File size: 14,713 Bytes
b0c0df0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
# Current Tasks

> () indicates the task name in the lmms_eval. The task name is also used to specify the dataset in the configuration file.

**Note:** This documentation is manually maintained. For the most up-to-date and complete list of supported tasks, please run:
```bash
python -m lmms_eval --tasks list
```

To see the number of questions in each task:
```bash
python -m lmms_eval --tasks list_with_num
```
(Note: `list_with_num` will download all datasets and may require significant time and storage)

## 1. Image tasks:

- [AI2D](https://arxiv.org/abs/1603.07396) (ai2d)
- [ChartQA](https://github.com/vis-nlp/ChartQA) (chartqa)
- [COCO Caption](https://github.com/tylin/coco-caption) (coco_cap)
  - COCO 2014 Caption (coco2014_cap)
    - COCO 2014 Caption Validation (coco2014_cap_val)
    - COCO 2014 Caption Test (coco2014_cap_test)
  - COCO 2017 Caption (coco2017_cap)
    - COCO 2017 Caption MiniVal (coco2017_cap_val)
    - COCO 2017 Caption MiniTest (coco2017_cap_test)
- [ConBench](https://github.com/foundation-multimodal-models/ConBench) (conbench)
- [DetailCaps-4870](https://github.com/foundation-multimodal-models/CAPTURE) (detailcaps)
- [DOCVQA](https://github.com/anisha2102/docvqa) (docvqa)
  - DOCVQA Validation (docvqa_val)
  - DOCVQA Test (docvqa_test)
- [Ferret](https://github.com/apple/ml-ferret) (ferret)
- [Flickr30K](https://github.com/BryanPlummer/flickr30k_entities) (flickr30k)
  - Flickr30K Test (flickr30k_test)
- [GQA](https://cs.stanford.edu/people/dorarad/gqa/index.html) (gqa)
- [GQA-ru](https://huggingface.co/datasets/deepvk/GQA-ru) (gqa_ru)
- [II-Bench](https://github.com/II-Bench/II-Bench) (ii_bench)
- [IllusionVQA](https://illusionvqa.github.io/) (illusionvqa)
- [Infographic VQA](https://www.docvqa.org/datasets/infographicvqa) (infovqa)
  - Infographic VQA Validation (infovqa_val)
  - Infographic VQA Test (infovqa_test)
- [LiveBench](https://huggingface.co/datasets/lmms-lab/LiveBench) (live_bench)
  - LiveBench 06/2024 (live_bench_2406)
  - LiveBench 07/2024 (live_bench_2407)
- [LLaVA-Bench-Wilder](https://huggingface.co/datasets/lmms-lab/LLaVA-Bench-Wilder) (llava_wilder_small)
- [LLaVA-Bench-COCO](https://llava-vl.github.io/) (llava_bench_coco)
- [LLaVA-Bench](https://llava-vl.github.io/) (llava_in_the_wild)
- [MathVerse](https://github.com/ZrrSkywalker/MathVerse) (mathverse)
  - MathVerse Text Dominant (mathverse_testmini_text_dominant)
  - MathVerse Text Only (mathverse_testmini_text_only)
  - MathVerse Text Lite (mathverse_testmini_text_lite)
  - MathVerse Vision Dominant (mathverse_testmini_vision_dominant)
