1709.00503
3D Face ModellingonLunar Lander (OpenAI Gym)
Score· 2017-09-01
163.5
SOTA
Mean Actor Critic arXiv:1709.00503