Reflection AI
Introducing Beam: model capability comparisons · 5 October 2026
| Rank | Model | Score |
|---|---|---|
| 5 | Beam | 49.7% |
| 6 | Inkling | 46.1% |
| 7 | Nemotron 3 Ultra | 44.6% |
| 1 | GLM 5.3 | 59.0% |
| 2 | Kimi K3 | 58.7% |
| 3 | Qwen3.8 Max | 52.1% |
| 4 | DeepSeek V4.1 Flash | 52.0% |
Ranks compare reported scores in the same published row; ties share a rank.
Reflection AI’s four capability tables, read 6 October 2026. All 21 rows and eight model columns are transcribed; NR means not reported and remains blank. The source’s Qwen 3.8 Max column uses this catalogue’s Qwen3.8 Max spelling. Beam results are publisher reports; Reflection AI cites Artificial Analysis and Datacurve for comparison-model evaluations. The announcement does not specify a common harness, effort or trial count for every row. Ranks are derived within each published row from reported values only, with ties sharing a rank; they do not establish an independent or overall model ranking. AutomationBench uses the public split; AA-Omniscience is an index on the public split only, calculated by Reflection AI. BrowseComp and DeepSearchQA use context management. AA-LCR has no stated version. These settings remain separate from other source fields.