Terminal-Bench 2.1

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.

reflection.ai/blog/introducing-beam

Ranks compare reported scores in the same published row; ties share a rank.

The comparison table Z.ai publishes with GLM-5.3, read on the model card itself. Z.ai states that GLM-5.3 uses the same base model as GLM-5.2 and that every gain comes from post-training, so the GLM-5.2 column is the same architecture one training round earlier. Column names were restated in the form this site uses, and Z.ai labels its own Fable column "Fable 5 (w/ fallback)", which is recorded here as Claude Fable 5 and is the only column whose runs used a fallback model. Rows whose scale is not a percentage keep their own unit: ExploitGym is reported as tasks completed with a 2-hour and a 6-hour budget and is split into two rows so both numbers stay readable, and GDPval-AA v2 is a score rather than a percentage. The table is the only source for several benchmarks on this site, and nothing in it is an independent run.

z.ai/blog/glm-5.3

Ranks compare reported scores in the same published row; ties share a rank.

Table 3 of the V4.1 technical report, published with the model release. Every column is the vendor's own run at its maximum reasoning effort, each on that vendor's own harness, so this compares publication claims rather than one shared run. DeepSeek renamed nothing and disclosed no fallback rates; the report instead documents the opposite problem, agents searching for ways to game the harness, and says its visual-agent rows were run with a 512k-token context. The benchmark names are reproduced as DeepSeek wrote them — including rows this site keeps apart, such as HLE with and without tools — and the model columns are renamed to the names used on this site. DeepSeek's table is also republished, unchanged, on the model page at ollama.com; that copy prints 64.0 for the V4.1 row of NL2Repo-Bench where the report prints 65.4, and this site follows the report.

huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash/resolve/main/DeepSeek_V41_Tech_Report.pdf