  - MathVerse Vision Intensive (mathverse_testmini_vision_intensive)
  - MathVerse Vision Only (mathverse_testmini_vision_only)
- [MathVista](https://mathvista.github.io/) (mathvista)
  - MathVista Validation (mathvista_testmini)
  - MathVista Test (mathvista_test)
- [MMBench](https://github.com/open-compass/MMBench) (mmbench)
  - MMBench English (mmbench_en)
    - MMBench English Dev (mmbench_en_dev)
    - MMBench English Test (mmbench_en_test)
  - MMBench Chinese (mmbench_cn)
    - MMBench Chinese Dev (mmbench_cn_dev)
    - MMBench Chinese Test (mmbench_cn_test)
- [MME](https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models/tree/Evaluation) (mme)
- [MME-RealWorld](https://mme-realworld.github.io/) (mmerealworld)
  - MME-RealWorld English (mmerealworld)
  - MME-RealWorld Mini (mmerealworld_lite)
  - MME-RealWorld Chinese (mmerealworld_cn)
- [MMRefine](http://mmrefine.github.io/) (mmrefine)
- [MMStar](https://github.com/MMStar-Benchmark/MMStar) (mmstar)
- [MMUPD](https://huggingface.co/datasets/MM-UPD/MM-UPD) (mmupd)
  - MMUPD Base (mmupd_base)
    - MMAAD Base (mmaad_base)
    - MMIASD Base (mmiasd_base)
    - MMIVQD Base (mmivqd_base)
  - MMUPD Option (mmupd_option)
    - MMAAD Option (mmaad_option)
    - MMIASD Option (mmiasd_option)
    - MMIVQD Option (mmivqd_option)
  - MMUPD Instruction (mmupd_instruction)
    - MMAAD Instruction (mmaad_instruction)
    - MMIASD Instruction (mmiasd_instruction)
    - MMIVQD Instruction (mmivqd_instruction)
- [MMVet](https://github.com/yuweihao/MM-Vet) (mmvet)
- [Multilingual LlaVa Bench](https://huggingface.co/datasets/gagan3012/multilingual-llava-bench)
  - llava_in_the_wild_arabic
  - llava_in_the_wild_bengali
  - llava_in_the_wild_chinese
  - llava_in_the_wild_french
  - llava_in_the_wild_hindi
  - llava_in_the_wild_japanese
  - llava_in_the_wild_russian
  - llava_in_the_wild_spanish
  - llava_in_the_wild_urdu
- [NaturalBench](https://huggingface.co/datasets/BaiqiL/NaturalBench)  
- [NoCaps](https://nocaps.org/) (nocaps)
  - NoCaps Validation (nocaps_val)
  - NoCaps Test (nocaps_test)
- [OCRBench](https://github.com/Yuliang-Liu/MultimodalOCR) (ocrbench)
- [OKVQA](https://okvqa.allenai.org/) (ok_vqa)
  - OKVQA Validation 2014 (ok_vqa_val2014)
- [POPE](https://github.com/RUCAIBox/POPE) (pope)
- [RefCOCO](https://github.com/lichengunc/refer) (refcoco)
  - refcoco_seg_test
  - refcoco_seg_val
  - refcoco_seg_testA
  - refcoco_seg_testB
  - refcoco_bbox_test
  - refcoco_bbox_val
  - refcoco_bbox_testA
  - refcoco_bbox_testB
- [RefCOCO+](https://github.com/lichengunc/refer) (refcoco+)
  - refcoco+\_seg
