Research and deep-research agents compared: public evidence
Informational only. Scores summarize cited public evidence under published rules; they are not a guarantee, endorsement, certification or ranking of quality.
Data as of 2026-10-20 (Scoring rules v0.1); entries last reviewed 2026-10-16 to 2026-10-19. Generated from agents.json; values match each entry page.
Scope of each entry
Read the scope before comparing: entries cover different products, versions and modes.
- Consensus: Consensus academic search and answer engine (Quick, Pro and Deep modes). The Deep Search agent (July 2025) and Research Agent (2026) were not separately tested.
- Elicit: Elicit is a commercial AI research assistant that searches academic papers and supports systematic-review steps (screening and data extraction).
- OpenAI Deep Research: OpenAI Deep Research is a commercial ChatGPT feature that writes cited research reports.
- Gemini Deep Research: Gemini Deep Research is a Google feature, in the Gemini app and as a Gemini API agent, that plans multi-step web research and writes cited reports.
- Claude Research: The Research mode in Claude's web, desktop and mobile apps (launched April 2025). Plain Claude models used via the API are not covered.
- STORM / Co-STORM (knowledge-storm library): The open-source knowledge-storm library (v1.0.0 to 1.1.1, Sept 2024 to Sept 2025), covering the STORM (automatic) and Co-STORM (human-in-the-loop) modes, run with a language model and search engine chosen by the user. The 2024 NAACL code branch is historical context. The hosted research preview is not covered.
- GPT Researcher: GPT Researcher is an open-source research agent that writes cited reports.
- Kimi Researcher (Kimi Deep Research): Moonshot AI's Deep Research mode in Kimi, powered by the Kimi-Researcher model (launched June 2025).
- Manus: Manus, a general-purpose AI agent from Butterfly Effect for research and multi-step digital tasks. The current product is Manus 2.0 (28 September 2026), which the vendor describes as a new architecture.
- Academic search tools (Elicit, Consensus) are mostly tested on finding and summarising papers; general deep-research agents are tested on open web research tasks. Scores are not directly comparable across these groups.
Scores and evidence
Listed alphabetically within each group, not by score. Factor scores are 0–100; see the methodology for weights and evidence grades.
Academic search and review tools
| Agent | Overall score | Evidence grade | Completion | Disputes | Adherence | Evidence quality | Counted sources (peer-reviewed) | Last reviewed |
|---|---|---|---|---|---|---|---|---|
| Consensus | 62 | B | 50 | 80 | 50 | 75 | 6 (6) | |
| Elicit | 68 | A | 55 | 80 | 55 | 85 | 10 (9) |
General research and deep-research agents
| Agent | Overall score | Evidence grade | Completion | Disputes | Adherence | Evidence quality | Counted sources (peer-reviewed) | Last reviewed |
|---|---|---|---|---|---|---|---|---|
| Claude Research | 58 | B- | 50 | 75 | 50 | 60 | 4 (3) | |
| Gemini Deep Research | 63 | B | 60 | 65 | 55 | 72 | 8 (2) | |
| GPT Researcher | 53 | B- | 55 | 40 | 50 | 65 | 3 (2) | |
| OpenAI Deep Research | 65 | B | 60 | 65 | 60 | 75 | 5 (2) | |
| STORM / Co-STORM (knowledge-storm library) | 56 | B | 50 | 55 | 45 | 75 | 7 (5) | |
| Kimi Researcher (Kimi Deep Research) | — | Insufficient evidence | — | — | — | — | 2 (1) | |
| Manus | — | Insufficient evidence | — | — | — | — | 0 (0) |
Entries marked Insufficient evidence have fewer than 3 counted independent performance sources and no overall score.
What the evidence does and doesn’t show
- Scores summarize the counted independent sources for each entry; they are not production outcomes and are not a ranking of quality.
- Entries are reviewed separately, with different sources and dates; a higher overall score does not mean one agent is better for a given task.
Claude Research
4 counted independent performance sources (3 peer-reviewed). Noted uncertainties from the entry page:
- All counted tests used 2025 versions (Claude 3.7 / Opus 4 / Sonnet 4.5 era); Research now runs on Claude Opus 5.5, which has not been independently tested.
- DeepResearchEval labels the system "Claude-Sonnet-4.5" although its collection dates precede that model's release.
Consensus
6 counted independent performance sources (6 peer-reviewed). Noted uncertainties from the entry page:
- Tests mostly covered standard or Pro search; Deep Search and Research Agent not separately tested.
- Citation Grounding (2026) postdates all tests.
Elicit
10 counted independent performance sources (9 peer-reviewed). Noted uncertainties from the entry page:
- Most tests used paid tiers (Plus, Pro, Review/Systematic Review workflow); the free Basic tier was not tested separately.
- Elicit changed often (credits to subscription in July 2024; high-accuracy default from May 2025; Systematic Review workflow); the oldest study used April 2023 searches.
Gemini Deep Research
8 counted independent performance sources (2 peer-reviewed). Noted uncertainties from the entry page:
- The current product uses Gemini 3.1 Pro (April 2026); five of the seven sources tested Gemini 2.5 Pro versions from 2025, and one tested 3 Pro.
- Three sources (DeepResearch Bench, DeepResearch Bench II, DeepResearchEval) used a Gemini model as the main judge; DeepResearch Bench also used Gemini Deep Research reports as its references.
GPT Researcher
3 counted independent performance sources (2 peer-reviewed). Noted uncertainties from the entry page:
- Results depend on the AI model and search provider used; the evaluations used differing, mostly 2025-era configurations.
- Fix status of some advisories was not independently verified.
Kimi Researcher (Kimi Deep Research)
2 counted independent performance sources (1 peer-reviewed). Noted uncertainties from the entry page:
- Only two independent evaluations found; one is a preprint with competitor co-authors.
- Whether Deep Research now uses newer Kimi models (K2.5–K3) is not stated; the help page still names Kimi-Researcher.
Manus
0 counted independent performance sources (0 peer-reviewed). Noted uncertainties from the entry page:
- All independent tests found used 2025 versions; Manus 2.0 is a new architecture per the vendor and is untested.
- Vendor-reported GAIA scores and Manus 2.0 efficiency figures are not used.
OpenAI Deep Research
5 counted independent performance sources (2 peer-reviewed). Noted uncertainties from the entry page:
- The underlying model has changed over time; most independent tests used 2025 versions.
- No independent test of usage-limit or permission adherence was found.
STORM / Co-STORM (knowledge-storm library)
7 counted independent performance sources (5 peer-reviewed). Noted uncertainties from the entry page:
- Most independent results use LLM judges and relative scores, so they show how STORM compares with other systems rather than an absolute success rate.
- Results depend on the language model and search engine. Most studies used GPT-4o-era or open models.
Related: Perplexity. Perplexity is listed in the Verification category, scoped to citation-backed answering, so it is not included here.
Citation guidance
When quoting a score, include the agent name, overall score and evidence grade, the as-of date (last_reviewed, or as_of for a feed item), and a link to the entry page, e.g. "Aider (open-source): 52/100, evidence grade A, as of 2026-10-17 (Agent Reputation & Trust Clearinghouse, CC BY 4.0, https://www.agentclearinghouse.org/agents/aider.html)". Say that the score is informational and not a guarantee, endorsement, certification or ranking. Do not present directory or feed order as a ranking. More examples: https://www.agentclearinghouse.org/citing.html
More
- Methodology (factors, weights, evidence grades)
- Changelog and update feed
- For agents / data (JSON, CSV, license)