RECON
Research agents find and verify several facts about identified people on the open web without mixing up people with similar names.
The benchmark covers 514 human-verified facts about 140 people. Sixtyfour's page lists 23 systems and reports weighted accuracy, precision and recall.
- Made by
- Sixtyfour
- Released
- April 2026
- Kind
- Deep research
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Agent task
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- Browser
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- A host
- In views
- Agents
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 21st, 2026
Sixtyfour XHigh tops the leaderboard with 70.6% Grok 4.20 Multi-agent leads with 36.2% among models released by September 2026
Best score per entry from the benchmark's own leaderboard, read on November 21st, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Grok 4.20 Multi-agent, at 36.2%. This view shows only models we track, each at its best.
The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6.1 Terra
- and 12 more
- 70.6 Sixtyfour XHigh
- 54.3 Sixtyfour High
- 48.4 Sixtyfour Scout
- 44.7 Sixtyfour Medium
- 41.1 Parallel Ultra 2x
- 37.5 Parallel Ultra 8x
- 36.2 Grok 4.20 Multi-agent
- 36.0 Grok 4.6
- 30.9 Grok 4.3
- 28.8 Sixtyfour Low
- 27.2 Parallel Ultra
- 27.0 Kimi K3
- 26.3 Claude Opus 5.5
- 25.1 GPT-6 Astra
- 23.9 Exa agent xhigh
- 23.0 GPT-6.1 Sol
- 20.4 GPT-5.6 Sol
- 13.4
Gemini 3.1 Pro
- 12.6 Claude Sonnet 5
- 12.5
DeepSeek-V4-Flash
- 12.3
DeepSeek-V4-Pro
- 3.70 GLM-5.3
- 1.60 Claude Haiku 4.5
- 1 Sixtyfour XHigh 70.6%
- 2 Sixtyfour High 54.3%
- 3 Sixtyfour Scout 48.4%
- 4 Sixtyfour Medium 44.7%
- 5 Parallel Ultra 2x 41.1%
- 6 Parallel Ultra 8x 37.5%
- 7 Grok 4.20 Multi-agent 36.2%
- 8 Grok 4.6 36%
- 9 Grok 4.3 30.9%
- 10 Sixtyfour Low 28.8%
- 11 Parallel Ultra 27.2%
- 12 Kimi K3 27%
- 13 Claude Opus 5.5 26.3%
- 14 GPT-6 Astra 25.1%
- 15 Exa agent xhigh 23.9%
- 16 GPT-6.1 Sol max 23%
- 17 GPT-5.6 Sol xhigh 20.4%
- 18
Gemini 3.1 Pro 13.4%
- 19 Claude Sonnet 5 12.6%
- 20
DeepSeek-V4-Flash 12.5%
- 21
DeepSeek-V4-Pro 12.3%
- 22 GLM-5.3 3.70%
- 23 Claude Haiku 4.5 1.60%
Source: Official RECON leaderboard
- 1 Grok 4.20 Multi-agent 36.2%
- 2 Grok 4.6 36%
- 3 Grok 4.3 30.9%
- 4 Kimi K3 27%
- 5 Claude Opus 5.5 26.3%
- 6 GPT-6 Astra 25.1%
- 7 GPT-6.1 Sol max 23%
- 8 GPT-5.6 Sol xhigh 20.4%
- 9
Gemini 3.1 Pro 13.4%
- 10 Claude Sonnet 5 12.6%
- 11
DeepSeek-V4-Flash 12.5%
- 12
DeepSeek-V4-Pro 12.3%
- 13 GLM-5.3 3.70%
- 14 Claude Haiku 4.5 1.60%
Source: Official RECON leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Sixtyfour XHigh | 70.6% | Official leaderboard | ||
| 2 | Sixtyfour High | 54.3% | Official leaderboard | ||
| 3 | Sixtyfour Scout | 48.4% | Official leaderboard | ||
| 4 | Sixtyfour Medium | 44.7% | Official leaderboard | ||
| 5 | Parallel Ultra 2x | 41.1% | Official leaderboard | ||
| 6 | Parallel Ultra 8x | 37.5% | Official leaderboard | ||
| 7 | Grok 4.20 Multi-agent | 36.2% | Mar 2026 | Official leaderboard | |
| 8 | Grok 4.6 | 36% | Aug 2026 | Official leaderboard | |
| 9 | Grok 4.3 | 30.9% | Apr 2026 | Official leaderboard | |
| 10 | Sixtyfour Low | 28.8% | Official leaderboard | ||
| 11 | Parallel Ultra | 27.2% | Official leaderboard | ||
| 12 | Kimi K3 | 27% | Jul 2026 | Official leaderboard | |
| 13 | Claude Opus 5.5 | 26.3% | Sep 2026 | Official leaderboard | |
| 14 | GPT-6 Astra | 25.1% | Sep 2026 | Official leaderboard | |
| 15 | Exa agent xhigh | 23.9% | Official leaderboard | ||
| 16 | GPT-6.1 Sol | 23% | max | Sep 2026 | Official leaderboard |
| 17 | GPT-5.6 Sol | 20.4% | xhigh | Jul 2026 | Official leaderboard |
| 18 | | 13.4% | Feb 2026 | Official leaderboard | |
| 19 | Claude Sonnet 5 | 12.6% | Jun 2026 | Official leaderboard | |