    - refcoco+\_seg_val
    - refcoco+\_seg_testA
    - refcoco+\_seg_testB
  - refcoco+\_bbox
    - refcoco+\_bbox_val
    - refcoco+\_bbox_testA
    - refcoco+\_bbox_testB
- [RefCOCOg](https://github.com/lichengunc/refer) (refcocog)
  - refcocog_seg_test
  - refcocog_seg_val
  - refcocog_bbox_test
  - refcocog_bbox_val
- [ScienceQA](https://scienceqa.github.io/) (scienceqa_full)
  - ScienceQA Full (scienceqa)
  - ScienceQA IMG (scienceqa_img)
- [ScreenSpot](https://github.com/njucckevin/SeeClick) (screenspot)
  - ScreenSpot REC / Grounding (screenspot_rec)
  - ScreenSpot REG / Instruction Generation (screenspot_reg)
- [ST-VQA](https://rrc.cvc.uab.es/?ch=11) (stvqa)
- [synthdog](https://github.com/clovaai/donut) (synthdog)
  - synthdog English (synthdog_en)
  - synthdog Chinese (synthdog_zh)
- [TextCaps](https://textvqa.org/textcaps/) (textcaps)
  - TextCaps Validation (textcaps_val)
  - TextCaps Test (textcaps_test)
- [TextVQA](https://textvqa.org/) (textvqa)
  - TextVQA Validation (textvqa_val)
  - TextVQA Test (textvqa_test)
- [VCR-Wiki](https://github.com/tianyu-z/VCR)
  - VCR-Wiki English
    - VCR-Wiki English easy 100 (vcr_wiki_en_easy_100)
    - VCR-Wiki English easy 500 (vcr_wiki_en_easy_500)
    - VCR-Wiki English easy (vcr_wiki_en_easy)
    - VCR-Wiki English hard 100 (vcr_wiki_en_hard_100)
    - VCR-Wiki English hard 500 (vcr_wiki_en_hard_500)
    - VCR-Wiki English hard (vcr_wiki_en_hard)
  - VCR-Wiki Chinese
    - VCR-Wiki Chinese easy 100 (vcr_wiki_zh_easy_100)
    - VCR-Wiki Chinese easy 500 (vcr_wiki_zh_easy_500)
    - VCR-Wiki Chinese easy (vcr_wiki_zh_easy)
    - VCR-Wiki Chinese hard 100 (vcr_wiki_zh_hard_100)
    - VCR-Wiki Chinese hard 500 (vcr_wiki_zh_hard_500)
    - VCR-Wiki Chinese hard (vcr_wiki_zh_hard)
- [VibeEval](https://github.com/reka-ai/reka-vibe-eval) (vibe_eval)
- [VizWizVQA](https://vizwiz.org/tasks-and-datasets/vqa/) (vizwiz_vqa)
  - VizWizVQA Validation (vizwiz_vqa_val)
  - VizWizVQA Test (vizwiz_vqa_test)
- [VL-RewardBench](https://vl-rewardbench.github.io) (vl_rewardbench)
- [VQAv2](https://visualqa.org/) (vqav2)
  - VQAv2 Validation (vqav2_val)
  - VQAv2 Test (vqav2_test)
- [WebSRC](https://x-lance.github.io/WebSRC/) (websrc)
  - WebSRC Validation (websrc_val)
  - WebSRC Test (websrc_test)
- [WildVision-Bench](https://github.com/WildVision-AI/WildVision-Bench) (wildvision)
  - WildVision 0617(wildvision_0617)
  - WildVision 0630 (wildvision_0630)
- [SeedBench 2 Plus](https://huggingface.co/datasets/AILab-CVC/SEED-Bench-2-plus) (seedbench_2_plus)
- [SalBench](https://salbench.github.io/)
  - p3
  - p3_box
  - p3_box_img
  - o3
  - o3_box
  - o3_box_img

