Our new X account is live! Follow @wizwand_team for updates

Deep Research Report Generation on DeepResearch Bench

52.84Comprehensiveness

tavily-research

Updated 4d ago

Evaluation Results

Method
tavily-research 2026.01	52.84	52.44	53.59	51.92	49.21
Tavily Research 2026.01	52.84	52.44	53.59	51.92	49.21
ADORE 2026.01	52.22	52.65	54.37	51.11	52.18
CellCog 2026.01	52.17	51.94	51.9	51.37	51.94
ThinkDepthAI 2026.01	52.02	52.43	53.88	52.04	50.12
WebWeaver 2026.02	51.45	50.58	50.02	50.81	49.79
AgentCPM-Report (Pipeline RL) 2026.02	50.54	50.11	52.64	48.87	44.17
RhinoInsigh 2026.02	50.51	50.92	51.45	51.72	50
LangChain 2026.01	50.06	50.6	50.76	51.31	49.72
Salesforce Air 2026.01	50	50.65	51.09	50.77	50.32
LangChain 2026.01	49.8	49.33	47.34	51.05	48.99
Gemini-2.5-Pro-deepresearch 2026.02	49.51	49.71	49.45	50.12	50
gemini-2.5-pro-deepresearch 2026.01	49.51	49.71	49.45	50.12	50
Gemini 2.5 Pro 2026.01	49.51	49.71	49.45	50.12	50
Enterprise DR 2026.02	49.01	49.86	50.28	50.03	49.98
AgentCPM-Report (Atomic RL) 2026.02	48.7	48.81	51.36	48.64	42.25
OpenAI-deepresearch 2026.02	46.46	46.45	43.73	49.39	47.22
openai-deep-research 2026.01	46.46	46.45	43.73	49.39	47.22
OpenAI Deep Research 2026.01	46.46	46.45	43.73	49.39	47.22
AgentCPM-Report (SFT) 2026.02	46.24	46.73	48.1	47.61	41.79
Claude-research 2026.02	45.34	45	42.79	47.58	44.66
claude-research 2026.01	45.34	45	42.79	47.58	44.66
Claude Research 2026.01	45.34	45	42.79	47.58	44.66
WebWeaver 2026.02	45.15	46.77	45.78	49.21	47.34
Doubao-research 2026.02	44.84	44.34	40.56	47.95	44.69
deepresearcher-reflect-evolve 2026.01	43.44	46.21	45.48	48.99	48.21
IntentRL clarify 2026.02	43.1	45.27	45.02	44.04	48.5
DR Tulu-8B 2026.02	41.7	-	41.8	48.2	41.3
IntentRL clarify 2026.02	41.49	43.65	44.06	43.19	47.04
Learn-to-Ask clarify 2026.02	40.87	43.66	43.43	43.07	49.42
IntentRL clarify 2026.02	40.71	44.86	40.07	42.71	50.78
CollabLLM clarify 2026.02	40.37	43.13	43.28	42.11	48.83
IntentRL clarify 2026.02	39.9	42.14	42.17	41.98	45.39
CollabLLM clarify 2026.02	39.65	41.86	42.16	40.4	46.83
Learn-to-Ask clarify 2026.02	39.62	41.81	41.87	40.51	46.88
WebThinker-32B-DPO 2026.02	39.4	-	35.4	46	43.5
Learn-to-Ask clarify 2026.02	39.16	41.12	41.08	40.31	45.99
perplexity-research 2026.01	39.1	40.46	35.65	46.11	43.08
Qwen clarify 2026.02	38.6	40.72	40.66	39.07	46.48
CollabLLM clarify 2026.02	38.2	40.39	40.23	39.52	45.17
nvidia-aiq-research-assistant 2026.01	37.98	40.52	38.39	44.59	42.63
OpenAI clarify 2026.02	37.82	40.26	36.87	40.09	50.76
Tell Me More clarify 2026.02	37.44	40.56	40.42	38.45	48.24
no clarify 2026.02	37.12	39.42	39.1	37.78	45.64
no clarify 2026.02	36.92	39.39	39.31	37.27	46.32
no clarify 2026.02	36.66	39.41	38.17	37.74	48.06
Tell Me More clarify 2026.02	36.47	39.32	39.22	37.08	46.65
Learn-to-Ask clarify 2026.02	36.24	41.5	36.95	40.61	50.48
Tell Me More clarify 2026.02	36.21	38.58	37.95	36.61	45.5
grok-deeper-search 2026.01	36.08	38.22	30.89	46.59	42.17
CollabLLM clarify 2026.02	35.87	40.12	37.28	38.46	50.05
WebShaper-32B 2026.02	31.58	34.93	26.17	44.81	40.38
Tell Me More clarify 2026.02	31.47	36.99	32.8	34.1	48.08
no clarify 2026.02	30.46	36.62	30.5	34.62	48.42