| 20 | | 12.5% | Apr 2026 | Official leaderboard | |
| 21 | | 12.3% | Apr 2026 | Official leaderboard | |
| 22 | GLM-5.3 | 3.70% | Aug 2026 | Official leaderboard | |
| 23 | Claude Haiku 4.5 | 1.60% | Oct 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Grok 4.20 Multi-agent | 36.2% | Mar 2026 | Official leaderboard | |
| 2 | Grok 4.6 | 36% | Aug 2026 | Official leaderboard | |
| 3 | Grok 4.3 | 30.9% | Apr 2026 | Official leaderboard | |
| 4 | Kimi K3 | 27% | Jul 2026 | Official leaderboard | |
| 5 | Claude Opus 5.5 | 26.3% | Sep 2026 | Official leaderboard | |
| 6 | GPT-6 Astra | 25.1% | Sep 2026 | Official leaderboard | |
| 7 | GPT-6.1 Sol | 23% | max | Sep 2026 | Official leaderboard |
| 8 | GPT-5.6 Sol | 20.4% | xhigh | Jul 2026 | Official leaderboard |
| 9 | | 13.4% | Feb 2026 | Official leaderboard | |
| 10 | Claude Sonnet 5 | 12.6% | Jun 2026 | Official leaderboard | |
| 11 | | 12.5% | Apr 2026 | Official leaderboard | |
| 12 | | 12.3% | Apr 2026 | Official leaderboard | |
| 13 | GLM-5.3 | 3.70% | Aug 2026 | Official leaderboard | |
| 14 | Claude Haiku 4.5 | 1.60% | Oct 2025 | Official leaderboard |
Rankings by part
We read 2 parts from the benchmark’s own leaderboard: Precision and Recall. Each ranks models on one part of the test. GPT-6 Astra leads Precision and Grok 4.20 Multi-agent leads Recall. Arrows show how far a model moved from its overall rank among the models we track.
Precision
14 models we track have a score here.
- 1 GPT-6 Astra ↑5 90.6%
- 2 GPT-6.1 Sol ↑5 85.1%
- 3 Claude Opus 5.5 ↑2 83.3%
- 4 Kimi K3 80.1%
- 5 Grok 4.6 ↓3 77.4%
- 6 Grok 4.20 Multi-agent ↓5 77%
- 7 Grok 4.3 ↓4 76.2%
- 8
DeepSeek-V4-Flash ↑3 75%
- 9 GPT-5.6 Sol ↓1 74.2%
- 10
DeepSeek-V4-Pro ↑2 74%
Recall
14 models we track have a score here.
- 1 Grok 4.20 Multi-agent 51.6%
- 2 Grok 4.6 50.8%
- 3 Grok 4.3 44.9%
- 4 Kimi K3 36%
- 5 Claude Opus 5.5 32.9%
- 6 GPT-5.6 Sol ↑2 31.3%
- 7 GPT-6 Astra ↓1 28%
- 8 GPT-6.1 Sol ↓1 27.8%
- 9
Gemini 3.1 Pro 23.2%
- 10 Claude Sonnet 5 20%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official RECON leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official RECON leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Tool use
- AutomationBench In use Agent completes end-to-end business workflows inside a simulated company exposing dozens of REST APIs. Graded on resulting state.
Gemini 4 Neon 56.3%
- MCP Atlas In use Multi-step workflows over real MCP servers. Scores tool-use competency on realistic tasks.
Gemini 4 Argon 90.7%
- BFCL V4 In use Models call functions and tools, including multi-turn agentic tasks with web search and memory. Checked against expected calls and outcomes.
Qwen3.7-Max 75%
- τ³-bench Banking In use Agents act as banking customer-service reps over many turns with a simulated user, following policy. Pass^1 on the final database state.
Qwen 3.8 Max 55.1%
- Toolathlon-Verified In use 108 long-horizon tasks across 32 apps through about 600 MCP tools. Execution-based checkers inspect final environment state. GLM-5.3-Flash 78.4%
- DeepSearchQA In use Questions that need multi-step search and synthesis. Final answers graded against references. Kimi K3 95%
Data audit
All 11 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 5 pass
- Pass Independent runs Scores from the official leaderboard (23 entries).
- Pass Models scored 14 models we track, plus 9 other entries on its leaderboard.
- Pass Newest score The newest is from September 2026, for GPT-6.1 Sol.
- Pass Frontier models 3 of the top 10 have a score, led by GPT-6 Astra (#4).
- Pass Headroom The best is 36.2%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on sixtyfour.ai: 14 rows for models we track and 9 other entries at the last read.
- Pass Last read November 21st, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.