## 2. Multi-image tasks:

- [CMMMU](https://cmmmu-benchmark.github.io/) (cmmmu)
  - CMMMU Validation (cmmmu_val)
  - CMMMU Test (cmmmu_test)
- [HallusionBench](https://github.com/tianyi-lab/HallusionBench) (hallusion_bench_image)
- [ICON-QA](https://iconqa.github.io/) (iconqa)
  - ICON-QA Validation (iconqa_val)
  - ICON-QA Test (iconqa_test)
- [JMMMU](https://mmmu-japanese-benchmark.github.io/JMMMU/) (jmmmu)
- [LLaVA-NeXT-Interleave-Bench](https://huggingface.co/datasets/lmms-lab/LLaVA-NeXT-Interleave-Bench) (llava_interleave_bench)
  - llava_interleave_bench_in_domain
  - llava_interleave_bench_out_domain
  - llava_interleave_bench_multi_view
- [MIRB](https://github.com/ys-zong/MIRB) (mirb)
- [MMMU](https://mmmu-benchmark.github.io/) (mmmu)
  - MMMU Validation (mmmu_val)
  - MMMU Test (mmmu_test)
- [MMMU_Pro](https://huggingface.co/datasets/MMMU/MMMU_Pro)
  - MMMU Pro (mmmu_pro)
    - MMMU Pro Original (mmmu_pro_original)
    - MMMU Pro Vision (mmmu_pro_vision)
  - MMMU Pro COT (mmmu_pro_cot)
    - MMMU Pro Original COT (mmmu_pro_original_cot)
    - MMMU Pro Vision COT (mmmu_pro_vision_cot)
    - MMMU Pro Composite COT (mmmu_pro_composite_cot)
- [MMT Multiple Image](https://mmt-bench.github.io/) (mmt_mi)
  - MMT Multiple Image Validation (mmt_mi_val)
  - MMT Multiple Image Test (mmt_mi_test)
- [MuirBench](https://muirbench.github.io/) (muirbench)
- [MP-DocVQA](https://github.com/rubenpt91/MP-DocVQA-Framework) (multidocvqa)
  - MP-DocVQA Validation (multidocvqa_val)
  - MP-DocVQA Test (multidocvqa_test)
- [OlympiadBench](https://github.com/OpenBMB/OlympiadBench) (olympiadbench)
  - OlympiadBench Test English (olympiadbench_test_en)
  - OlympiadBench Test Chinese (olympiadbench_test_cn)
- [Q-Bench](https://q-future.github.io/Q-Bench/) (qbenchs_dev)
  - Q-Bench2-HF (qbench2_dev)
  - Q-Bench-HF (qbench_dev)
  - A-Bench-HF (abench_dev)
- [MEGA-Bench](https://tiger-ai-lab.github.io/MEGA-Bench/) (megabench)
  - MEGA-Bench Core (megabench_core)
  - MEGA-Bench Open (megabench_open)
  - MEGA-Bench Core single-image subset (megabench_core_si)
  - MEGA-Bench Open single-image subset (megabench_open_si)

## 3. Videos tasks:

- [ActivityNet-QA](https://github.com/MILVLG/activitynet-qa) (activitynetqa_generation)
- [SeedBench](https://github.com/AILab-CVC/SEED-Bench) (seedbench)
- [SeedBench 2](https://github.com/AILab-CVC/SEED-Bench) (seedbench_2)
- [CVRR-ES](https://github.com/mbzuai-oryx/CVRR-Evaluation-Suite) (cvrr)
  - cvrr_continuity_and_object_instance_count
  - cvrr_fine_grained_action_understanding
  - cvrr_interpretation_of_social_context
  - cvrr_interpretation_of_visual_context
  - cvrr_multiple_actions_in_a_single_video
  - cvrr_non_existent_actions_with_existent_scene_depictions
  - cvrr_non_existent_actions_with_non_existent_scene_depictions
  - cvrr_partial_actions
  - cvrr_time_order_understanding
  - cvrr_understanding_emotional_context
  - cvrr_unusual_and_physically_anomalous_activities
- [EgoSchema](https://github.com/egoschema/EgoSchema) (egoschema)
  - egoschema_mcppl
  - egoschema_subset_mcppl
  - egoschema_subset
- [LEMONADE](https://huggingface.co/datasets/amathislab/LEMONADE) (lemonade)
- [LongVideoBench](https://github.com/longvideobench/LongVideoBench)
- [MovieChat](https://github.com/rese1f/MovieChat) (moviechat)
  - Global Mode for entire video (moviechat_global)
  - Breakpoint Mode for specific moments (moviechat_breakpoint)
- [MLVU](https://github.com/JUNJIE99/MLVU) (mlvu)
- [MMT-Bench](https://mmt-bench.github.io/) (mmt)
  - MMT Validation (mmt_val)
  - MMT Test (mmt_test)
- [MVBench](https://github.com/OpenGVLab/Ask-Anything/blob/main/video_chat2/MVBENCH.md) (mvbench)

  - mvbench_action_sequence
  - mvbench_moving_count
  - mvbench_action_prediction
  - mvbench_episodic_reasoning
  - mvbench_action_antonym
  - mvbench_action_count
  - mvbench_scene_transition
  - mvbench_object_shuffle
  - mvbench_object_existence
  - mvbench_fine_grained_pose
  - mvbench_unexpected_action
  - mvbench_moving_direction
  - mvbench_state_change
  - mvbench_object_interaction
  - mvbench_character_order
  - mvbench_action_localization
  - mvbench_counterfactual_inference
  - mvbench_fine_grained_action
  - mvbench_moving_attribute
  - mvbench_egocentric_navigation

- [NExT-QA](https://github.com/doc-doc/NExT-QA) (nextqa)

  - NExT-QA Multiple Choice Test (nextqa_mc_test)
  - NExT-QA Open Ended Validation (nextqa_oe_val)
  - NExT-QA Open Ended Test (nextqa_oe_test)

- [PerceptionTest](https://github.com/google-deepmind/perception_test)

  - PerceptionTest Test
    - perceptiontest_test_mc
    - perceptiontest_test_mcppl
  - PerceptionTest Validation
    - perceptiontest_val_mc
    - perceptiontest_val_mcppl

- [TempCompass](https://github.com/llyx97/TempCompass) (tempcompass)

  - tempcompass_multi_choice
  - tempcompass_yes_no
  - tempcompass_caption_matching
  - tempcompass_captioning


- [TemporalBench](https://huggingface.co/datasets/microsoft/TemporalBench) (temporalbench)

  - temporalbench_short_qa
  - temporalbench_long_qa
  - temporalbench_short_caption


- [Vatex](https://eric-xw.github.io/vatex-website/index.html) (vatex)

  - Vatex Chinese (vatex_val_zh)
  - Vatex Test (vatex_test)

- [VideoDetailDescription](https://huggingface.co/datasets/lmms-lab/VideoDetailCaption) (video_dc499)
- [Video-ChatGPT](https://github.com/mbzuai-oryx/Video-ChatGPT) (videochatgpt)
  - Video-ChatGPT Generic (videochatgpt_gen)
  - Video-ChatGPT Temporal (videochatgpt_temporal)
  - Video-ChatGPT Consistency (videochatgpt_consistency)
- [Video-MME](https://video-mme.github.io/) (videomme)
- [Vinoground](https://vinoground.github.io) (vinoground)
- [VITATECS](https://github.com/lscpku/VITATECS) (vitatecs)

  - VITATECS Direction (vitatecs_direction)
  - VITATECS Intensity (vitatecs_intensity)
  - VITATECS Sequence (vitatecs_sequence)
  - VITATECS Compositionality (vitatecs_compositionality)
  - VITATECS Localization (vitatecs_localization)
  - VITATECS Type (vitatecs_type)

- [WorldQA](https://zhangyuanhan-ai.github.io/WorldQA/) (worldqa)

  - WorldQA Generation (worldqa_gen)
  - WorldQA Multiple Choice (worldqa_mc)

- [YouCook2](http://youcook2.eecs.umich.edu/) (youcook2_val)

- [VDC](https://github.com/rese1f/aurora) (vdc)
  - VDC Detailed Caption (detailed_test)
  - VDC Camera Caption (camera_test)
  - VDC Short Caption (short_test)
  - VDC Background Caption (background_test)
  - VDC Main Object Caption (main_object_test)

- [VideoEval-Pro](https://tiger-ai-lab.github.io/VideoEval-Pro/) (videoevalpro)


## 4. Text Tasks

- [GSM8K](https://github.com/openai/grade-school-math) (gsm8k)
- [HellaSwag](https://rowanzellers.com/hellaswag/) (hellaswag)
- [IFEval](https://github.com/google-research/google-research/tree/master/instruction_following_eval) (ifeval)
- [MMLU](https://github.com/hendrycks/test) (mmlu)
- [MMLU_pro](https://github.com/TIGER-AI-Lab/MMLU-Pro) (mmlu_pro)